{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T08:54:10Z","timestamp":1791968050809,"version":"4.3.4"},"reference-count":60,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,12,7]],"date-time":"2021-12-07T00:00:00Z","timestamp":1638835200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2021,12,7]],"date-time":"2021-12-07T00:00:00Z","timestamp":1638835200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["522919591260"],"award-info":[{"award-number":["522919591260"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81974276. 523"],"award-info":[{"award-number":["81974276. 523"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2022,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Pneumothorax is a life\u2010threatening emergency that requires immediate treatment. Frontal\u2010view chest X\u2010ray images are typically used for pneumothorax detection in clinical practice. However, manual review of radiographs is time\u2010consuming, labor\u2010intensive, and highly dependent on the experience of radiologists, which may lead to misdiagnosis. Here, we aim to develop a reliable automatic classification method to assist radiologists in rapidly and accurately diagnosing pneumothorax in frontal chest radiographs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A novel residual neural network (ResNet)\u2010based two\u2010stage deep\u2010learning strategy is proposed for pneumothorax identification: local feature learning (LFL) followed by global multi\u2010instance learning (GMIL). Most of the nonlesion regions in the images are removed for learning discriminative features. Two datasets are used for large\u2010scale validation: a private dataset (27\u00a0955 frontal\u2010view chest X\u2010ray images) and a public dataset (the National Institutes of Health [NIH] ChestX\u2010ray14; 112\u00a0120 frontal\u2010view X\u2010ray images). The model performance of the identification was evaluated using the accuracy, precision, recall, specificity, F1\u2010score, receiver operating characteristic (ROC), and area under ROC curve (AUC). Fivefold cross\u2010validation is conducted on the datasets, and then the mean and standard deviation of the above\u2010mentioned metrics are calculated to assess the overall performance of the model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The experimental results demonstrate that the proposed learning strategy can achieve state\u2010of\u2010the\u2010art performance on the NIH dataset with an accuracy, AUC, precision, recall, specificity, and F1\u2010score of 94.4% \u00b1 0.7%, 97.3% \u00b1 0.5%, 94.2% \u00b1 0.3%, 94.6% \u00b1 1.5%, 94.2% \u00b1 0.4%, and 94.4% \u00b1 0.7%, respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The experimental results demonstrate that our proposed CAD system is an efficient assistive tool in the identification of pneumothorax.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.15328","type":"journal-article","created":{"date-parts":[[2021,11,21]],"date-time":"2021-11-21T05:10:00Z","timestamp":1637471400000},"page":"231-243","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Deep multi\u2010instance transfer learning for pneumothorax classification in chest X\u2010ray images"],"prefix":"10.1002","volume":"49","author":[{"given":"Yuchi","family":"Tian","sequence":"first","affiliation":[{"name":"Academy of Engineering and Technology Fudan University  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiology The Second Affiliated Hospital Zhejiang University School of Medicine  Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjie","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Radiology Ruijin Hospital Affiliated to School of Medicine Shanghai Jiao Tong University  China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering Shanghai Jiao Tong University  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dahong","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering Shanghai Jiao Tong University  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,12,7]]},"reference":[{"key":"e_1_2_10_2_1","volume-title":"Pleural Diseases","author":"Light RW","year":"2007"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.10476"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1378\/chest.11-1691"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1183\/09059180.00005310"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM200003233421207"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2213-2600(15)00220-9"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1097\/00003246-199107000-00014"},{"issue":"4","key":"e_1_2_10_9_1","first-page":"S372","article-title":"Pneumothorax: from definition to diagnosis and treatment","volume":"6","author":"Zarogoulidis P","year":"2014","journal-title":"J Thorac Dis"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2016150409"},{"key":"e_1_2_10_11_1","doi-asserted-by":"crossref","unstructured":"SutharM MahjoubfarA SealsK LeeEW JalaiiB.Diagnostic tool for pneumothorax. In2016 IEEE Photonics Society Summer Topical Meeting Series (SUM);IEEE;218\u2010219:2016.","DOI":"10.1109\/PHOSST.2016.7548806"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.183.1.1549671"},{"key":"e_1_2_10_13_1","first-page":"267","volume-title":"R\u00f6Fo\u2010Fortschritte auf dem Gebiet der R\u00f6ntgenstrahlen und der bildgebenden Verfahren","author":"Thomsen L","year":"2014"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.166.2.8553937"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2251011102"},{"key":"e_1_2_10_16_1","doi-asserted-by":"crossref","unstructured":"GevaO Zimmerman\u2010MorenoG LiebermanS KonenE GreenspanH.Pneumothorax detection in chest radiographs using local and global texture signatures. In Medical Imaging 2015: Computer\u2010Aided Diagnosis. International Society for Optics and Photonics;2015; 9414:94141P.","DOI":"10.1117\/12.2083128"},{"key":"e_1_2_10_17_1","unstructured":"DoiK SanadaS.Method and system for automatic detection of ribs and pneumothorax in digital chest radiographs. U.S. Patent 5 668 888 issued;1997."},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1378\/chest.122.2.678"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.596790"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/2908517"},{"key":"e_1_2_10_21_1","first-page":"573","article-title":"Artificial convolutional neural network in object detection and semantic segmentation for medical imaging analysis","volume":"11","author":"Yang R","year":"2021","journal-title":"Front Oncol"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09854-1"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1093\/jrr\/rrz086"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32606-7_3"},{"key":"e_1_2_10_25_1","doi-asserted-by":"crossref","unstructured":"AnandR SowmyaV GopalakrishnanEA SomanKP.Modified Vgg deep learning architecture for Covid\u201019 classification using bio\u2010medical images. InIOP Conference Series: Materials Science and Engineering.IOP Publishing;2021;1084:012001.","DOI":"10.1088\/1757-899X\/1084\/1\/012001"},{"key":"e_1_2_10_26_1","doi-asserted-by":"crossref","unstructured":"LiZ WangC HanM et\u00a0al.Thoracic disease identification and localization with limited supervision. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition;2018:8290\u20108299.","DOI":"10.1109\/CVPR.2018.00865"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-019-06130-x"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3035572"},{"key":"e_1_2_10_29_1","first-page":"1","article-title":"Deep learning algorithm for surveillance of pneumothorax after lung biopsy: a multicenter diagnostic cohort study","author":"Hwang EJ","year":"2020","journal-title":"Eur Radiol"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinimag.2020.01.008"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10140-020-01767-4"},{"key":"e_1_2_10_32_1","doi-asserted-by":"crossref","unstructured":"IqbalT ShaukatA AkramU.Automatic diagnosis of pneumothorax from chest radiographs: a systematic literature review. arXiv preprint arXiv:2012.11214 2020.","DOI":"10.1109\/ACCESS.2021.3122998"},{"key":"e_1_2_10_33_1","doi-asserted-by":"crossref","unstructured":"Sze\u2010ToA RiasatianA TizhooshHR.Searching for pneumothorax in X\u2010ray images using autoencoded deep features. arXiv preprint arXiv:2102.06096 2021.","DOI":"10.1038\/s41598-021-89194-4"},{"key":"e_1_2_10_34_1","doi-asserted-by":"crossref","unstructured":"Sze\u2010ToA WangZ.tCheXNet: detecting pneumothorax on chest X\u2010ray images using deep transfer learning. InInternational Conference on Image Analysis and Recognition.Springer Cham;2019:325\u2010332.","DOI":"10.1007\/978-3-030-27272-2_28"},{"issue":"14","key":"e_1_2_10_35_1","first-page":"1","article-title":"Automated segmentation and diagnosis of pneumothorax on chest X\u2010rays with fully convolutional multi\u2010scale ScSE\u2010DenseNet: a retrospective study","volume":"20","author":"Wang Q","year":"2020","journal-title":"BMC Med Inf Decis Making"},{"key":"e_1_2_10_36_1","unstructured":"Goo\u00dfenA DeshpandeH HarderT et\u00a0al.Deep learning for pneumothorax detection and localization in chest radiographs. arXiv preprint arXiv:1907.07324;2019."},{"key":"e_1_2_10_37_1","doi-asserted-by":"crossref","unstructured":"DengJ DongW SocherR LiLi\u2010J LiK Fei\u2010FeiLi Imagenet: a large\u2010scale hierarchical image database. In2009 IEEE Conference on Computer Vision and Pattern Recognition.IEEE;2009:248\u2010255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_10_38_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Institute of Electrical and Electronic Engineers;2016:770\u2010778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_2_10_40_1","doi-asserted-by":"crossref","unstructured":"TanC SunF KongT et\u00a0al.A survey on deep transfer learning. InInternational Conference on Artificial Neural Networks.Springer Cham;2018:270\u2010279.","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2021.110713"},{"key":"e_1_2_10_43_1","article-title":"COVID\u201019 diagnosis from chest X\u2010ray images using transfer learning: enhanced performance by debiasing dataloader","author":"Polat \u00c7","journal-title":"J Xray Sci Technol"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11031242"},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-78060-4"},{"key":"e_1_2_10_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2017.08.001"},{"key":"e_1_2_10_47_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.U\u2010net: convolutional networks for biomedical image segmentation. InInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer Cham;2015:234\u2010241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"6","key":"e_1_2_10_48_1","first-page":"475","article-title":"Two public chest X\u2010ray datasets for computer\u2010aided screening of pulmonary diseases","volume":"4","author":"Jaeger S","year":"2014","journal-title":"Quant Imag Med Surg"},{"key":"e_1_2_10_49_1","doi-asserted-by":"crossref","unstructured":"StirenkoS KochuraY AlieninO et\u00a0al.Chest X\u2010ray analysis of tuberculosis by deep learning with segmentation and augmentation. In2018 IEEE 38th International Conference on Electronics and Nanotechnology (ELNANO).IEEE;2018:422\u2010428.","DOI":"10.1109\/ELNANO.2018.8477564"},{"key":"e_1_2_10_50_1","doi-asserted-by":"crossref","unstructured":"WangX PengY LuLe LuZ BagheriM SummersRM.Chestx\u2010ray8: hospital\u2010scale chest x\u2010ray database and benchmarks on weakly\u2010supervised classification and localization of common thorax diseases. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Institute of Electrical and Electronic Engineers 2017:2097\u20102106.","DOI":"10.1109\/CVPR.2017.369"},{"key":"e_1_2_10_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(96)00034-3"},{"key":"e_1_2_10_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.009"},{"key":"e_1_2_10_53_1","doi-asserted-by":"crossref","unstructured":"SzegedyC IoffeS VanhouckeV AlemiA.Inception\u2010v4 inception\u2010resnet and the impact of residual connections on learning. InProceedings of the AAAI Conference on Artificial Intelligence;2017;31(1).","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"e_1_2_10_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-2766-4"},{"key":"e_1_2_10_55_1","unstructured":"IoffeS SzegedyC.Batch normalization: accelerating deep network training by reducing internal covariate shift. InInternational Conference on Machine Learning. PMLR 2015:448\u2010456."},{"issue":"11","key":"e_1_2_10_56_1","article-title":"Visualizing data using t\u2010SNE","volume":"9","author":"Van der Maaten L","year":"2008","journal-title":"J Mach Learn Res"},{"key":"e_1_2_10_57_1","unstructured":"HendrycksD BasartS MuN et\u00a0al.The many faces of robustness: a critical analysis of out\u2010of\u2010distribution generalization. arXiv preprint arXiv:2006.16241;2020."},{"key":"e_1_2_10_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3006377"},{"key":"e_1_2_10_59_1","unstructured":"KunduJN VenkatN Venkatesh BabuR.Universal source\u2010free domain adaptation. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition;2020:4544\u20104553."},{"key":"e_1_2_10_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107109"},{"key":"e_1_2_10_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101766"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15328","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15328","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15328","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T08:34:41Z","timestamp":1791966881000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15328"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,7]]},"references-count":60,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["10.1002\/mp.15328"],"URL":"https:\/\/doi.org\/10.1002\/mp.15328","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,7]]},"assertion":[{"value":"2021-01-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}