An Automatic detection method of lung cancers including Ground Glass Opacities from Chest X-ray CT

人工智能是一门新兴的具有挑战力的学科。

自人工智能诞生以来,发展迅速,产生了许多分支。

诸如强化学习、模拟环境、智能硬件、机器学习等。

但是,在当前人工智能技术迅猛发展,为人们的生活带来许多便利。

下面是搜索整理的人工智能英文参考文献的分享，供大家借鉴参考。

人工智能英文参考文献一：[1]Lars Egevad,Peter Str?m,Kimmo Kartasalo,Henrik Olsson,Hemamali Samaratunga,Brett Delahunt,Martin Eklund. The utility of artificial intelligence in the assessment of prostate pathology[J]. Histopathology,2020,76(6).[2]Rudy van Belkom. The Impact of Artificial Intelligence on the Activities ofa Futurist[J]. World Futures Review,2020,12(2).[3]Reza Hafezi. How Artificial Intelligence Can Improve Understanding in Challenging Chaotic Environments[J]. World Futures Review,2020,12(2).[4]Alejandro Díaz-Domínguez. How Futures Studies and Foresight Could Address Ethical Dilemmas of Machine Learning and Artificial Intelligence[J]. World Futures Review,2020,12(2).[5]Russell T. Warne,Jared Z. Burton. Beliefs About Human Intelligence in a Sample of Teachers and Nonteachers[J]. Journal for the Education of the Gifted,2020,43(2).[6]Russell Belk,Mariam Humayun,Ahir Gopaldas. Artificial Life[J]. Journal of Macromarketing,2020,40(2).[7]Walter Kehl,Mike Jackson,Alessandro Fergnani. Natural Language Processing and Futures Studies[J]. World Futures Review,2020,12(2).[8]Anne Boysen. Mine the Gap: Augmenting Foresight Methodologies with Data Analytics[J]. World Futures Review,2020,12(2).[9]Marco Bevolo,Filiberto Amati. The Potential Role of AI in Anticipating Futures from a Design Process Perspective: From the Reflexive Description of “Design” to a Discussion of Influences by the Inclusion of AI in the Futures Research Process[J]. World Futures Review,2020,12(2).[10]Lan Xu,Paul Tu,Qian Tang,Dan Seli?teanu. Contract Design for Cloud Logistics (CL) Based on Blockchain Technology (BT)[J]. Complexity,2020,2020.[11]L. Grant,X. Xue,Z. Vajihi,A. Azuelos,S. Rosenthal,D. Hopkins,R. Aroutiunian,B. Unger,A. Guttman,M. Afilalo. LO32: Artificial intelligence to predict disposition to improve flow in the emergency department[J]. CJEM,2020,22(S1).[12]A. Kirubarajan,A. Taher,S. Khan,S. Masood. P071: Artificial intelligence in emergency medicine: A scoping review[J]. CJEM,2020,22(S1).[13]L. Grant,P. Joo,B. Eng,A. Carrington,M. Nemnom,V. Thiruganasambandamoorthy. LO22: Risk-stratification of emergency department syncope by artificial intelligence using machine learning: human, statistics or machine[J]. CJEM,2020,22(S1).[14]Riva Giuseppe,Riva Eleonora. OS for Ind Robots: Manufacturing Robots Get Smarter Thanks to Artificial Intelligence.[J]. Cyberpsychology, behavior and social networking,2020,23(5).[15]Markus M. Obmann,Aurelio Cosentino,Joshy Cyriac,Verena Hofmann,Bram Stieltjes,Daniel T. Boll,Benjamin M. Yeh,Matthias R. Benz. Quantitative enhancement thresholds and machine learning algorithms for the evaluation of renal lesions using single-phase split-filter dual-energy CT[J]. Abdominal Radiology,2020,45(1).[16]Haytham H. Elmousalami,Mahmoud Elaskary. Drilling stuck pipe classification and mitigation in the Gulf of Suez oil fields using artificial intelligence[J]. Journal of Petroleum Exploration and Production Technology,2020,10(10).[17]Rüdiger Schulz-Wendtland,Karin Bock. Bildgebung in der Mammadiagnostik –Ein Ausblick <trans-title xml:lang="en">Imaging in breast diagnostics—an outlook [J]. Der Gyn?kologe,2020,53(6).</trans-title>[18]Nowakowski Piotr,Szwarc Krzysztof,Boryczka Urszula. Combining an artificial intelligence algorithm and a novel vehicle for sustainable e-waste collection[J]. Science of the Total Environment,2020,730.[19]Wang Huaizhi,Liu Yangyang,Zhou Bin,Li Canbing,Cao Guangzhong,Voropai Nikolai,Barakhtenko Evgeny. Taxonomy research of artificial intelligence for deterministic solar power forecasting[J]. Energy Conversion and Management,2020,214.[20]Kagemoto Hiroshi. Forecasting a water-surface wave train with artificial intelligence- A case study[J]. Ocean Engineering,2020,207.[21]Tomonori Aoki,Atsuo Yamada,Kazuharu Aoyama,Hiroaki Saito,Gota Fujisawa,Nariaki Odawara,Ryo Kondo,Akiyoshi Tsuboi,Rei Ishibashi,Ayako Nakada,Ryota Niikura,Mitsuhiro Fujishiro,Shiro Oka,Soichiro Ishihara,Tomoki Matsuda,Masato Nakahori,Shinji Tanaka,Kazuhiko Koike,Tomohiro Tada. Clinical usefulness of a deep learning‐based system as the first screening on small‐bowel capsule endoscopy reading[J]. Digestive Endoscopy,2020,32(4).[22]Masashi Fujii,Hajime Isomoto. Next generation of endoscopy: Harmony with artificial intelligence and robotic‐assisted devices[J]. Digestive Endoscopy,2020,32(4).[23]Roberto Verganti,Luca Vendraminelli,Marco Iansiti. Innovation and Design in the Age of Artificial Intelligence[J]. Journal of Product Innovation Management,2020,37(3).[24]Yuval Elbaz,David Furman,Maytal Caspary Toroker. Modeling Diffusion in Functional Materials: From Density Functional Theory to Artificial Intelligence[J]. Advanced Functional Materials,2020,30(18).[25]Dinesh Visva Gunasekeran,Tien Yin Wong. Artificial Intelligence in Ophthalmology in 2020: A Technology on the Cusp for Translation and Implementation[J]. Asia-Pacific Journal of Ophthalmology,2020,9(2).[26]Fu-Neng Jiang,Li-Jun Dai,Yong-Ding Wu,Sheng-Bang Yang,Yu-Xiang Liang,Xin Zhang,Cui-Yun Zou,Ren-Qiang He,Xiao-Ming Xu,Wei-De Zhong. The study of multiple diagnosis models of human prostate cancer based on Taylor database by artificial neural networks[J]. Journal of the Chinese Medical Association,2020,83(5).[27]Matheus Calil Faleiros,Marcello Henrique Nogueira-Barbosa,Vitor Faeda Dalto,JoséRaniery Ferreira Júnior,Ariane Priscilla Magalh?es Tenório,Rodrigo Luppino-Assad,Paulo Louzada-Junior,Rangaraj Mandayam Rangayyan,Paulo Mazzoncini de Azevedo-Marques. Machine learning techniques for computer-aided classification of active inflammatory sacroiliitis in magnetic resonance imaging[J]. Advances in Rheumatology,2020,60(1078).[28]Balamurugan Balakreshnan,Grant Richards,Gaurav Nanda,Huachao Mao,Ragu Athinarayanan,Joseph Zaccaria. PPE Compliance Detection using Artificial Intelligence in Learning Factories[J]. Procedia Manufacturing,2020,45.[29]M. Stévenin,V. Avisse,N. Ducarme,A. de Broca. Qui est responsable si un robot autonome vient à entra?ner un dommage ?[J]. Ethique et Santé,2020.[30]Fatemeh Barzegari Banadkooki,Mohammad Ehteram,Fatemeh Panahi,Saad Sh. Sammen,Faridah Binti Othman,Ahmed EL-Shafie. Estimation of Total Dissolved Solids (TDS) using New Hybrid Machine Learning Models[J]. Journal of Hydrology,2020.[31]Adam J. Schwartz,Henry D. Clarke,Mark J. Spangehl,Joshua S. Bingham,DavidA. Etzioni,Matthew R. Neville. Can a Convolutional Neural Network Classify Knee Osteoarthritis on Plain Radiographs as Accurately as Fellowship-Trained Knee Arthroplasty Surgeons?[J]. The Journal of Arthroplasty,2020.[32]Ivana Nizetic Kosovic,Toni Mastelic,Damir Ivankovic. Using Artificial Intelligence on environmental data from Internet of Things for estimating solar radiation: Comprehensive analysis[J]. Journal of Cleaner Production,2020.[33]Lauren Fried,Andrea Tan,Shirin Bajaj,Tracey N. Liebman,David Polsky,Jennifer A. Stein. Technological advances for the detection of melanoma: Part I. Advances in diagnostic techniques[J]. Journal of the American Academy of Dermatology,2020.[34]Mohammed Amoon,Torki Altameem,Ayman Altameem. Internet of things Sensor Assisted Security and Quality Analysis for Health Care Data Sets Using Artificial Intelligent Based Heuristic Health Management System[J]. Measurement,2020.[35]E. Lotan,C. Tschider,D.K. Sodickson,A. Caplan,M. Bruno,B. Zhang,Yvonne W. Lui. Medical Imaging and Privacy in the Era of Artificial Intelligence: Myth, Fallacy, and the Future[J]. Journal of the American College of Radiology,2020.[36]Fabien Lareyre,Cédric Adam,Marion Carrier,Juliette Raffort. Artificial Intelligence in Vascular Surgery: moving from Big Data to Smart Data[J]. Annals of Vascular Surgery,2020.[37]Ilesanmi Daniyan,Khumbulani Mpofu,Moses Oyesola,Boitumelo Ramatsetse,Adefemi Adeodu. Artificial intelligence for predictive maintenance in the railcar learning factories[J]. Procedia Manufacturing,2020,45.[38]Janet L. McCauley,Anthony E. Swartz. Reframing Telehealth[J]. Obstetrics and Gynecology Clinics of North America,2020.[39]Jean-Emmanuel Bibault,Lei Xing. Screening for chronic obstructive pulmonary disease with artificial intelligence[J]. The Lancet Digital Health,2020,2(5).[40]Andrea Laghi. Cautions about radiologic diagnosis of COVID-19 infection driven by artificial intelligence[J]. The Lancet Digital Health,2020,2(5).人工智能英文参考文献二：[41]K. Orhan,I. S. Bayrakdar,M. Ezhov,A. Kravtsov,T. ?zyürek. Evaluation of artificial intelligence for detecting periapical pathosis on cone‐beam computed tomography scans[J]. International Endodontic Journal,2020,53(5).[42]Avila A M,Mezi? I. Data-driven analysis and forecasting of highway traffic dynamics.[J]. Nature communications,2020,11(1).[43]Neri Emanuele,Miele Vittorio,Coppola Francesca,Grassi Roberto. Use of CT andartificial intelligence in suspected or COVID-19 positive patients: statement of the Italian Society of Medical and Interventional Radiology.[J]. La Radiologia medica,2020.[44]Tau Noam,Stundzia Audrius,Yasufuku Kazuhiro,Hussey Douglas,Metser Ur. Convolutional Neural Networks in Predicting Nodal and Distant Metastatic Potential of Newly Diagnosed Non-Small Cell Lung Cancer on FDG PET Images.[J]. AJR. American journal of roentgenology,2020.[45]Coppola Francesca,Faggioni Lorenzo,Regge Daniele,Giovagnoni Andrea,Golfieri Rita,Bibbolino Corrado,Miele Vittorio,Neri Emanuele,Grassi Roberto. Artificial intelligence: radiologists' expectations and opinions gleaned from a nationwide online survey.[J]. La Radiologia medica,2020.[46]?. ? ? ? ? [J]. ,2020,25(4).[47]Savage Rock H,van Assen Marly,Martin Simon S,Sahbaee Pooyan,Griffith Lewis P,Giovagnoli Dante,Sperl Jonathan I,Hopfgartner Christian,K?rgel Rainer,Schoepf U Joseph. Utilizing Artificial Intelligence to Determine Bone Mineral Density Via Chest Computed Tomography.[J]. Journal of thoracic imaging,2020,35 Suppl 1.[48]Brzezicki Maksymilian A,Bridger Nicholas E,Kobeti? Matthew D,Ostrowski Maciej,Grabowski Waldemar,Gill Simran S,Neumann Sandra. Artificial intelligence outperforms human students in conducting neurosurgical audits.[J]. Clinical neurology and neurosurgery,2020,192.[49]Lockhart Mark E,Smith Andrew D. Fatty Liver Disease: Artificial Intelligence Takes on the Challenge.[J]. Radiology,2020,295(2).[50]Wood Edward H,Korot Edward,Storey Philip P,Muscat Stephanie,Williams George A,Drenser Kimberly A. The retina revolution: signaling pathway therapies, genetic therapies, mitochondrial therapies, artificial intelligence.[J]. Current opinion in ophthalmology,2020,31(3).[51]Ho Dean,Quake Stephen R,McCabe Edward R B,Chng Wee Joo,Chow Edward K,Ding Xianting,Gelb Bruce D,Ginsburg Geoffrey S,Hassenstab Jason,Ho Chih-Ming,Mobley William C,Nolan Garry P,Rosen Steven T,Tan Patrick,Yen Yun,Zarrinpar Ali. Enabling Technologies for Personalized and Precision Medicine.[J]. Trends in biotechnology,2020,38(5).[52]Fischer Andreas M,Varga-Szemes Akos,van Assen Marly,Griffith L Parkwood,Sahbaee Pooyan,Sperl Jonathan I,Nance John W,Schoepf U Joseph. Comparison of Artificial Intelligence-Based Fully Automatic Chest CT Emphysema Quantification to Pulmonary Function Testing.[J]. AJR. American journal ofroentgenology,2020,214(5).[53]Moore William,Ko Jane,Gozansky Elliott. Artificial Intelligence Pertaining to Cardiothoracic Imaging and Patient Care: Beyond Image Interpretation.[J]. Journal of thoracic imaging,2020,35(3).[54]Hwang Eui Jin,Park Chang Min. Clinical Implementation of Deep Learning in Thoracic Radiology: Potential Applications and Challenges.[J]. Korean journal of radiology,2020,21(5).[55]Mateen Bilal A,David Anna L,Denaxas Spiros. Electronic Health Records to Predict Gestational Diabetes Risk.[J]. Trends in pharmacological sciences,2020,41(5).[56]Yao Xiang,Mao Ling,Lv Shunli,Ren Zhenghong,Li Wentao,Ren Ke. CT radiomics features as a diagnostic tool for classifying basal ganglia infarction onset time.[J]. Journal of the neurological sciences,2020,412.[57]van Assen Marly,Banerjee Imon,De Cecco Carlo N. Beyond the Artificial Intelligence Hype: What Lies Behind the Algorithms and What We Can Achieve.[J]. Journal of thoracic imaging,2020,35 Suppl 1.[58]Guzik Tomasz J,Fuster Valentin. Leaders in Cardiovascular Research: Valentin Fuster.[J]. Cardiovascular research,2020,116(6).[59]Fischer Andreas M,Eid Marwen,De Cecco Carlo N,Gulsun Mehmet A,van Assen Marly,Nance John W,Sahbaee Pooyan,De Santis Domenico,Bauer Maximilian J,Jacobs Brian E,Varga-Szemes Akos,Kabakus Ismail M,Sharma Puneet,Jackson Logan J,Schoepf U Joseph. Accuracy of an Artificial Intelligence Deep Learning Algorithm Implementing a Recurrent Neural Network With Long Short-term Memory for the Automated Detection of Calcified Plaques From Coronary Computed Tomography Angiography.[J]. Journal of thoracic imaging,2020,35 Suppl 1.[60]Ghosh Adarsh,Kandasamy Devasenathipathy. Interpretable Artificial Intelligence: Why and When.[J]. AJR. American journal of roentgenology,2020,214(5).[61]M.Rosario González-Rodríguez,M.Carmen Díaz-Fernández,Carmen Pacheco Gómez. Facial-expression recognition: An emergent approach to the measurement of tourist satisfaction through emotions[J]. Telematics and Informatics,2020,51.[62]Ru-Xi Ding,Iván Palomares,Xueqing Wang,Guo-Rui Yang,Bingsheng Liu,Yucheng Dong,Enrique Herrera-Viedma,Francisco Herrera. Large-Scale decision-making: Characterization, taxonomy, challenges and future directions from an Artificial Intelligence and applications perspective[J]. Information Fusion,2020,59.[63]Abdulrhman H. Al-Jebrni,Brendan Chwyl,Xiao Yu Wang,Alexander Wong,Bechara J. Saab. AI-enabled remote and objective quantification of stress at scale[J]. Biomedical Signal Processing and Control,2020,59.[64]Gillian Thomas,Elizabeth Eisenhauer,Robert G. Bristow,Cai Grau,Coen Hurkmans,Piet Ost,Matthias Guckenberger,Eric Deutsch,Denis Lacombe,Damien C. Weber. The European Organisation for Research and Treatment of Cancer, State of Science in radiation oncology and priorities for clinical trials meeting report[J]. European Journal of Cancer,2020,131.[65]Muhammad Asif. Are QM models aligned with Industry 4.0? A perspective on current practices[J]. Journal of Cleaner Production,2020,258.[66]Siva Teja Kakileti,Himanshu J. Madhu,Geetha Manjunath,Leonard Wee,Andre Dekker,Sudhakar Sampangi. Personalized risk prediction for breast cancer pre-screening using artificial intelligence and thermal radiomics[J]. Artificial Intelligence In Medicine,2020,105.[67]. Evaluation of Payer Budget Impact Associated with the Use of Artificial Intelligence in Vitro Diagnostic, Kidneyintelx, to Modify DKD Progression:[J]. American Journal of Kidney Diseases,2020,75(5).[68]Rohit Nishant,Mike Kennedy,Jacqueline Corbett. Artificial intelligence for sustainability: Challenges, opportunities, and a research agenda[J]. International Journal of Information Management,2020,53.[69]Hoang Nguyen,Xuan-Nam Bui. Soft computing models for predicting blast-induced air over-pressure: A novel artificial intelligence approach[J]. Applied Soft Computing Journal,2020,92.[70]Benjamin S. Hopkins,Aditya Mazmudar,Conor Driscoll,Mark Svet,Jack Goergen,Max Kelsten,Nathan A. Shlobin,Kartik Kesavabhotla,Zachary A Smith,Nader S Dahdaleh. Using artificial intelligence (AI) to predict postoperative surgical site infection: A retrospective cohort of 4046 posterior spinal fusions[J]. Clinical Neurology and Neurosurgery,2020,192.[71]Mei Yang,Runze Zhou,Xiangjun Qiu,Xiangfei Feng,Jian Sun,Qunshan Wang,Qiufen Lu,Pengpai Zhang,Bo Liu,Wei Li,Mu Chen,Yan Zhao,Binfeng Mo,Xin Zhou,Xi Zhang,Yingxue Hua,Jin Guo,Fangfang Bi,Yajun Cao,Feng Ling,Shengming Shi,Yi-Gang Li. Artificial intelligence-assisted analysis on the association between exposure to ambient fine particulate matter and incidence of arrhythmias in outpatients of Shanghai community hospitals[J]. Environment International,2020,139.[72]Fatemehalsadat Madaeni,Rachid Lhissou,Karem Chokmani,Sebastien Raymond,Yves Gauthier. Ice jam formation, breakup and prediction methods based on hydroclimatic data using artificial intelligence: A review[J]. Cold Regions Science and Technology,2020,174.[73]Steve Chukwuebuka Arum,David Grace,Paul Daniel Mitchell. A review of wireless communication using high-altitude platforms for extended coverage and capacity[J]. Computer Communications,2020,157.[74]Yong-Hong Kuo,Nicholas B. Chan,Janny M.Y. Leung,Helen Meng,Anthony Man-Cho So,Kelvin K.F. Tsoi,Colin A. Graham. An Integrated Approach of Machine Learning and Systems Thinking for Waiting Time Prediction in an Emergency Department[J]. International Journal of Medical Informatics,2020,139.[75]Matteo Terzi,Gian Antonio Susto,Pratik Chaudhari. Directional adversarial training for cost sensitive deep learning classification applications[J]. Engineering Applications of Artificial Intelligence,2020,91.[76]Arman Kilic. Artificial Intelligence and Machine Learning in Cardiovascular Health Care[J]. The Annals of Thoracic Surgery,2020,109(5).[77]Hossein Azarmdel,Ahmad Jahanbakhshi,Seyed Saeid Mohtasebi,Alfredo Rosado Mu?oz. Evaluation of image processing technique as an expert system in mulberry fruit grading based on ripeness level using artificial neural networks (ANNs) and support vector machine (SVM)[J]. Postharvest Biology and Technology,2020,166.[78]Wafaa Wardah,Abdollah Dehzangi,Ghazaleh Taherzadeh,Mahmood A. Rashid,M.G.M. Khan,Tatsuhiko Tsunoda,Alok Sharma. Predicting protein-peptide binding sites with a deep convolutional neural network[J]. Journal of Theoretical Biology,2020,496.[79]Francisco F.X. Vasconcelos,Róger M. Sarmento,Pedro P. Rebou?as Filho,Victor Hugo C. de Albuquerque. Artificial intelligence techniques empowered edge-cloud architecture for brain CT image analysis[J]. Engineering Applications of Artificial Intelligence,2020,91.[80]Masaaki Konishi. Bioethanol production estimated from volatile compositions in hydrolysates of lignocellulosic biomass by deep learning[J]. Journal of Bioscience and Bioengineering,2020,129(6).人工智能英文参考文献三：[81]J. Kwon,K. Kim. Artificial Intelligence for Early Prediction of Pulmonary Hypertension Using Electrocardiography[J]. Journal of Heart and Lung Transplantation,2020,39(4).[82]C. Maathuis,W. Pieters,J. van den Berg. Decision support model for effects estimation and proportionality assessment for targeting in cyber operations[J]. Defence Technology,2020.[83]Samer Ellahham. Artificial Intelligence in Diabetes Care[J]. The American Journal of Medicine,2020.[84]Yi-Ting Hsieh,Lee-Ming Chuang,Yi-Der Jiang,Tien-Jyun Chang,Chung-May Yang,Chang-Hao Yang,Li-Wei Chan,Tzu-Yun Kao,Ta-Ching Chen,Hsuan-Chieh Lin,Chin-Han Tsai,Mingke Chen. Application of deep learning image assessment software VeriSee? for diabetic retinopathy screening[J]. Journal of the Formosan Medical Association,2020.[85]Emre ARTUN,Burak KULGA. Selection of candidate wells for re-fracturing in tight gas sand reservoirs using fuzzy inference[J]. Petroleum Exploration and Development Online,2020,47(2).[86]Alberto Arenal,Cristina Armu?a,Claudio Feijoo,Sergio Ramos,Zimu Xu,Ana Moreno. Innovation ecosystems theory revisited: The case of artificial intelligence in China[J]. Telecommunications Policy,2020.[87]T. Som,M. Dwivedi,C. Dubey,A. Sharma. Parametric Studies on Artificial Intelligence Techniques for Battery SOC Management and Optimization of Renewable Power[J]. Procedia Computer Science,2020,167.[88]Bushra Kidwai,Nadesh RK. Design and Development of Diagnostic Chabot for supporting Primary Health Care Systems[J]. Procedia Computer Science,2020,167.[89]Asl? Bozda?,Ye?im Dokuz,?znur Begüm G?k?ek. Spatial prediction of PM 10 concentration using machine learning algorithms in Ankara, Turkey[J]. Environmental Pollution,2020.[90]K.P. Smith,J.E. Kirby. Image analysis and artificial intelligence in infectious disease diagnostics[J]. Clinical Microbiology and Infection,2020.[91]Alklih Mohamad YOUSEF,Ghahfarokhi Payam KAVOUSI,Marwan ALNUAIMI,Yara ALATRACH. Predictive data analytics application for enhanced oil recovery in a mature field in the Middle East[J]. Petroleum Exploration and Development Online,2020,47(2).[92]Omer F. Ahmad,Danail Stoyanov,Laurence B. Lovat. Barriers and pitfalls for artificial intelligence in gastroenterology: Ethical and regulatory issues[J]. Techniques and Innovations in Gastrointestinal Endoscopy,2020,22(2).[93]Sanne A. Hoogenboom,Ulas Bagci,Michael B. Wallace. Artificial intelligence in gastroenterology. The current state of play and the potential. How will it affect our practice and when?[J]. Techniques and Innovations in Gastrointestinal Endoscopy,2020,22(2).[94]Douglas K. Rex. Can we do resect and discard with artificial intelligence-assisted colon polyp “optical biopsy?”[J]. Techniques and Innovations in Gastrointestinal Endoscopy,2020,22(2).[95]Neal Shahidi,Michael J. Bourke. Can artificial intelligence accurately diagnose endoscopically curable gastrointestinal cancers?[J]. Techniques and Innovations in Gastrointestinal Endoscopy,2020,22(2).[96]Michael Byrne. Artificial intelligence in gastroenterology[J]. Techniques and Innovations in Gastrointestinal Endoscopy,2020,22(2).[97]Piet C. de Groen. Using artificial intelligence to improve adequacy of inspection in gastrointestinal endoscopy[J]. Techniques and Innovations in Gastrointestinal Endoscopy,2020,22(2).[98]Robin Zachariah,Andrew Ninh,William Karnes. Artificial intelligence for colon polyp detection: Why should we embrace this?[J]. Techniques and Innovations in Gastrointestinal Endoscopy,2020,22(2).[99]Alexandra T. Greenhill,Bethany R. Edmunds. A primer of artificial intelligence in medicine[J]. Techniques and Innovations in Gastrointestinal Endoscopy,2020,22(2).[100]Tomohiro Tada,Toshiaki Hirasawa,Toshiyuki Yoshio. The role for artificial intelligence in evaluation of upper GI cancer[J]. Techniques and Innovations in Gastrointestinal Endoscopy,2020,22(2).[101]Yahui Jiang,Meng Yang,Shuhao Wang,Xiangchun Li,Yan Sun. Emerging role of deep learning‐based artificial intelligence in tumor pathology[J]. Cancer Communications,2020,40(4).[102]Kristopher D. Knott,Andreas Seraphim,Joao B. Augusto,Hui Xue,Liza Chacko,Nay Aung,Steffen E. Petersen,Jackie A. Cooper,Charlotte Manisty,Anish N. Bhuva,Tushar Kotecha,Christos V. Bourantas,Rhodri H. Davies,Louise A.E. Brown,Sven Plein,Marianna Fontana,Peter Kellman,James C. Moon. The Prognostic Significance of Quantitative Myocardial Perfusion: An Artificial Intelligence–Based Approach Using Perfusion Mapping[J]. Circulation,2020,141(16).[103]Muhammad Asad,Ahmed Moustafa,Takayuki Ito. FedOpt: Towards Communication Efficiency and Privacy Preservation in Federated Learning[J]. Applied Sciences,2020,10(8).[104]Wu Wenzhi,Zhang Yan,Wang Pu,Zhang Li,Wang Guixiang,Lei Guanghui,Xiao Qiang,Cao Xiaochen,Bian Yueran,Xie Simiao,Huang Fei,Luo Na,Zhang Jingyuan,Luo Mingyan. Psychological stress of medical staffs during outbreak of COVID-19 and adjustment strategy.[J]. Journal of medical virology,2020.[105]. Eyenuk Fulfills Contract for Artificial Intelligence Grading of Retinal Images[J]. Telecomworldwire,2020.[106]Kim Tae Woo,Duhachek Adam. Artificial Intelligence and Persuasion: A Construal-Level Account.[J]. Psychological science,2020,31(4).[107]McCall Becky. COVID-19 and artificial intelligence: protecting health-care workers and curbing the spread.[J]. The Lancet. Digital health,2020,2(4).[108]Alca?iz Mariano,Chicchi Giglioli Irene A,Sirera Marian,Minissi Eleonora,Abad Luis. [Autism spectrum disorder biomarkers based on biosignals, virtual reality and artificial intelligence].[J]. Medicina,2020,80 Suppl 2.[109]Cong Lei,Feng Wanbing,Yao Zhigang,Zhou Xiaoming,Xiao Wei. Deep Learning Model as a New Trend in Computer-aided Diagnosis of Tumor Pathology for Lung Cancer.[J]. Journal of Cancer,2020,11(12).[110]Wang Fengdan,Gu Xiao,Chen Shi,Liu Yongliang,Shen Qing,Pan Hui,Shi Lei,Jin Zhengyu. Artificial intelligence system can achieve comparable results to experts for bone age assessment of Chinese children with abnormal growth and development.[J]. PeerJ,2020,8.[111]Hu Wenmo,Yang Huayu,Xu Haifeng,Mao Yilei. Radiomics based on artificial intelligence in liver diseases: where we are?[J]. Gastroenterology report,2020,8(2).[112]Batayneh Wafa,Abdulhay Enas,Alothman Mohammad. Prediction of the performance of artificial neural networks in mapping sEMG to finger joint angles via signal pre-investigation techniques.[J]. Heliyon,2020,6(4).[113]Aydin Emrah,Türkmen ?nan Utku,Namli G?zde,?ztürk ?i?dem,Esen Ay?e B,Eray Y Nur,Ero?lu Egemen,Akova Fatih. A novel and simple machine learning algorithm for preoperative diagnosis of acute appendicitis in children.[J]. Pediatric surgery international,2020.[114]Ellahham Samer. Artificial Intelligence in Diabetes Care.[J]. The Americanjournal of medicine,2020.[115]David J. Winkel,Thomas J. Weikert,Hanns-Christian Breit,Guillaume Chabin,Eli Gibson,Tobias J. Heye,Dorin Comaniciu,Daniel T. Boll. Validation of a fully automated liver segmentation algorithm using multi-scale deep reinforcement learning and comparison versus manual segmentation[J]. European Journal of Radiology,2020,126.[116]Binjie Fu,Guoshu Wang,Mingyue Wu,Wangjia Li,Yineng Zheng,Zhigang Chu,Fajin Lv. Influence of CT effective dose and convolution kernel on the detection of pulmonary nodules in different artificial intelligence software systems: A phantom study[J]. European Journal of Radiology,2020,126.[117]Georgios N. Kouziokas. A new W-SVM kernel combining PSO-neural network transformed vector and Bayesian optimized SVM in GDP forecasting[J]. Engineering Applications of Artificial Intelligence,2020,92.[118]Qingsong Ruan,Zilin Wang,Yaping Zhou,Dayong Lv. A new investor sentiment indicator ( ISI ) based on artificial intelligence: A powerful return predictor in China[J]. Economic Modelling,2020,88.[119]Mohamed Abdel-Basset,Weiping Ding,Laila Abdel-Fatah. The fusion of Internet of Intelligent Things (IoIT) in remote diagnosis of obstructive Sleep Apnea: A survey and a new model[J]. Information Fusion,2020,61.[120]Federico Caobelli. Artificial intelligence in medical imaging: Game over for radiologists?[J]. European Journal of Radiology,2020,126.以上就是关于人工智能参考文献的分享，希望对你有所帮助。

Computer-Aided Diagnosis in Chest Radiography:A SurveyBram van Ginneken*,Bart M.ter Haar Romeny,and Max A.Viergever,Member IEEEAbstract—The traditional chest radiograph is still ubiquitous in clinical practice,and will likely remain so for quite some time. Yet,its interpretation is notoriously difficult.This explains the con-tinued interest in computer-aided diagnosis for chest radiography. The purpose of this survey is to categorize and briefly review the literature on computer analysis of chest images,which comprises over150papers published in the last30years.Remaining chal-lenges are indicated and some directions for future research are given.Index Terms—Chest radiography,computer-aided diagnosis, lung field segmentation,lung nodule detection,rib segmentation,.I.I NTRODUCTIONT HE discovery of X-rays by Wilhelm Conrad Röntgen, in1895[1],has revolutionized the field of diagnostic medicine.Today a wide variety of(three-dimensional)imaging techniques is available,and many types of examinations have been,or are about to be replaced by computed tomography (CT)and/or magnetic resonance imaging(MRI)within the next few years.But this is certainly not the case for the chest radiograph.On the contrary,the traditional chest study is still by far the most common type of radiological procedure,making up at least a third of all exams in a typical radiology department [2],[?].Daffner[2]describes the chest as“the mirror of health and disease:”An enormous amount of information about the condition of the patient can be extracted from a chest film and,therefore,“the‘routine’chest radiograph should not be considered quite so routine.”Interpreting a chest radiograph is extremely challenging.Su-perimposed anatomical structures make the image complicated. Even experienced radiologists have trouble distinguishing infil-trates from the normal pattern of branching blood vessels in the lung fields,or detecting subtle nodules that indicate lung cancer [4].When radiologists rate the severity of abnormal findings, large interobserver and even intraobserver differences occur[5], [6].The clinical importance of chest radiographs,combined with their complicated nature,explains the interest to develop computer algorithms to assist radiologists in reading chest im-Manuscript received June10,2001;revised October30,2001.Asterisk indi-cates corresponding author.*B.van Ginneken is with the Image Sciences Institute,University Medical Center Utrecht,Heidelberglaan100,3584CX Utrecht,The Netherlands(e-mail: bram@isi.uu.nl).B.M.ter Haar Romeny is with the Faculty of Biomedical Engineering,Med-ical and Biomedical Imaging,Eindhoven University of Technology,5600MB Eindhoven,The Netherlands.M.A.Viergever is with the Image Sciences Institute,University Medical Center Utrecht,Heidelberglaan100,3584CX Utrecht,The Netherlands. Publisher Item Identifier S0278-0062(01)11136-5.ages.The purpose of this survey is to categorize and briefly re-view the literature on computer analysis of chest radiographs with an emphasis on the techniques that have been employed and on the tasks these techniques are supposed to solve. Soon after the invention of the modern digital computer at the end of the1940s,research began on having computers per-form tasks that had previously been performed only by human intelligence.The first articles about computer analysis of radio-graphic images appeared in the1960s[7],[8].Papers describing techniques specifically designed for computerized detection of abnormalities in chest radiographs began to appear in the1970s. These were among the first papers in the field of medical image analysis,as is noted in a recent review by Duncan and Ayache [9].These early studies displayed a considerable optimism re-garding the capabilities of computers to generate complete di-agnoses.They are summarized in one review[10]as attempts to“fully automate the chest exam.”Over the decades this ex-pectation has subsided(which seems to have happened to the early enthusiasm regarding the capabilities of artificial intelli-gence systems in general).Currently,the general agreement is that the focus should be on making useful computer-generated information available to physicians for decision support rather than trying to make a computer act like a diagnostician[11]; from the abbreviations FACD(fully automatic computer diag-nosis),ICD(interactive computer diagnosis),and CAD(com-puter-aided diagnosis),only the latter is in common use nowa-days.Several related fields are important for CAD in chest radi-ography,but are outside the scope of this survey because no image processing is involved.Among these are studies on acqui-sition,about digital chest units versus analog film systems(e.g., [12]–[15]),or on dual energy systems in chest radiography(e.g., [16]–[18]);studies that use psychophysics,e.g.,to determine the optimum tube voltage[19]or to aid the detection of abnor-malities by measuring visual dwell[20],[21];attempts to quan-tify the performance of radiologists,usually through observer studies,when image quality parameters of the chest radiographs are varied(e.g.,[22]–[28]);and research on estimating proba-bilities that patients exhibit a certain disease,given a number of features from clinical information and/or output of computer al-gorithms.Such studies have continued to appear,starting in the 1960s[29],[30]until recently,e.g.,[31]–[33].Three main areas can be distinguished in the literature on computer analysis of chest radiographs:1)general processing techniques;2)algorithms for segmentation of anatomical struc-tures;and3)analysis aimed at solving a particular task or ap-0278–0062/01$10.00©2001IEEEplication,usually an attempt to detect a specific kind of abnor-mality.The following subdivision is adopted and followed in the sequel of this survey.•General processing:—enhancement;—subtraction techniques.•Segmentation:—lung fields;—rib cage;—other structures.•Analysis:—size measurements;—lung nodule detection;—texture analysis;—other applications.Conners et al.[10]reviewed computer analysis of radiographic imagesingeneralin1982,withastrongemphasisonchestradiog-raphy.Overviews of research at the Kurt Rossmann Laboratories at the University of Chicago,an active group in computer-aided diagnosis,are given in[34]–[40].A recent general introduction to computer-aided diagnosis with some examples taken from CAD in chest radiography can be found in[41].Other informative gen-eral overviews can be found in[42]and[43],although the dis-cussion on CAD in chest radiography in both works is strongly focussed on the work done at the University of Chicago.An in-teresting collection of short papers on CAD can be found in[44]. Reeves and Kostis[45]recently reviewed CAD for lung cancer and although the emphasis is on CT,there is also an overview of methods developed for chest radiographs.It is worth mentioning here that CAD has been shown to be effective in screening mammography.These successes are cer-tainly helping to make CAD in chest radiography acceptable, notably for the detection of lung nodules.Moreover,the tech-niques employed in both fields are often similar and may in-spire new research.Overviews of CAD in mammography can be found in[42],[46],and[47].Almost all work discussed here is applied to frontal[poste-rior-anterior(PA)]chest radiographs.A few studies are aimed at lateral radiographs,and those cases are specifically mentioned. Although the skills of experienced radiologists are beyond reach for nonmedical researchers,anyone working on algo-rithms for the analysis of chest radiographs should obtain some knowledge about the anatomy of the chest,its appearance on projection radiographs and the nature of various abnormal findings.Introductory texts can be found in Squire[48],and in Lange’s standard textbook[49].A detailed pictorial description of normal and abnormal findings in chest radiographs is given in the chapter on chest imaging in[50].A comprehensible overview of interstitial disease can be found in[51].Several tables are included that summarize papers on specific topics.In these tables,studies are listed in chronological order. In most cases information about the evaluation of the presented techniques,such as the size of the test database,are included.We refrained from including any reported figures on classification performance or segmentation accuracy,because these results are usually very dependent on the subtlety of the abnormalities in the test images which makes it impossible to compare the merits of various methods on the basis of such figures alone.II.G ENERAL P ROCESSINGA.EnhancementChest radiographs inherently display a wide dynamic range of X-ray intensities.In conventional,unprocessed images it is often hard to“see through”the mediastinum and contrast in the lung fields is limited.A classical solution to this kind of problem in image processing is the use of(local)histogram equalization techniques.A related technique is enhancement of high-frequency details(sharpening).Such techniques are so essential for optimized display of images in soft-copy reading environments that numerous studies have been devoted to this subject.A wide variety of preprocessing procedures for chest radiographs based on local equalization,sharpening,and combinations and modifications of these techniques have been proposed.It is beyond the scope of this survey to give a complete overview.The following works deal with optimal display and image enhancement[52]–[61].Examples of hardware solutions can be found in[62],[63].Nowadays,almost all vendors sell digital chest units with a larger dynamic range than conventional units and most vendors automatically preprocess the images with proprietary algorithms.B.Subtraction TechniquesSubtraction techniques attempt to remove normal structures in chest radiographs,so that abnormalities stand out more clearly,either for the radiologist to see or for the computer to detect.A first approach is temporal subtraction,proposed by Kano et al.[64].An input image is registered with a previous radiograph of the same patient.Elastic matching is employed in which the displacement of small regions of interest(ROIs)is computed based on cross correlation and a smooth deformation field is obtained by fitting a high-order polynomial function to the dis-placement vectors.The registered image is subtracted and if the registration is successful,areas with interval change stand out as either dark or bright on a gray background.The original tech-nique has been improved and evaluated using subjective ratings by radiologists[65],[66]and the results of the method have been compared with manual registration[67].An observer study [68]with a small number of selected cases showed an increase in detection accuracy of interval change when both the normal image and the subtraction image were presented to the radiol-ogist.Recently,Zhao et al.[69]proposed a temporal subtrac-tion technique that performs elastic registration on rib border segments detected with an adaptive oriented filter and reported that the contrast around lung nodules substantially increased in the subtracted images.With the advent of digital archives,tem-poral subtraction techniques may be applied on a routine basis since monitoring interval change is one of the main reasons for making chest radiographs(it is common to obtain a chest radio-graph of patients on an intensive-care unit every day).If a previous radiograph is not available,a subtraction can be made by mirroring the left/right lung field,performing elastic registration on the right/left lung field and subtracting.This technique,coined contralateral subtraction,employs the sym-metry of the rib cage.Li et al.[70],[71]use a scheme similar to Kano et al.[64],based on cross correlation and evaluate theA N O VERVIEW OF L ITERATURE ON L UNG F IELD S EGMENTATION .T HE F IRST C OLUMN L ISTS THE F IRST A UTHOR AND R EFERENCE (S ).M ETHODS A RE D IVIDED IN R ULE -B ASED (RB)AND /OR P IXELC LASSIFICATION (PC)S CHEMES ,S EE THE T EXT FORD ETAILS .T HE C OLUMN E V ALUATION G IVES THE N UMBER OF I MAGES U SED IN E V ALUATION O NLY (I MAGES U SED IN A T EST S ET A RE N OT I NCLUDED ).R M EANS E V ALUATION T HROUGH S UBJECTIVE R ATING BY A R ADIOLOGIST OFTHE R ESULT ,U SUALLY IN C LASSES F ROM 1(P OOR )TO 5(E XCELLENT ).Q S TANDS FOR Q UANTITATIVE E V ALUATION ,IN W HICH THE R ESULT ISC OMPARED ON A P IXEL -BY -P IXEL B ASIS W ITH A M ANUAL SEGMENTATIONresult with subjective ratings by radiologists.Yoshida [72],[73]minimizes the sum of squared differences,using a mapping that is ensured to be smooth through a regularization term and an optimization in the wavelet domain,and,in [74]segments ab-normal areas that “light up”in the subtracted image.The tech-nique is used to eliminate false positives from a number of can-didate lung nodules.It may also be possible to eliminate or suppress normal struc-tures in radiographs by subtracting a model that is fitted to the input image.The algorithm to remove ribs by V ogelsang et al.[75],[76]isanexampleofthisapproach.Ribsbordersaredetected and a simple physical model of the density of the rib cage is sub-tracted from the input image.The technique is not evaluated.III.S EGMENTATIONA.Lung FieldsAutomatic segmentation of the lung fields is virtually mandatory before computer analysis of chest radiographs can take place.Several studies deal with this problem exclusively.Others deal with parts of the problem,such as detection of the outer ribcage [87],the diaphragm [88],or the costophrenic angle (where the diaphragm and the rib cage meet)[89].A few studies focus on lateral chest radiographs [90],[92].Table I gives an overview of papers on lung segmentation.The two main approaches are rule-based reasoning and pixel classi-fication.A rule-based scheme is a sequence of steps,tests and rules.Most algorithms for the segmentation of lung fields fall in this category [83],[86]–[92],[98].Techniques employed are (local)thresholding,region growing,edge detection,ridge detec-tion,morphological operations,fitting of geometrical models or functions,dynamic programming.On the other hand,several at-tempts have been made to classify each pixel in the image into an anatomical class (usually lung or background,but in some cases more classes such as heart,mediastinum,and diaphragm [85],[97]).Classifiers are various types of neural networks,or Markov random field modeling,trained with a variety of (local)features including intensity,location,texture measures [84],[85],[93],[94],[97].VanGinnekenandTerHaarRomeny[98]combineboth approaches in a hybrid scheme.It is also possible to use general knowledge-based segmenta-tion methods,such as active shape models [100],or extensions of such methods for the segmentation of lung fields,as is shown in [99].In studies done in the 1970s often a rough or partial outline of the lung fields was detected,with rule-based schemes usu-ally based on analysis of profiles [101]–[105].In this survey,the term “profiles”refers to an average of consecutive one-di-mensional lines of pixels,usually running horizontally or verti-cally.Evaluations of the effectiveness of these methods are not made,and none of these papers focuses on lung field segmenta-tion specifically but use the segmentation for further processing or to estimate the heart size or lung capacity.These methods un-doubtedly inspired later studies.Overall,the problem of segmenting lung fields has attracted considerable attention.Several authors report good results that approach the inter-observer variability ([98]lists a com-parison of quantitative results of several studies).The task of segmenting lung fields might,therefore,be considered largely solved,although no attempts have been made to test methods with very large databases to verify if schemes are also able to produce reasonable results for the,say,1%most difficult cases.Likewise,a study in which the performance of various methods on a large common database of radiographs (of varying quality and obtained with different settings)is compared,has not been made,and would be a worthwhile endeavor.A N O VERVIEW OF L ITERATURE ON R IB D ETECTION IN F RONTALC HEST R ADIOGRAPHS .T HE F IRST C OLUMN L ISTS THE F IRST A UTHOR AND R EFERENCE (S ).T HE C OLUMN P/A I NDICATES I F P OSTERIOR (P)OR A NTERIOR (A)R IBS A RE D ETECTED ,OR B OTH OR N ONE .T HE R IGHT C OLUMN L ISTS ON H OW M ANY I MAGES THE M ETHOD I S E V ALUATED AND I F THE E V ALUATION I S A S UBJECTIVE J UDGEMENT F ROM THEA UTHOR (A),B ASED ON R ATINGS BY R ADIOLOGISTS (R)OR Q UANTITATIVE(Q)Finally,we note that it is often hard to establish ground truth data for evaluation of segmentation techniques.This problem applies to all segmentation tasks discussed here.Preferably,the objects should be delineated by several experienced observers.In the case of lung fields,the definition of a lung field is al-ready unclear,because large parts of the lungs are obscured in PA chest radiographs [106].In rib segmentation,the overlap-ping posterior and anterior rib parts make a definition of “rib borders”difficult.B.Rib CageThere are several reasons why the automatic delineation of rib borders can be useful for computer analysis.First of all,the ribs provide a frame of reference and the locations of abnormalities are often indicated by radiologists in terms of numbered (inter)costal spaces.Second,rib border segmentation may be used to detect rib abnormalities such as fractured or missing ribs.Third,once locations of ribs are known,ROIs between (the intercostal space)or on (the costal space)the ribs can be defined for further analysis.Fourth,knowledge about the location of rib borders may be used to eliminate false positives in the detection of ab-normalities such as nodules.Rib crossings (of the posterior and anterior parts of the ribs)frequently turn up as false positives in nodule detection schemes.The approaches to rib (cage)segmentation are summarized in Table II.Several methods also detect (parts of)the contours of the lung fields [111],[112],[114],but an evaluation of their accuracy is not included.The classical approach to rib segmentation,used in most studies,is as follows.A geometrical model of rib borders ischosen,e.g.,parabolasorellipsesoracombination.Edgedetec-tion extracts segments that may be parts of the rib borders.These candidate rib border parts are analyzed and rejected,or grouped together into complete ribs.In other studies,each candidate votes for combinations of model parameters (a modified Hough trans-form).Postprocessing steps may remove some borders,or infer new rib borders that had not been detected.A fine-tuning stage may be added in which the strict geometric model is abandoned,such as the snakes fitted to rib borders in [114].A difficulty in the classical approach is that the relations be-tween ribs are not taken into account during the fitting proce-dure.Ribs may be missed or detected twice and the fact that consecutive ribs and left-right ribs have similar shape is often ignored.Early attempts to model the relation between ribs,as in [110]do not appear very powerful or use simple ad hoc rules [114].This was already recognized by Wechsler [109]in 1977:“We believe that at this stage a significant improvement in rib boundary detection could be achieved only by a knowl-edge-based system which would incorporate a model of the rib cage.”The rib-cage model in [115]is an attempt to model the shape of the complete rib cage and fit it directly to the image.The number of images used in evaluation is in general consid-erably smaller than in the case of lung field segmentation and in many cases the evaluation is confined to qualitative judgements from the authors themselves (these studies are indicated with A in the right column of Table II).Since the full rib cage has a much more complex shape than the outline of the lung fields,partial failures occur frequently.Furthermore,the detection of anterior (or ventral,as opposed to the posterior or dorsal)parts of the ribs has been addressed only in studies that omit properevaluation.Therefore,we conclude that the problem of auto-matic segmentation of the rib cage in chest radiographs is still far from solved.C.Other StructuresToriwaki et al.describe a complete system for the analysis of chest radiographs[77],[78]that includes segmentation of lung fields,rib cage,heart,clavicles,and blood vessels followed by automatic detection of abnormalities.Only a rough description of results on15[77]and40images[78]taken from a mass screening for lung tuberculosis in Japan is given without mention of the na-ture and subtlety of the abnormalities in this database.A method to select small ROIs within the lung fields that do not contain rib borders is presented by Chen et al.[116].The lateral lungfieldsaresubdividedintoregionswhicharepartlyeliminated if they contain edges of certain strength and orientation. Several methods for segmentation of(parts of)the heart boundary have been proposed[8],[76],[101],[117]–[120], usually with the aim of detecting cardiomegaly(enlarged heart size).Note that a correct segmentation of the lung fields is sufficient to compute the cardiothoracic ratio(CTR)indicative of cardiomegaly,since parts of the boundaries of the lung fields coincide with the heart contour.In Section IV-A,these methods will be discussed in some more detail.Armato et al.[121]developed an algorithm to detect ab-normal asymmetry in chest radiographs using a rule-based scheme for detecting lung contours and comparing the pro-jected lung areas.The method was evaluated on70radiographs.IV.A NALYSISWhat kind of abnormalities does the radiologist who reads chest radiographs encounter in his/her day-to-day practice?The answer to this question should set the agenda for computer sci-entists who want to—as it was put in Section I—“fully automate the chest exam.”.MacMahon[122]has attempted to answer this question by counting the abnormalities encountered in1085 abnormal chest radiographs,collected from consecutive cases, and dividing them in30categories.The main results of this study are summarized in Table III.The statistics are surprising when compared with abnormalities commonly investigated in the literature on computer analysis of chest images.Lung nodules are a relatively rare abnormality but have received much attention in the literature and observer studies tend to use their detectability as a criterion for diagnostic accuracy.Pulmonary infiltrates could be detected in principle by the texture analysis schemes to be discussed later and are the most commonly occurring abnormality.Catheters are next,and although catheters usually stand out clearly in the image,locating their tip was the task that was most frequently limited by image quality.One may argue that the presence of a catheter,or drainage tube,or pacemaker is not an abnormality.However,the presence of such objects can have a large effect on computer analyses and it is important to realize how common such findings are.The same is true for clothing artifacts,that are present in many chest radiographs. The following applications of computer analysis of chest ra-diographs are reported in the literature.•Lung nodule detection.TABLE IIIT HE F REQUENCY W ITH W HICH A BNORMALITIES A RE E NCOUNTERED INA BNORMAL C HEST R ADIOGRAPHS E NCOUNTERED IN C LINICAL P RACTICE.D ATA W AS O BTAINED F ROM1085S TANDARD R ADIOGRAPHS OF A DULTS.T HE I NFORMATION IN T HIS T ABLE I S T AKENF ROM THE S TUDY“T HE N ATUREAND S UBTLETY OF A BNORMAL F INDINGS IN C HEST R ADIOGRAPHS”BYM ACMAHON et al.[122]•Detection of cardiomegaly or estimation of the CTR.•Estimation of total lung volume.•Detection of pneumothorax.•Estimation of the severity of pneumoconiosis(coal worker’s disease).•Detection of interstitial disease.•Detection of abnormalities encountered in mass screening for tuberculosis.We divide these applications into four groups.Size measure-ments are applications based on results that can be computed di-rectly from a segmentation.The detection of nodules is consid-ered a separate category.Several other applications are grouped under“texture analysis”and the remaining tasks are listed under “other applications.”A.Size MeasurementsIn a few applications,diagnostic information can be extracted directly from segmentations.An example is the estimation of enlarged heart size(cardiomegaly)usually performed by measuring the CTR,the maximal horizontal diameter of the heart divided by the maximal horizontal diameter of the thorax. This is the subject of probably the earliest computer analysis studies of chest radiographs by Becker,Meyers,and co-workers [7],[8].Points on the rib-cage boundary and heart boundary are extracted from horizontal profiles and the CTR is estimated for 37radiographs.In work by Hall[117]and Kruger[101],and their co-workers,several parts of the lung and heart boundaries were segmented.Images were classified in one of three categories (normal,rheumatic heart disease,or otherwise abnormal)using various ratios of distances derived from the segmentation asTABLE IVA N O VERVIEWOFM ETHODS FOR I NITIAL S ELECTION OF N ODULE C ANDIDATES .T HE F IRST C OLUMN L ISTS THE F IRST A UTHORANDR EFERENCE (S ).T HE M ETHOD AND E V ALUATION D ATA S ET A RE D ESCRIBED BRIEFLYfeatures in linear and quadratic discriminant functions.The method was evaluated on 320films,a surprisingly large number for studies from the ing a similar approach,Sezaki and Ukena [118]computed the CTR by a scheme that detects the vertical boundary of the rib cage and the heart through analysis of horizontal profiles and the application of a few rules to correct failures.Roellinger et al.[123]used the method from [101]to detect points on the heart boundary to which a Fourier shape was fitted.The coefficients of the Fourier shape were used to classify the heart shape as normal or abnormal,giving reasonable results on a database of 481images with 209normal cases.A comparable method was proposed by Nakamori et al.[119].A Fourier shape was fitted to points on the heart boundary found by edge detection and the results were used to detect cardiomegaly in [120]and evaluated on a database of 400radiographs with 91abnormals.In conclusion,computer estimation of the CTR has received considerable attention and promising results have been obtained.It is likely that modern segmentation methods will outperform the schemes used in most studies cited here since these are based on simple rules to detect only a limited number of landmark points in the image.Clinical applications of automatic detection of heart shape abnormalities seem feasible,but the problem has not attracted much attention the last decade.A related example of size measurements is the determination of total lung capacity (TLC).In this case boundary points on both a PA and a lateral radiograph must be detected.The volume is estimated using an empiric formula that assumes simple shapes for the lungs and that has been shown to correlatewell with the true TLC.Paul et al.[103]described a method to automatically determine the TLC using profile analysis similar to Kruger et al.[101].It was tested on 15radiographs.Carrascal et al.[92]used a rule-based segmentation of PA and lateral lung fields to estimate the TLC for 65radiographs.B.Nodule DetectionAutomatic detection of lung nodules is the most studied problem in computer analysis of chest radiographs.One in every 18woman and every 12men develop lung cancer,making it the leading cause of cancer deaths.Early detection of lung tumors (visible on the chest film as nodules)may increase the patient’s chance of survival.But detecting nodules is a complicated task;see,e.g.,[4].In a lung cancer screening program for heavy smokers in which chest radiographs were taken every four months,it was shown that for 90%of periph-eral lung cancers that were detected,nodules were visible on earlier radiographs,when these older images were checked retrospectively [159].Nodules show up as relatively low-contrast white circular ob-jects within the lung fields.The difficulty for CAD schemes is to distinguish true nodules from (overlapping)shadows from ves-sels and ribs.Almost all methods rely on a two-step approach for nodule detection.In the first stage initial candidate nodules are detected.The second stage consists of eliminating as many false positive candidates as possible,without sacrificing too many true posi-tives.Table IV lists methods for the detection of candidate nod-。

肺窗观察头颈CTA图像显示肺部病变姜雪;张丽娟;黄琳;吕发金【摘要】目的探讨采用肺窗观察头颈CTA图像对于显示肺部病变的价值.方法回顾性分析连续1 000例接受头颈CTA患者资料,将其分为老年组(≥60岁)、中青年组(＜60岁)和吸烟组、非吸烟组,分别比较不同组别纵隔窗、肺窗显示肺部病变的情况.结果 1 000例中,308例患者发现肺部病变,283例仅肺窗可见,8例仅纵隔窗可见,17例两者均可见.共发现8例肺癌,1例磨玻璃肿块仅肺窗可见.283例仅肺窗可见病变中,老年组(191/494,38.67％)明显高于中青年组(92/506,18.18％;x2=51.680,P＜0.001),吸烟组(143/348,41.09％)明显高于非吸烟组(140/652,21.47％;x2=43.043,P＜0.001).结论观察头颈CTA肺窗图像可增加肺部病变的显示率;对于老年人(≥60岁)或长期吸烟者尤有意义.%Objective To explore the significance of lung window observation of head and neck CTA imaging for detecting lung lesions.Methods Head and neck CTA images of 1 000 patients were retrospectively analyzed.The patients were divided into the elderly group (≥ 60 y ears) and the young group (＜ 60 years),also smoking group and non-smoking group.The displaying of lung lesions on mediastinum window and lung window images were compared between the groups,respectively.Results Pulmonary lesions were found in 308 of 1 000 patients.The lesions were only visible on the lung window images in 283 patients,only visible in the mediastinum window images in 8 patients,visible in both lung and mediastinum window imaged in 17 patients.Lung cancers were detected in 8 patients,and ground glass lump in 1 patient was only visible in lung window images.The lesions only visibleon lung window images in the elderly group (191/494,38.67％) was significantly higher than that in the young group(92/506,18.18％;x2=51.680,P＜0.001),and insmoking group(143/348,41.09 ％) was significantly higher than that in non-smoking group (140/652,21.47％;x2 =43.043,P＜0.001).Conclusion Lung window observation of head and neck CTA images can increase displaying rate of lung lesions,especially in elders (over 60 years) and long-term smokers.【期刊名称】《中国介入影像与治疗学》【年(卷),期】2018(015)005【总页数】4页(P273-276)【关键词】体层摄影术,X线计算机;血管造影术;肺窗【作者】姜雪;张丽娟;黄琳;吕发金【作者单位】重庆医科大学附属第一医院放射科,重庆 400016;重庆医科大学附属第一医院放射科,重庆 400016;重庆医科大学附属第一医院放射科,重庆 400016;重庆医科大学附属第一医院放射科,重庆 400016【正文语种】中文【中图分类】R734.2;R814.42头颈CTA是目前检查头颈血管类疾病最常用的方法之一[1]。

2021574肺癌作为人类健康和生命威胁最大的恶性肿瘤之一[1]，在我国的发病率和死亡率增长最快。

早期诊断是提高患者生存率的关键[2]，但是由于肺结节的直径小，早期的肺癌结节很难检测到。

计算机断层扫描（CT）与其他医学诊断技术相比具有更高的准确性，因此被广泛用于检测肺结节。

检查CT会花费医生的大量时间和精力，并且医生的诊断水平不一致，因此很容易出现误诊。

为了提高诊断的准确性，目前已有计算机辅助诊断（CAD）系统来辅助肺癌检测[3-4]。

医生可以将结果作为判断的参考，这项技术加快了检测速度，并在一定程度上降低了误诊率[5]。

肺癌的自动检测过程分为两个步骤：（1）提取所有可疑候选结节；（2）将提取的结节分为两类（阳性和假阳性结节）。

第二步中的分类对象来自第一步中的识别结基于NRU网络的肺结节检测方法徐麒皓，李波武汉科技大学计算机科学与技术学院，武汉430081摘要：肺癌的早期发现和早期诊断是提高肺癌患者生存率的关键。

由于肺癌早期结节很小，目前已有的肺结节检测系统在检测这些结节时很容易漏诊。

准确检测早期肺癌结节对于提高肺癌治愈率至关重要，为了降低检测系统对早期结节的漏诊率，需要优化候选结节的提取步骤。

在U-Net网络中引入残差网络的捷径，有效解决了传统U-Net 网络由于缺乏深度而导致结果较差的问题。

在此改进的基础上提出了一种U型噪声残差网络NRU（Noisy Residual U-Net），通过利用跳跃层连接的特性和向卷积层添加噪声来增强神经网络对小结节的灵敏度。

使用Lung Nodule Analysis2016和阿里巴巴天池肺癌检测竞赛数据集训练神经网络。

U-Net和NRU之间的比较实验表明，该算法对直径为3~5mm（97.1％）的小结节的灵敏度大于U-Net值（90.5％）。

关键词：肺癌；肺结节；肺结节检测系统；噪声；残差网络文献标志码：A中图分类号：TP391.41doi：10.3778/j.issn.1002-8331.1911-0216Method for Detecting Pulmonary Nodules Based on NRU NetworkXU Qihao,LI BoSchool of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan430081,ChinaAbstract：The early detection and diagnosis of lung cancer is the key to improve the survival rate of lung cancer patients. Due to the small nodules in the early stage of lung cancer,the existing pulmonary nodules detection system is easy to miss the diagnosis when detecting these nodules.Accurate detection of early lung nodules is crucial to improve the cure rate of lung cancer.In order to reduce the missed rate of early nodules in the detection system,it is necessary to optimize the extrac-tion procedure of candidate nodules.The shortcut of residual network is introduced into U-Net,which effectively solves the disadvantage of poor results caused by the lack of depth in the traditional U-Net.On the basis of this improvement,a U-type noise residual network NRU（Noisy Residual U-Net）is proposed to enhance the sensitivity of neural network to small nodules by using the characteristics of hopping layer connection and adding noise to the convolutional layer.The Lung Nodule Analysis2016and Alibaba Tianchi lung cancer detection competition data sets are used to train the neural parison experiments between U-Net and NRU show that the sensitivity of the algorithm to small nodules with a diameter of3-5mm（97.1%）is greater than that of U-Net（90.5%）.Key words：lung cancer;pulmonary nodules;pulmonary nodules detection system;noise;residual network⦾模式识别与人工智能⦾基金项目：国家自然科学基金（61572381）。

网络出版时间：２０２３－１０－３０２０：１３：５５　网络出版地址：ｈｔｔｐｓ：／／ｌｉｎｋ．ｃｎｋｉ．ｎｅｔ／ｕｒｌｉｄ／３４．１０８６．Ｒ．２０２３１０２７．１５３０．０１０肺器官芯片的构建及应用刘　含，孙美好，李建生（河南中医药大学，呼吸疾病中医药防治省部共建协同创新中心，河南省中医药防治呼吸病重点实验室，河南郑州　４５００１６）收稿日期：２０２３－０３－２０，修回日期：２０２３－０６－１０基金项目：国家“万人计划”－百千万工程领军人才项目（组厅字【２０１６】３７号）；国家自然科学基金资助项目（Ｎｏ１１９０２２４５）；中国博士后科学基金资助项目（Ｎｏ２０２１Ｍ６９０９３８）；河南省重点研发与推广专项（科技攻关）（Ｎｏ２２２１０２３１０１８３）作者简介：刘　含（１９８８－）女，博士，校聘教授，研究方向：器官芯片的制备及在中医药领域的应用，Ｅ ｍａｉｌ：ｌｉｕｈａｎｙｉｒａｎ＠１２６．ｃｏｍ；李建生（１９６３－）男，博士，教授，博士生导师，研究方向：中医药配伍规律与药理，通信作者，Ｅ ｍａｉｌ：ｌｉ＿ｊｓ８＠１６３．ｃｏｍｄｏｉ：１０．１２３６０／ＣＰＢ２０２２０５１０９文献标志码：Ａ文章编号：１００１－１９７８（２０２３）１１－２０２２－０７中国图书分类号：Ｒ ０５；Ｒ ３３２；Ｒ３３２ ２；Ｒ３１８；Ｒ３６３ ３３２；Ｒ５６摘要：肺器官芯片是一种基于微流控芯片的３Ｄ细胞培养系统，能更准确的模拟人体细胞Ｒ微环境，在生物医学工程等领域具有广阔的应用前景。

该文主要综述了肺器官芯片的制备技术，常见肺器官芯片的构建及相关疾病机制的研究，肺器官芯片在毒性检测、药效药理评价和精准医疗领域的应用等，进一步分析了现有肺器官芯片的不足，同时结合多学科交叉等领域对其发展方向进行了思考，以期为肺部疾病的基础研究及临床防治提供参考。

关键词：肺器官芯片；３Ｄ打印；呼吸系统疾病；病理模型；药效药理评价；精准医疗开放科学（资源服务）标识码（ＯＳＩＤ）： 呼吸系统疾病是影响公众健康的重大问题之一，其患病率、死亡率呈逐年上升趋势，已引起广泛重视［１］。

㊃专题㊃基金项目:国家公益性行业科研专项(201402024)通信作者:金发光,E m a i l :j i n f a g@f mm u .e d u .c n 支气管镜新技术在肺癌早期诊断中的应用金发光(第四军医大学唐都医院呼吸与危重症医学科,陕西西安710038) 摘 要:肺癌的分期是影响肺癌患者预后的重要因素㊂本文将对新型的支气管镜及支气管镜技术,如荧光㊁窄谱㊁超声㊁电磁导航㊁虚拟支气管镜㊁共聚焦激光显微内镜㊁细胞内镜㊁光学相干断层成像等在早期肺癌诊断中的作用进行综述,这些技术从不同角度和层面克服了传统技术的缺陷,极大提高了早期肺癌的诊断率㊂关键词:肺肿瘤;支气管镜检查;早期诊断中图分类号:R 734.2 文献标识码:A 文章编号:1004-583X (2016)11-1161-06d o i :10.3969/j.i s s n .1004-583X.2016.11.001E a r l y d i a g n o s i s o f l u n g c a n c e rw i t hn e wb r o n c h o s c o p y t e c h n i qu e s J i nF a g u a n gD e p a r t m e n t o f P u l m o n a r y a n dC r i t i c a lC a r eM e d c i n e ,T a n g d u H o s pi t a l ,t h eF o u r t h M i l i t a r y M e d i c a lU n i v e r s i t y ,X i ᶄa n 710038,C h i n a C o r r e s p o n d i n g a u t h o r :J i nF a g u a n g ,E m a i l :j i n f a g @fmm u .e d u .c n A B S T R A C T :T h e s t a g i n g o f l u n g c a n c e r i s o n e o f t h em a i n f a c t o r s t h a t a f f e c t s t h e p r o g n o s i s o f p a t i e n t sw i t h l u n gc a n c e r .H e r e ,w er e v i e ws o m en e w b r o n c h o s c o p y t e c h n i q u e s i ne a r l yd i a g o n i so f l u n g ca n c e r ,s u c ha sf l u o r e s c e n c eb r o nc h o s c o p e ,n a r r o w s p e c t r u m b r o n c h o s c o p e ,u l t r a s o n i cb r o n c h o s c o p e ,e l e c t r o m a g n e t i cn a v i g a t i o nb r o n c h o s c o p y ,v i r t u a lb r o n c h o s c o p i c n a v i g a t i o n ,c o n f o c a ll a s e r e nd o m i c r o s c o p y ,e n d o -c y t o s c o p y s y s t e m a nd o p t i c a l c o he r e n c e t o m o g r a p h y i m a g i n g .T h e s e t e c h n i q u e s o v e r c o m e t h e d ef e c t s o f t r a d i t i o n a lm e t h o d s a n d h a v eg r e a t l y i m p r o v e d th e e a r l y di a g n o s t i c r a t e o f l u n g ca n c e r .K E Y W O R D S :l u n g n e o p l a s m s ;b r o nc h o s c o p y ;e a r l yd i a gn o s is 金发光,男,第四军医大学唐都医院呼吸与危重症医学科主任,博士,教授,主任医师,博士生导师㊂兼任陕西省医学会内科学分会主任委员㊁呼吸结核分会名誉主任委员㊁全军呼吸内科专业委员会副主任委员㊁中国医师协会呼吸医师分会常务委员㊁中华医学会呼吸病学分会委员㊁中华医学会呼吸病学分会介入呼吸病学组副组长㊁中国支气管病及呼吸内镜委员会副主任委员㊁中国老年医学会呼吸和危重病委员会委员㊁国家卫生部内镜专家委员会常务理事㊁‘中华肺部疾病杂志“副总编辑㊁中国呼吸医师网站副总编辑等职务,为‘中华结核呼吸杂志“㊁‘国际呼吸杂志“㊁‘中国急救医学“㊁‘中华临床医师杂志(电子版)“㊁‘解放军医学杂志“等杂志常务编委㊁编委或特约编辑等㊂获国家科技进步三等奖1项㊁军队医疗成果一等奖2项㊁军队科技进步二等奖2项㊁陕西省科技进步一等奖㊁陕西省科技二等奖1项㊁中华医学科技三等奖1项㊂主要致力于呼吸衰竭㊁肺癌早期诊断和呼吸病介入微创诊治等方面的研究,并在国内形成明显特色和优势㊂承担国家自然科学基金5项㊁国家卫生行业重大专项1项㊁国家科技重大专项课题 十二五 重大新药创制课题分题1项㊁军队科技攻关重点项目1项㊁军队临床重点创新项目1项㊁军队 十一五 攻关项目1项㊁陕西省攻关项目4项,承担学校教学课题4项,近年来共发表论文274篇,S C I 收录50篇,出版专著(包括主编㊁副主编及参编)共15部㊂由于大气污染㊁各种理化因素对人体的不断刺激,以及其他导致肺癌发病的危险因素不断增加,肺癌已成为全世界发病率和病死率最高的恶性肿瘤,而中国是世界上肺癌患者最多的国家㊂由于肺癌早期症状不典型,加之我国人群就医习惯影响,临床发现的肺癌,确诊时约有80%已发展到中晚期,患者5年生存率不到10%,而早期患者生存率可达80%㊂因此,早期诊断对改善肺癌患者的预后有着极其重要的价值㊂支气管镜是目前临床诊断肺癌的基本手段之一,通过支气管镜下的病变直接观察以及通过病变部位肺泡灌洗㊁刷检㊁肺组织活检㊁下呼吸道分泌物采集等方法进行病理细胞学或病理组织学检查进行诊断㊂由于病变的性质㊁位置以及病变大小的差异性,使得常规支气管镜的诊断阳性率与操作者的技术熟练程度呈现相关性,波动在一个较大范围㊂但如何做到早期诊断,一直是临床研究的重要课题㊂随着支气管镜技术的快速发展,出现了一大批新型㊃1611㊃‘临床荟萃“ 2016年11月5日第31卷第11期 C l i n i c a l F o c u s ,N o v e m b e r 5,2016,V o l 31,N o .11Copyright ©博看网. All Rights Reserved.的支气管镜及支气管镜技术,如荧光支气管镜㊁窄谱支气管镜㊁超声支气管镜㊁电磁导航支气管镜㊁光学相干断层成像㊁共聚焦荧光/激光显微内镜等新技术,从不同角度和层面客服了传统技术存在的缺陷,极大提高了肺癌的早期诊断率,并对肺癌的分期提供了依据㊂1自荧光支气管镜(a u t o m a t i c f l u o r e s c e n c e b r o n c h o s c o p y,A F B)A F B是利用细胞自发荧光和电脑图像分析技术相结合研发的一种新型支气管镜㊂通过气管㊁支气管黏膜的荧光变化,判断有无异常病变的存在,并可根据荧光图像的显示,对荧光异常部位的黏膜进行刷检或活检,增加了早期肺癌尤其是癌前病变或原位癌和局部黏膜浸润癌的检出率,但特异性较低[1]㊂不同文献报道的特异性差异较大,其原因之一为不同荧光设备的使用,另一个原因就是用于调查人口的患病率不同[2]㊂一项对15个中心㊁14项研究的结果进行的荧光支气管镜和白光支气管镜诊断率的m e t a分析结果显示[3],A F B的总体敏感性㊁特异性㊁阳性似然率和阴性似然率分别为0.90(95%C I=0.84~0.93), 0.56(95%C I=0.45~0.66),2.0(r a n g e,1.7~ 2.5)和0.18(r a n g e,0.13~0.26),诊断比值比为11,普通光支气管镜(W L B)的总体敏感性㊁特异性㊁阳性似然率和阴性似然率分别为0.66(95%C I=0.58~ 0.73),0.69(95%C I=0.57~0.79),2.1(1.6~ 2.9)和0.50(0.43~0.58),诊断比值比为4㊂总结认为A F B在肺癌和癌前病变的检出率方面优于传统的W L B㊂另一项来自21个研究3266例患者的m e t a分析结果显示[4],A F B+W L B在癌前病变和浸润癌的检测方面总体相对敏感性㊁特异性均高于单纯的W L B,结果差异有统计学意义㊂研究显示A F B在癌前病变检出诊断价值与荧光支气管镜的类型㊁病变的程度㊁调查人群的病变发生率甚至支气管镜检查医生的经验高度相关[5]㊂低敏感性一直是A F B的一个重要问题,与其他光学支气管镜图像技术结合可以提高A F B的诊断性能[6]㊂2支气管内超声(e n d o b r o n c h i a l a l t r a s o u n d,E B U S) E B U S的出现扩大了支气管镜诊断的能力,是介入呼吸病学领域近年来的重大进展之一㊂E B U S有两种形式,包括径向和线性[7]㊂两种均通过一个传感器产生和接受声波,组织反射的声波通过处理器合成生成二维超声图像㊂放射状的超声探头不仅可以引导经纤维支气管镜针吸活检术(T B N A),还可以评估气道结构㊂另一方面,线性超声可以在实时超声引导下进行纵隔㊁肺门㊁肺内淋巴结的T B N A[7-8]㊂由此,E B U S仪器设备目前分两大类,一类是一体化的超声支气管镜,即将凸面超声搭载于支气管镜的前端㊂由于镜体较粗,主要用于叶支气管以上气管㊁支气管内外病变以及相应区域淋巴结探查㊂该型超声还具有多普勒模式,可对病变内的血管㊁血液供应丰富程度进行评估,此外还能清晰显示病变周围组织的血管情况,给穿刺活检提供安全保障㊂由于其可在实时引导下进行病灶的穿刺活检,不仅显著提高了诊断的阳性率,而且较传统的盲法穿刺显著提高了操作的安全性㊂另一类是通过支气管镜工作孔道插入超声探头的方法㊂微型超声探头由于直径小,可伸入亚段5~7级的支气管,通过与支气管壁的紧密接触对肺外周病变进行探查㊂支气管周围病变表现为低回声,肺实质富含气体表现为强烈高回声,两者之间形成清晰的边界;邻近肿块的肺不张区域由于肺泡分泌物㊁肺实质㊁空气混合形成的多重界面,比肿瘤有更高的回声[9]㊂在E B U S对气管壁的结构辨识上,因为研究方法的差异,在不同的学者研究中[10-12],对于支气管壁超声图像的分层有不同认识,有5层㊁6层㊁7层的分法㊂无论以上哪种分法,肺外支气管软骨部与肺内支气管的软骨层均表现为低回声区,其内外表面由于界面反射而呈高回声,在肺外支气管膜部,其平滑肌层表现为低回声㊂目前E B U S主要应用在以下方面:①纵隔㊁肺门㊁肺内肿大淋巴结的诊断[11-13];②用于肺癌术前及术后再分期[11-17];③气管外㊁纵隔内其他良㊁恶性疾病的诊断[18-20];④用于肺外周病变的诊断[21-25]㊂3窄谱光成像支气管镜(n a r r o w b a n di m a g i n g, N B I)是利用专用的光学滤过器,将红㊁绿㊁蓝三色的宽带光过滤为窄谱的蓝光,黏膜表层及黏膜表层下的血管图像可在415n m㊁540n m波长下呈现茶色及青绿色的色调,血是黑色的,因为415n m㊁540n m波长的光线主要被血红蛋白吸收,而且其表面无反射[26]㊂通过高对比度对黏膜表面观察,可为血管病变的诊断提供重要的细微图形㊂由于癌前病变和异型增生都伴有异常血管生成,因而N B I可以通过检测支气管黏膜内的血管异常分布与血管内鳞状异型增生而诊断支气管树内的癌前病变㊁恶性病变[27-28]㊂㊃2611㊃‘临床荟萃“2016年11月5日第31卷第11期 C l i n i c a l F o c u s,N o v e m b e r5,2016,V o l31,N o.11Copyright©博看网. All Rights Reserved.支气管黏膜的病理形态包括以下几种:多点状㊁迂曲增生㊁突然截断㊂通常这些表现会一起出现,但其中一种会占有主导地位,并与肺癌的特定病理类型有关[29]㊂多点状多见于腺癌,其次是鳞癌;血管迂曲增生和血管截断多见于鳞癌[30]㊂H e r t h等[31]研究评估了单独使用N B I与联合W L B和A F I诊断率,结果发现,N B I和A F I与W L B相比,敏感性更高,但N B I 和A F I之间差异无统计学意义;无论N B I还是A F I 联合W L B检查,都不能提高敏感性;与单独使用相比,N B I与A F I联合可以提高敏感性,但差异无统计学意义㊂结论认为,N B I在早期肺癌的血管内鳞状异常增生发现上优于F B I,特异性增高而敏感性未降低㊂因而,N B I在癌前和恶性病变评估上的作用被定义为:N B I这一技术是有效的,其特异性和敏感性足以发现早期肺癌,可以识别异常增生㊁原位癌和浸润癌[31-33]㊂4电磁导航支气管镜(e l e c t r o m a g n e t i cn a v i g a t i o n b r o n c h o s c o p y,E N B)E N B的原理是将患者的胸部螺旋C T图像,通过E N B专门的软件系统进行三维重建,生成轴位㊁冠状位㊁矢状位坐标,获得模拟的3D支气管树图像,当导航探头位于电磁场中时,其空间坐标可被E B N 系统捕获,电磁定位传感器的探头位置变化可显示于显示器上并与C T图像进行叠加,E N B系统会自动生成直达靶区的导航计划,使探头准确地到达目标肺组织,从而准确定位获取病变组织㊂该技术具有无射线辐射伤害㊁导航定位精确㊁使用方便㊁无须使用造影剂的优点㊂电磁导航支气管镜设备由电磁定位板㊁定位传感探头㊁工作通道㊁计算机软件系统与显示器组成㊂该技术在人体的研究首次发表于2006年,用于肺外周病变的诊断[34],其后国内外众多研究结论不一,认为E N B的确诊率与结节大小无关[35];认为E N B对于>2c m的结节诊断率高于ɤ2c m结节,结节与胸膜距离㊁肺叶分布对诊断率无影响[36];1项发表于2014年的综述和M e t a分析纳入了15个临床试验,对E N B诊断肺内结节准确率和安全性进行分析,结果显示E N B整体诊断灵敏度为64.9%,准确率为73.9%;诊断肺癌的灵敏度为71.1%,阴性预测值为52.1%[37]㊂该技术目前除用于肺外周病变的诊断外,还被应用于淋巴结活检[38]以及放疗基准标记的放置[39]㊂研究显示电磁导航支气管镜技术与正电子发射计算机断层显像(P E T-C T)联合能提高肺外周病变的诊断率[40]㊂5虚拟导航支气管镜(v i r t u a l b r o n c h o s c o p i c n a v i g a t i o n,V B N)V B N和E B N类似,同样用薄层高分辨C T图像重建三维图像并规划路径㊂当操作人员在电脑上确定最佳路径后,V B N系统通过气道路径的动画显示,为到达活检区域提供完全视觉化的引导㊂为了保证到达目标肺组织,目前常采用可活检的超细支气管镜联合V B N,在其引导下超细支气管镜可进入到5~ 8级细支气管,发现病灶进行活检或盲检㊂临床研究结果证实,V B N联合超细支气管镜诊断周围结节病灶(8mm~3c m)的阳性率在60%~70%,V B N联合E B U S-G S较单用E B U S-G S的诊断率明显提高[41-42]㊂6共聚焦激光显微内镜(c o n f o c a l l a s e r e n d o m i c r o s c o p y,C L E)激光共聚焦扫描显微技术是一种高分辨率的显微成像技术㊂普通的光学显微镜在对较厚的标本进行观察时,来自观察点邻近区域的荧光会对结构的分辨率形成较大的干扰㊂共聚焦显微技术的关键点在于,每次只对空间上的一个点进行成像,再通过计算机扫描形成标本的二维或者三维图象㊂而成像点以外的光信号不会对图像形成干扰,从而提高了显微图像的清晰度和细节分辨能力㊂共聚焦激光显微内镜应用共聚焦显微镜成像原理,使用一根由30000根光纤及定制的微型镜片构成的直径1mm的可弯曲光纤探头替代共聚焦显微镜的物镜,通过支气管镜活检孔道进入体内,在细胞层次上对支气管黏膜结构进行扫描,获得活组织的断层图像,然后利用计算机将断层图像综合成三维图像㊂可以在常规支气管镜检查时获得气管及肺泡内的精准高分辨率的图像㊂其图像可放大1000倍,组织探测深度可至50μm,可实时㊁分层观察黏膜的显微变化,发现早期黏膜病变㊂目前该技术已被用于辅助检测外周型肺癌及间质性肺病等㊂初期的研究已在肺外周结节良恶性方面有了初步的图像标准,在检测间质性肺病形态学改变㊁评估慢性肺病气道重建的模式㊁观察判断肺移植排斥以及实时监测I C U患者等方面被证实确立有潜在价值[43-48]㊂7细胞内镜(e n d o-c y t o s c o p y s y s t e m,E C S) 2003年日本O l y m p u s即研制出了细胞内镜系统,但因故未能批准生产,这同样也是一种光学活检技术㊂一项对细胞内镜系统的功能进行的研究[49],㊃3611㊃‘临床荟萃“2016年11月5日第31卷第11期 C l i n i c a l F o c u s,N o v e m b e r5,2016,V o l31,N o.11Copyright©博看网. All Rights Reserved.细胞内镜系统可以通过支气管镜进入支气管树对正常的支气管黏膜上皮㊁黏膜异常增生及鳞状细胞癌进行显微成像,然后在显示器上进行570倍的放大㊂对22例患者,其中鳞状细胞癌7例,鳞状不典型增生11例和光动力(P D T)治疗后4例,进行了白光㊁N B I 和A F I支气管镜检查㊂对异常和正常的支气管黏膜都进行了0.5%亚甲蓝染色并在E C S高倍镜下进行观察㊂对活检标本的组织学检查用苏木精和伊红染色㊂结果发现正常支气管黏膜纤毛柱状上皮细胞可见,而支气管鳞状不典型增生,富含包浆的表面细胞规律排列㊂在鳞状细胞癌,大的多形态的肿瘤细胞呈现密度增加的不规则分层形态㊂其E C S图像与常规的光学显微镜组织学检查一致㊂结论认为E C S可以在支气管镜实时检查时有效地鉴别正常支气管上皮细胞㊁异常细胞和肿瘤细胞检查㊂2013年一项研究通过微型照相机捕捉支气管镜下的白光显微图像,使用单个显微光束同时获得细胞内镜和荧光共聚焦显微内镜的图像,为将白光与荧光图像结合起来的多模式内镜提供了可能[50]㊂8光学相干断层成像(o p t i c a l c o h e r e n c e t o m o g r a p h y,O C T)光学相干断层成像术是一种高分辨率,非接触性㊁无创的生物组织成像技术㊂1991年美国麻省理工学院最先报道了这一技术,后被用于眼科疾病的诊断,继而被消化专业学者引入内镜诊断的范畴,并迅速扩展到呼吸道㊁心血管㊁泌尿道等㊂O C T利用对组织无损伤的低能量近红外线作为光源,采用光学干涉原理,获得反射的组织断层扫描图像,检测生物组织微小结构,其图像分辨率达微米级[51]㊂近年来有学者将O C T用于肺部疾病的研究㊂其成像原理与超声成像技术类似,但由于光传播速度约为声速的20万倍,因而O C T可以获得即时图像㊂将光源发出的光线分成两束,一束发射到被检组织,称为信号臂,另一束光线发射到作为参照的反光镜上,两束光波长一致时,光线产生干涉效益㊂生物组织反射回来的光线信号随组织的性状而显示不同强弱,光信号经经计算机处理,得出与超声㊁C T类似的二次断层图像,其图像分辨率为10~20μm,图像清晰度接近组织学切片的多层显微结构,是目前诊断技术中图像分辨率最高的[52]㊂研究发现O C T 图像能清晰显示气道上皮㊁黏膜㊁软骨㊁腺体和皮下组织[53]㊂有学者将其与荧光支气管镜联合用于检查早期肺癌病变部位,结果发现O C T图像对气道上皮增殖㊁肥厚㊁上皮化生㊁原位癌和浸润癌等癌前病变的显示清晰度与组织学图像相似,认为两者联合能够提高诊断的特异性[54]㊂O C T采用对人体组织无损伤的低能量光源,操作简单㊁可重复成像,无射线暴露的风险[55],但光穿透能力弱,仅能显示1.5~2.0 mm深度组织形态,对严重钙化㊁纤维增殖病变穿透能力有限,尚无法取代组织学活检[56]㊂目前,已有O C T采用激光替代近红外线光,光线穿透力显著增强,使得扫描范围加大,图像分辨率进一步提高[57]㊂支气管镜技术与放射学㊁超声学和电磁导航等新技术相结合,不仅扩展了对远端气管的检查范围,还促进了对气管恶性病变的准确分期㊂支气管镜新技术极大程度提高了肺癌的早诊率㊂我们相信,随着科学技术的飞速发展,支气管镜检查新技术将会得到进一步发展与完善,成为肺癌早期诊断最重要的方法㊂参考文献:[1]v a nd e r H e i j d e n E H,H o e f s l o o t W,v a n H e e s HW,e ta l.H i g hd e f i n i t i o nb r o n c h o s c o p y:a r a n d o m i z e d e x p l o r a t o r y s t u d yo f d i a g n o s t i c v a l u e c o m p a r e d t o s t a n d a r d w h i t e l i g h tb r o nc h o s c o p y a n da u t o f l u o r e s c e n c eb r o n c h o s c o p y[J].R e s p i rR e s,2015,16(1):33.[2] Z a r i cB,P e r i nB,B e c k e rH D,e t a l.A u t o f l u o r e s c e n c e i m a g i n gv i d e o b r o n c h o s c o p y i n t h e d e t e c t i o n o fl u n g c a n c e r:f r o mr e s e a r c ht o o lt o e v e r y d a y p r o c e d u r e[J].E x p e r t R e v M e dD e v i c e s,2011,8(2):167-172.[3] C h e n W,G a o X,T i a n Q,e t a l.A c o m p a r i s o n o fa u t o f l u o r e s c e n c eb r o nc h o s c o p y a n dw h i t e l i g h t b r o n c h o s c o p y i nd e t e c t i o no fl u n g c a n c e ra n d p r e n e o p l a s t i cl e s i o n s:a m e t a-a n a l y s i s[J].L u n g C a n c e r,2011,73(2):183-188.[4]S u n J,G a r f i e l d D H,L a m B,e t a l.T h e v a l u e o fa u t o f l u o r e s c e n c eb r o nc h o s c o p y c o m b i n ed w i t h w h i te l i g h tb r o nc h o s c o p y c o m p a r e dw i t hw h i t e l i g h t a l o n e i n t h ed i a g n o s i so f i n t r a e p i t h e l i a ln e o p l a s i aa n di n v a s i v el u n g c a n c e r:a m e t a-a n a l y s i s[J].JT h o r a cO n c o l,2011,6(8):1336-1344.[5] Z a r i cB,S t o j s i cV,S a r c e vT,e t a l.A d v a n c e db r o n c h o s c o p i ct e c h n i q u e s i n d i a g n o s i s a n d s t a g i n g o f l u n g c a n c e r[J].JT h o r a cD i s,2013,5(4):S359-370.[6] G a b r e c h tT,R a d uA,G r o s j e a nP,e t a l.I m p r o v e m e n t o f t h es p e c i f i c i t y o fc a n c e rd e t e c t i o nb y a u t o f l u o r e s c e n c e i m a g i n g i nt h e t r a c h e o-b r o n c h i a l t r e eu s i n g b a c k s c a t t e r e dv i o l e t l i g h t[J].P h o t o d i a g n o s i sP h o t o d y nT h e r,2008,5(1):2-9.[7] D i n c e rH E.L i n e a rE B U S i n s t a g i n g n o n-s m a l l c e l l l u n g c a n c e ra n d d i a g n o s i n gb e n i g n d i s e a s e s[J].J B r o nc h o l o g y I n t e r vP u l m o n o l,2013,20(1):66-76.[8] G r o t hS S,W h i t s o n B A,D C u n h aJ,e ta l.E n d o b r o n c h i a lu l t r a s o u n d-g u i d e d f i n e-n e e d l ea s p i r a t i o no fm e d i a s t i n a l l y m p hn o d e s:as i n g l ei n s t i t u t i o n se a r l y l e a r n i n g c u r v e[J].A n n㊃4611㊃‘临床荟萃“2016年11月5日第31卷第11期 C l i n i c a l F o c u s,N o v e m b e r5,2016,V o l31,N o.11Copyright©博看网. All Rights Reserved.T h o r a cS u r g,2008,86(4):1104-1109.[9] B a b a M,S e k i n e Y,S u z u k i M,e ta l.C o r r e l a t i o n b e t w e e ne n d o b r o n c h i a l u l t r a s o n o g r a p h y(E B U S)i m a g e sa n dh i s t o l o g i cf i n d i ng s i nn o r m a l a n d t u m o r-i n v a d e db r o n chi a lw a l l[J].L u n gC a n c e r,2002,35(1):65-71.[10] T a n a k aF,Mu r oK,Y a m a s a k i S,e t a l.E v a l u a t i o n o f t r a c h e ob r o nc h i a lw a l l i n v a s i o nu s i n g t r a n s b r o n c h i a lu l t r a s o n o g r a p h y(T B U S)[J].E u r JC a r d i o t h o r a c S u r g,2000,17(5):570-574.[11] H e r t hF,E r n s tA,S c h u l zM,e t a l.E n d o b r o n c h i a l u l t r a s o u n dr e l i a b l y d i f f e r e n t i a t e s b e t w e e n a i r w a y i n f i l t r a t i o n a n dc o m p r e s s i o nb y t u m o r[J].C h e s t,2003,123(2):458-462.[12] H e r t hF J,E b e r h a r d t R,K r a s n i k M,e ta l.E n d o b r o n c h i a lu l t r a s o u n d-g u i d e dt r a n s b r o n c h i a ln e e d l ea s p i r a t i o n o fl y m p hn o d e s i n t h e r a d i o l o g i c a l l y a n d p o s i t r o ne m i s s i o nt o m o g r a p h y-n o r m a lm e d i a s t i n u mi n p a t i e n t sw i t h l u n g c a n c e r[J].C h e s t, 2008,133(4):887-891.[13]金发光,王小平,傅恩清,等.支气管内超声引导针吸活检术在肺癌纵隔淋巴结分期和治疗中的价值[J].中华肺部疾病杂志, 2015,8(5):5-7.[14] C e t i n k a y aE,O z gül MA,T u t a r N,e ta l.T h e d i a g n o s t i cu t i l i t y o fr e a l-t i m e E B U S-T B N A f o r h i l a r a n d m e d i a s t i n a l l y m p hn o d e s i n c o n v e n t i o n a lT B N An e g a t i v e p a t i e n t s[J].A n nT h o r a cC a r d i o v a s cS u r g,2014,20(2):106-112. [15] A n r a k u M,P i e r r e A F,N a k a j i m a T,e ta l.E n d o b r o n c h i a lu l t r a s o u n d-g u i d e d t r a n s b r o n c h i a l n e e d l e a s p i r a t i o n i n t h em a n a g e m e n t o f p r e v i o u s l y t r e a t e d l u n g c a n c e r[J].A n nT h o r a cS u r g,2011,92(1):251-255.[16]S t e i n f o r t D P,S i v a S,L e o n g T L,e t a l.S y s t e m a t i ce n d o b r o n c h i a l u l t r a s o u n d-g u i d e d m e d i a s t i n a l s t a g i n g v e r s u sp o s i t r o ne m i s s i o nt o m o g r a p h y f o rc o m p r e h e n s i v e m e d i a s t i n a l s t a g i n g i nN S C L Cb e f o r e r a d i c a l r a d i o t h e r a p y o f n o n-s m a l l c e l l l u n g c a n c e r:a p i l o t s t u d y[J].M e d i c i n e(B a l t i m o r e),2016,95(8):e2488.[17] H e r t hF J,A n n e m aJ T,E b e r h a r d tR,e ta l.E n d o b r o n c h i a lu l t r a s o u n dw i t ht r a n s b r o n c h i a ln e e d l ea s p i r a t i o nf o r r e s t a g i n g t h em e d i a s t i n u mi nl u n g c a n c e r[J].JC l i n O n c o l,2008,26(20):3346-3350.[18]孙瑞琳,金发光,王佳,等.经支气管镜针吸活检术在气管纵隔周围病变诊断中的临床应用[J].中华肺部疾病杂志,2014,7(4):4-7.[19] D i n c e rH E.L i n e a rE B U S i n s t a g i n g n o n-s m a l l c e l l l u n g c a n c e ra n d d i a g n o s i n gb e n i g n d i s e a s e s[J].J B r o nc h o l o g y I n t e r vP u l m o n o l,2013,20(1):66-76.[20] T u r n e r J F.E n d o b r o n c h i a l u l t r a s o u n d a n d p e r i p h e r a lp u l m o n a r y l e s i o n s:l o c a l i z a t i o na n dh i s t o p a t h o l o g i cc o r r e l a t e s u s i n g a m i n i a t u r e p r o b ea n dt h ef l e x i b l eb r o n c h o s c o p e[J].C h e s t,2002,122(6):1874-1875.[21]李王平,马李杰,潘蕾,等.导向鞘引导的超声内镜在300例肺周围型病变诊断中的应用分析[J].中华肺部疾病杂志,2015,8(5):16-19.[22] P a o n e G,N i c a s t r i E,L u c a n t o n i G,e ta l.E n d o b r o n c h i a lu l t r a s o u n d-d r i v e nb i o p s y i nt h ed i a g n o s i so f p e r i p h e r a ll u n g l e s i o n s[J].C h e s t,2005,128(5):3551-3557. [23] H e r t h F J.E n d o b r o n c h i a lu l t r a s o u n d-g u i d e d b i o p s y o fc o i nl e s i o n s[J].F u t u r eO n c o l,2007,3(3):273-275. [24] K o k k o n o u z i s I,S t r i m p a k o sA S,L a m p a d i t i s I,e t a l.T h e r o l eo fe n d o b r o n c h i a l u l t r a s o u n d i n l u n g c a n c e r d i a g n o s i s a n d s t a g i n g:a c o m p r e h e n s i v e r e v i e w[J].C l i nL u n g C a n c e r,2012, 13(6):408-415.[25] Z a r i c B,P e r i nB.U s e o f n a r r o w-b a n d i m a g i n g b r o n c h o s c o p y i nd e t e c t i o no f l u n g c a n c e r[J].E x p e r t R e vM e dD e v i c e s,2010,7(3):395-406.[26] B o j a nZ,B r a n i s l a vP,A l e k s a n d r a J,e t a l.I n f l u e n c e o f n a r r o wb a n d i m a g i n g(N B I)v i d e o b r o nc h o s c o p y o nt h ea s s e s s m e n to fc e n t r a l l u n g c a n c e re x t e n s i o n a n dt h e r a p e u t i cde c i s i o n[J].C a n c e r I n v e s t,2009,27(9):918-923.[27] Z a r i cB,B e c k e r H D,P e r i n B,e ta l.N a r r o w b a n di m a g i n gv i d e o b r o n c h o s c o p y i m p r o v e s a s s e s s m e n t o f l u n g c a n c e re x t e n s i o na n di nf l u e n c e st h e r a p e u t i cs t r a t eg y[J].J p nJC l i nO n c o l,2009,39(10):657-663.[28]S h i b u y aK,H o s h i n o H,C h i y o M,e t a l.H i g h m a g n i f i c a t i o nb r o nc h o v ide o s c o p y c o m b i n e dw i t hn a r r o wb a n d i m a g i n g c o u l dd e t e c tc a p i l l a r y l o o p s o f a n g i o g e n i c s q u a m o u s d y s p l a s i ai nh e a v y s m o k e r s a t h i g h r i s k f o r l u n g c a n c e r[J].T h o r a x,2003,58(11):989-995.[29] Z a r i cB,P e r i nB,S t o j s i cV,e t a l.R e l a t i o nb e t w e e nv a s c u l a rp a t t e r n s v i s u a l i z e d b y N a r r o w B a n d I m a g i n g(N B I) v i d e o b r o n c h o s c o p y a n d h i s t o l o g i c a lt y p eo fl u n g c a n c e r[J].M e dO n c o l,2013,30(1):374.[30] H e r t hF J,E b e r h a r d tR,A n a n t h a m D,e ta l.N a r r o w-b a n di m a g i n g b r o n c h o s c o p y i n c r e a s e s t h e s p e c i f i c i t y o fb r o nc h o s c o p i c e a r l y l u n g c a n c e rde t e c t i o n[J].JT h o r a cO n c o l,2009,4(9):1060-1065.[31] Z a r i cB,P e r i nB,S t o j s i cV,e t a l.D e t e c t i o no f p r e m a l i g n a n tb r o nc h i a l l e s i o n s c a nb e s i g n i f i c a n t l y i m p r o v e db y c o m b i n a t i o no f a d v a n c e d b r o n c h o s c o p i c i m a g i n g t e c h n i q u e s[J].A n nT h o r a cM e d,2013,8(2):93-98.[32] V i n c e n tB D,F r a i g M,S i l v e s t r iG A.A p i l o t s t u d y o f n a r r o w-b a n d i m a g i n gc o m p a r ed t o w h i te l i g h t b r o n c h o s c o p yf o re v a l u a t i o nof n o r m a l a i r w a y sa n d p r e m a l ig n a n t a n d m a l i g n a n ta i r w a y s d i s e a s e[J].C h e s t,2007,131(6):1794-1799.[33]S c h w a r z Y,G r e i f J,B e c k e r H D,e t a l.R e a l-t i m ee l e c t r o m a g n e t i cn a v i g a t i o n b r o n c h o s c o p y t o p e r i p h e r a ll u n gl e s i o n s u s i n g o v e r l a i dC Ti m a g e s:t h e f i r s th u m a ns t u d y[J].C h e s t,2006,129(4):988-994.[34] W i l s o n D S,B a r t l e t t R J.I m p r o v e d d i a g n o s t i c y i e l d o fb r o nc h o s c o p y i n a c o mm u n i t y p r a c t i c e:c o m b i n a t i o n o fe l e c t r o m a g n e t i c n a v i g a t i o ns y s t e ma n d r a p i do n-s i t e e v a l u a t i o n[J].JB r I n t P u l m o n o l,2007,14(4):227-232.[35]J e n s e n KW,H s i a DW,S e i j o L M,e t a l.M u l t i c e n t e re x p e r i e n c ew i t he l e c t r o m a g n e t i cn a v i g a t i o n b r o n c h o s c o p yf o rt h e d i a g n o s i s o f p u l m o n a r y n o d u l e s[J].JB r o n c h o l o g y I n t e r v㊃5611㊃‘临床荟萃“2016年11月5日第31卷第11期 C l i n i c a l F o c u s,N o v e m b e r5,2016,V o l31,N o.11Copyright©博看网. All Rights Reserved.P u l m o n o l,2012,19(3):195-199.[36] G e xG,P r a l o n g J A,C o m b e s c u r eC,e ta l.D i a g n o s t i c y i e l da n d s a f e t y o f e l e c t r o m a g n e t i c n a v i g a t i o nb r o nc h o s c o p y f o r l u n gn o d u l e s:a s y s t e m a t i c r e v i e w a n d m e t a-a n a l y s i s[J].R e s p i r a t i o n,2014,87(2):165-176.[37] D i k e nÖE,K a r n a k D,Çi l e d a㊅g A,e t a l.E l e c t r o m a g n e t i cn a v i g a t i o n-g u i d e d T B N A v s c o n v e n t i o n a l T B N A i n t h ed i a g n o s i s o fme d i a s t i n a l l y m p h a d e n o p a t h y[J].C l i nR e s p i rJ,2015,9(2):214-220.[38]S c h r o e d e r C,H e j a l R,L i n d e n P A.C o i l s p r i n g f i d u c i a lm a r k e r s p l a c e d s a f e l y u s i n g n a v i g a t i o n b r o n c h o s e o p y i ni n o p e r a b l e p a t i e n t s a l l o w s a c c u r a t e d e l i v e r y o f C y b e r K n i f es t e r e o t a c t i c r a d i o s u r g e r y[J].JT h o r a cC a r d i o v a s c S u r g,2010, 140(5):1137-1142.[39] L a m p r e c h t B,P o r s e h P,P i r i c h C,e ta l.E l e c t r o m a g n e t i cn a v i g a t i o n b r o n c h o s c o p y i n c o m b i n a t i o n w i t h P E T-C T a n d r a p i d o n-s i t e c y t o p a t h o l o g i c e x a m i n a t i o n f o r d i a g n o s i s o f p e r i p h e r a l l u n g l e s i o n s[J].L u n g,2009,187(1):55-59. [40] A s a n oF.V i r t u a lb r o n c h o s c o p i c n a v i g a t i o n[J].C l i n C h e s tM e d,2010,31(1):75-85.[41]潘蕾,段瑞,薄丽艳,等.虚拟支气管镜导航联合超细支气管镜诊断肺外周病变的随机㊁临床试验研究[J].中华肺部疾病杂志,2015,8(5):20-24.[42] A r e n b e r g D A,G i l d e aT,W i l s o nD.P r o p o s e dc l a s s i f i c a t i o no fp r o b e-b a s e dc o n f o c a l l a s e re n d o m i c r o s c o p y(p C L E)f i n d i n g sf o re v a l u a t i o no f i n d e t e r m i n a t e p e r i p h e r a l l u ng n o d u l e s[J].A mJR e s p i rC r i tC a r eM e d,2011,183,A6097.[43] F u c h s F S,Z i r l i k S,H i l d n e r K,e t a l.C o n f o c a l l a s e re n d o m i c r o s c o p yf o rd i ag n o s i n g l u n g c a n c e ri n v i v o[J].E u rR e s p i r J,2013,41(6):1401-1408.[44] N e w t o n R C,K e m p S V,Y a n g G Z,e t a l.I m a g i n gp a r e n c h y m a l l u n g d i s e a s e sw i t hc o n f o c a l e n d o m i c r o s c o p y[J].R e s p i rM e d,2012,106(1):127-137.[45]S a l aün M,R o u s s e l F,B o u r g-H e c k l y G,e t a l.I nv i v o p r o b e-b a s e dC o n f oc a lL a s e rE nd o m i c r o s c o p y i n A m i o d a r o n e-re l a t e dP n e u m o n i a.E u r o p e a nR e s p i r a t o r y J o u r n a l[J].E u rR e s p i r J, 2013,42(6):1646-1658.[46] K e l l e r C A,E r a s m u s D,A l v a r e z F,e t a l.P r e l i m i n a r yo b s e r v a t i o n s i n t h eu s eo f c o n f o c a l a l v e o l a r e n d o m i c r o s c o p y i n r e c i p i e n t s o f s i n g l e l u n g t r a n s p l a n t a t i o n[J].A mJR e s p i rC r i tC a r eM e d,2010,181,A4316.[47] B i c k e n b a c h J,C z a p l i k M,D e m b i n s k i R,e t a l.I n v i v om i c r o s c o p y i na p o r c i n em o d e l o f a c u t e l u n g i n j u r y[J].R e s p i rP h y s i o lN e u r o b i o l,2010,172(3):192-200.[48]S h i b u y a K,F u j i w a r a T,Y a s u f u k u K,e t a l.I n v i v om i c r o s c o p i c i m a g i n g o ft h eb r o n c h i a lm u c o s au s i n g a ne n d o-c y t o s c o p y s y s t e m[J].L u n g C a n c e r,2011,72(2):184-190.[49] H u g h e sM,C h a n g T P,Y a n g G Z.F i b e r b u n d l e e n d o c y t o s c o p y[J].B i o m e dO p tE x p r e s s,2013,4(12):2781-2794. [50]洪城,钟南山,王玮.光学相干断层成像技术在肺部疾病应用的研究进展[J].中华医学杂志,2013,93(2):152-154. [51] R e g r a E,S e h a r J A,M o n t E,e t a l.O p t i c a l c o h e r e n c et o m o g r a p h y[J].C r a d i o v a s cR a d i a tM e d,2003,4(4):198-204.[52] P i t r i sC,B r e z i n s k i M E,B o u m a B E,e ta l.H i g hr e s o l u t i o nI m a g i n g o f t h eu p p e rr e s p i r a t o r y t r a c tw i t ho p t i c a l c o h e r e n c et o m o g l a p h y[J].A mJR e s p i rC r i tC a r e M e d,1998,157(5): 1640-1664.[53] L a m S,S t a n d i s h B,B a l d w i n C,e t a l.I n v i v o o p t i c a lc o h e r e n c e t o m o g r a p h y i m a g i n g o f p r e i n v a s i v e b r o n c h i a l l e s i o n s[J].C l i nC a n c e rR e s,2008,14(7):2006-2011.[54] C o x s o nHO,E a s t w o o dP R,W i l i a m s o n J P,e t a l.P h e n o t y p i n ga i r w a y d i s e a s e w i t h o p t i c a l c o h e r e n c e t o m o g r a p h y[J].R e s p i o r l o g y,2011,16(1):34-43.[55]J a n g I K,T e r a n e y G J,M a c N e i l l B,e t a l.I n v i v oc h a r a c t e r i z a t i o no fc o r o n a r y a t h e r o s c l e r o t i c p l a q u eb y u s eo fo p t i c a lc o h e r e n c et o m o g r a p h y[J].C i r c u l a t i o n,2005,111(12):1551-1555.收稿日期:2016-09-19编辑:姜恒丽㊃6611㊃‘临床荟萃“2016年11月5日第31卷第11期 C l i n i c a l F o c u s,N o v e m b e r5,2016,V o l31,N o.11Copyright©博看网. All Rights Reserved.。

一种基于二值形态学原理的肺部轮廓提取算法文章编号：1671-7104(2010)05-0413-05【作 者】【摘 要】【关 键 词】【中图分类号】【文献标识码】【 Writers 】【 Abstract 】【Key words 】李露1，马艺馨1，吴华伟21 上海交通大学电子信息与电气工程学院仪器科学与工程系，上海，2002402 上海交通大学医学院附属仁济医院放射科，上海，200127结合二值形态学原理，对人体胸腔横截面的CT图像通过标记、搜索连通域等处理，提取胸腔的轮廓和肺及食管的轮廓。

将处理图像复原与原图像进行对比表明，本文所采用的方法能准确地提取人体胸腔和肺及食管的轮廓，误差小于人眼的辨别能力。

医学图像处理；边缘检测；二值形态学；对象标记R445A doi:10.3969/j.isnn.1671-7104.2010.06.007Li Lu 1, Ma Yixin 1, Wu Huawei 21 Department of Instrument Science and Engineering, School of Electronics, Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240；2 Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai 200240)A method is presented in this paper which processes the human chest CT image with binary morphology theory, thenmarks and searches each connected domain to find chest contour and boundaries of lung and esophagus. Comparing with original CT image, the extracted boundaries have sufficient accuracy and human eyes cannot distinguish the error.medical image processing, edge detection, binary morphology, object tag收稿日期：2010-05-09基金项目：上海市浦江人才计划（08PJ1406900），上海交通大学医工(理) 交叉基金项目（YG2009MS52）通讯作者：马艺馨，E-mail: y.ma@Lung Boundary Detection Method Based onBinary Morphology Theory图像分割与边缘检测技术是将图像划分成若干具有特定意义的区域,并将区域的边界提取出来的图像处理技术，是对图像中的目标进行识别和理解等后续过程的必要前提。

肺部体格检查标准操作文字版Performing a thorough physical examination of the lungs is crucial in diagnosing and monitoring respiratory conditions. 肺部的全面体格检查对于诊断和监测呼吸系统疾病至关重要。

A standardized approach to lung examination helps ensure accuracy and consistency in the assessment process. 一个标准化的肺部检查方法有助于确保评估过程的准确性和一致性。

Healthcare providers must follow established protocols and guidelines to conduct a proper lung examination. 医疗保健提供者必须遵循既定的协议和指南进行正确的肺部检查。

The first step in a lung examination is obtaining a comprehensive medical history from the patient. 在肺部检查中的第一步是从病人那里获取全面的病史。

This includes asking about any respiratory symptoms, past medical conditions, smoking history, and exposure to environmental pollutants. 这包括询问任何呼吸系统症状、过去的疾病病史、吸烟史以及暴露于环境污染物的情况。

A thorough medical history provides valuable information that can guide the physical examination and help in determining the underlying cause of any lung abnormalities. 一份全面的病史提供了有价值的信息，可以指导体格检查，并有助于确定任何肺部异常的潜在原因。