{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T20:44:57Z","timestamp":1793825097551,"version":"4.6.1"},"reference-count":45,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81830052"],"award-info":[{"award-number":["81830052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["20ZR1438300"],"award-info":[{"award-number":["20ZR1438300"]}],"id":[{"id":"10.13039\/100007219","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":[[2023,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Breast cancer is a typically diagnosed and life\u2010threatening cancer in women. Thus, dynamic contrast\u2010enhanced magnetic resonance imaging (DCE\u2010MRI) is increasingly used for breast lesion detection and diagnosis because of the high resolution of soft tissues. Moreover, supervised detection methods have been implemented for breast lesion detection. However, these methods require substantial time and specialized staff to develop the labeled training samples.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>To investigate the potential of weakly supervised deep learning models for breast lesion detection.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A total of 1003 breast DCE\u2010MRI studies were collected, including 603 abnormal cases with 770 breast lesions and 400 normal subjects. The proposed model was trained using breast DCE\u2010MRI considering only the image\u2010level labels (normal and abnormal) and optimized for classification and detection sub\u2010tasks simultaneously. Ablation experiments were performed to evaluate different convolutional neural network (CNN) backbones (VGG19 and ResNet50) as shared convolutional layers, as well as to evaluate the effect of the preprocessing methods.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Our weakly supervised model performed better with VGG19 than with ResNet50 (<jats:italic>p<\/jats:italic> &lt; 0.05). The average precision (AP) of the classification sub\u2010task was 91.7% for abnormal cases and 88.0% for normal samples. The area under the receiver operating characteristic (ROC) curve (AUC) was 0.939 (95% confidence interval [CI]: 0.920\u20130.941). The weakly supervised detection task AP was 85.7%, and the correct location (CorLoc) was 90.2%. A sensitivity of 84.0% at two\u2010false positives per image was assessed based on free\u2010response ROC (FROC) curve.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The results confirm that a weakly supervised CNN based on self\u2010transfer learning is an effective and promising auxiliary tool for detecting breast lesions.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.16296","type":"journal-article","created":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T10:08:51Z","timestamp":1677146931000},"page":"4960-4972","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Weakly supervised breast lesion detection in DCE\u2010MRI using self\u2010transfer learning"],"prefix":"10.1002","volume":"50","author":[{"given":"Rong","family":"Sun","sequence":"first","affiliation":[{"name":"School of Health Science and Engineering University of Shanghai for Science and Technology  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Radiology Ruijin Hospital Affiliated to Shanghai Jiaotong University School of Medicine  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanzhong","family":"Xie","sequence":"additional","affiliation":[{"name":"Medical Imaging Center Taian Center Hospital  Shandong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengdong","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Health Science and Engineering University of Shanghai for Science and Technology  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,3]]},"reference":[{"key":"e_1_2_9_2_1","unstructured":"WildCP WeiderpassE StewartBW.World Cancer Report: cancer research for cancer prevention.Lyon: International Agency for Research on Cancer.2020."},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2019.00080"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14389"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.22680"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2009.23.0839"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-008-0863-7"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2461061298"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2914873"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2014.12.001"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4937787"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2014.01.008"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/56\/24\/008"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2860257"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2019.02.008"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.07.007"},{"key":"e_1_2_9_17_1","doi-asserted-by":"crossref","unstructured":"HwangS KimH\u2010E.Self\u2010transfer learning for fully weakly supervised object localization.International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2016:239\u2013246.","DOI":"10.1007\/978-3-319-46723-8_28"},{"key":"e_1_2_9_18_1","doi-asserted-by":"crossref","unstructured":"MaicasG SnaauwG BradleyAP ReidI CarneiroG.Model agnostic saliency for weakly supervised lesion detection from breast DCE\u2010MRI.2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).IEEE;2019:1057\u20131060.","DOI":"10.1109\/ISBI.2019.8759402"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26721"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1378\/chest.12-2351"},{"key":"e_1_2_9_21_1","doi-asserted-by":"crossref","unstructured":"WangC RenW HuangK TanT.Weakly supervised object localization with latent category learning.13th European Conference on Computer Vision.Springer;2014:431\u2013445.","DOI":"10.1007\/978-3-319-10599-4_28"},{"key":"e_1_2_9_22_1","doi-asserted-by":"crossref","unstructured":"Marrone S.;Piantadosi G.;Fusco R.;Petrillo A.;Sansone M.;Sansone C.An investigation of deep learning for lesions malignancy classification in breast DCE\u2010MRI.Proceedings of the International Conference on Image Analysis and Processing Catania Italy 11\u201315 September 2017.Springer;2017:479\u2013489.","DOI":"10.1007\/978-3-319-68548-9_44"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-07274-x"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/physci235060b0"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2013.12.005"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/42.251128"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2010.2046908"},{"key":"e_1_2_9_28_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recogni tion.IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2016:770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_29_1","unstructured":"SimonyanK ZissermanA.Very deep convolutional networks for large\u2010scale image recognition. International Conference on Learning Representations (ICLR).2015:1\u201314."},{"key":"e_1_2_9_30_1","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava N","year":"2014","journal-title":"J Mach Learn Res"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JRS.14.026506"},{"key":"e_1_2_9_32_1","doi-asserted-by":"crossref","unstructured":"SinghS GuptaA EfrosAA.Unsupervised discovery of mid\u2010level discriminative patches.12th European Conference on Computer Vision.Springer;2012:73\u201386.","DOI":"10.1007\/978-3-642-33709-3_6"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2396361"},{"key":"e_1_2_9_35_1","doi-asserted-by":"crossref","unstructured":"ZitnickCL Doll\u00e1rP.Edge boxes: locating object proposals from edges.13th European Conference on Computer Vision.Springer;2014:391\u2013405.","DOI":"10.1007\/978-3-319-10602-1_26"},{"key":"e_1_2_9_36_1","unstructured":"GlorotX BengioY.Understanding the difficulty of training deep feedforward neural networks. 13th Int. Conf. Artif. Intell. Statist.2010:249\u2013256."},{"key":"e_1_2_9_37_1","doi-asserted-by":"crossref","unstructured":"DeselaersT AlexeB FerrariV.Localizing objects while learning their appearance.Paper presented at: 11th European Conference on Computer Vision.2010:452\u2013466.","DOI":"10.1007\/978-3-642-15561-1_33"},{"key":"e_1_2_9_38_1","doi-asserted-by":"crossref","unstructured":"BilenH VedaldiA.Ieee. Weakly supervised deep detection networks.Ieee Conference on Computer Vision and Pattern Recognition (CVPR).2016:2846\u20132854.","DOI":"10.1109\/CVPR.2016.311"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2535231"},{"key":"e_1_2_9_40_1","doi-asserted-by":"crossref","unstructured":"TangK JoulinA LiLJ LiFF.Co\u2010localization in Real\u2010World Images.Ieee Conference on Computer Vision and Pattern Recognition (CVPR).2014:1464\u20131471.","DOI":"10.1109\/CVPR.2014.190"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1541-0420.2008.01049.x"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.06.015"},{"key":"e_1_2_9_43_1","doi-asserted-by":"crossref","unstructured":"HwangS KimH\u2010E.Self\u2010transfer learning for weakly supervised lesion localization.International conference on medical image computing and computer\u2010assisted intervention Springer.2016:239\u2013246.","DOI":"10.1007\/978-3-319-46723-8_28"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2899839"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/2413706"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics10050330"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16296","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.16296","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16296","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T14:53:08Z","timestamp":1755874388000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16296"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":45,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["10.1002\/mp.16296"],"URL":"https:\/\/doi.org\/10.1002\/mp.16296","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]},"assertion":[{"value":"2022-06-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-03-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}