{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T15:36:01Z","timestamp":1792164961995,"version":"4.4.0"},"reference-count":34,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T00:00:00Z","timestamp":1692403200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Magnetic Resonance Imaging"],"published-print":{"date-parts":[[2024,6]]},"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Deep learning models require large\u2010scale training to perform confidently, but obtaining annotated datasets in medical imaging is challenging. Weak annotation has emerged as a way to save time and effort.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>To develop a deep learning model for 3D breast cancer segmentation in dynamic contrast\u2010enhanced magnetic resonance imaging (DCE\u2010MRI) using weak annotation with reliable performance.<\/jats:p><\/jats:sec><jats:sec><jats:title>Study Type<\/jats:title><jats:p>Retrospective.<\/jats:p><\/jats:sec><jats:sec><jats:title>Population<\/jats:title><jats:p>Seven hundred and thirty\u2010six women with breast cancer from a single institution, divided into the development (<jats:italic>N<\/jats:italic>\u2009=\u2009544) and test dataset (<jats:italic>N<\/jats:italic>\u2009=\u2009192).<\/jats:p><\/jats:sec><jats:sec><jats:title>Field Strength\/Sequence<\/jats:title><jats:p>3.0\u2010T, 3D fat\u2010saturated gradient\u2010echo axial T1\u2010weighted flash 3D volumetric interpolated brain examination (VIBE) sequences.<\/jats:p><\/jats:sec><jats:sec><jats:title>Assessment<\/jats:title><jats:p>Two radiologists performed a weak annotation of the ground truth using bounding boxes. Based on this, the ground truth annotation was completed through autonomic and manual correction. The deep learning model using 3D U\u2010Net transformer (UNETR) was trained with this annotated dataset. The segmentation results of the test set were analyzed by quantitative and qualitative methods, and the regions were divided into whole breast and region of interest (ROI) within the bounding box.<\/jats:p><\/jats:sec><jats:sec><jats:title>Statistical Tests<\/jats:title><jats:p>As a quantitative method, we used the Dice similarity coefficient to evaluate the segmentation result. The volume correlation with the ground truth was evaluated with the Spearman correlation coefficient. Qualitatively, three readers independently evaluated the visual score in four scales. A <jats:italic>P<\/jats:italic>\u2010value &lt;0.05 was considered statistically significant.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The deep learning model we developed achieved a median Dice similarity score of 0.75 and 0.89 for the whole breast and ROI, respectively. The volume correlation coefficient with respect to the ground truth volume was 0.82 and 0.86 for the whole breast and ROI, respectively. The mean visual score, as evaluated by three readers, was 3.4.<\/jats:p><\/jats:sec><jats:sec><jats:title>Data Conclusion<\/jats:title><jats:p>The proposed deep learning model with weak annotation may show good performance for 3D segmentations of breast cancer using DCE\u2010MRI.<\/jats:p><\/jats:sec><jats:sec><jats:title>Level of Evidence<\/jats:title><jats:p>3<\/jats:p><\/jats:sec><jats:sec><jats:title>Technical Efficacy<\/jats:title><jats:p>Stage 2<\/jats:p><\/jats:sec>","DOI":"10.1002\/jmri.28960","type":"journal-article","created":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T20:06:59Z","timestamp":1692648419000},"page":"2252-2262","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["<scp>3D<\/scp> Breast Cancer Segmentation in <scp>DCE\u2010MRI<\/scp> Using Deep Learning With Weak Annotation"],"prefix":"10.1002","volume":"59","author":[{"given":"Ga Eun","family":"Park","sequence":"first","affiliation":[{"name":"Department of Radiology, Seoul St. Mary's Hospital, College of Medicine The Catholic University of Korea  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4478-9720","authenticated-orcid":false,"given":"Sung Hun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Radiology, Seoul St. Mary's Hospital, College of Medicine The Catholic University of Korea  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2149-0072","authenticated-orcid":false,"given":"Yoonho","family":"Nam","sequence":"additional","affiliation":[{"name":"Division of Biomedical Engineering Hankuk University of Foreign Studies  Yongin Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junghwa","family":"Kang","sequence":"additional","affiliation":[{"name":"Division of Biomedical Engineering Hankuk University of Foreign Studies  Yongin Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minjeong","family":"Park","sequence":"additional","affiliation":[{"name":"Division of Biomedical Engineering Hankuk University of Foreign Studies  Yongin Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bong Joo","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Seoul St. Mary's Hospital, College of Medicine The Catholic University of Korea  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019182947"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1515\/med-2021-0282"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.596364"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2021.04.010"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13849"},{"key":"e_1_2_7_7_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40644-019-0252-2"},{"key":"e_1_2_7_8_1","volume-title":"ACR BI\u2010RADS atlas, breast imaging reporting and data system","author":"D'Orsi CJ","year":"2013"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.21037\/tcr-20-3163"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01373-4"},{"key":"e_1_2_7_11_1","doi-asserted-by":"crossref","unstructured":"ReisS SeiboldC FreytagA RodnerE StiefelhagenR.Every annotation counts: Multi\u2010label deep supervision for medical image segmentation. In:IEEE\/CVF conference on computer vision and pattern recognition (CVPR); IEEE Computer Society;2021 p9527\u20139537.","DOI":"10.1109\/CVPR46437.2021.00941"},{"key":"e_1_2_7_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2021.109882"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/9962109"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3089292"},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101997"},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.210817"},{"key":"e_1_2_7_17_1","doi-asserted-by":"publisher","DOI":"10.3390\/app122110763"},{"key":"e_1_2_7_18_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0266147"},{"key":"e_1_2_7_19_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-020-00435-w"},{"key":"e_1_2_7_20_1","doi-asserted-by":"crossref","unstructured":"HatamizadehA TangY NathV et al.UNETR: Transformers for 3D medical image segmentation. In:Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision;2022 p574\u2013584.","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"e_1_2_7_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1987.4767941"},{"key":"e_1_2_7_22_1","unstructured":"CardosoMJ LiW BrownR et al.MONAI: An open\u2010source framework for deep learning in healthcare.2022 arXiv preprint arXiv:2211.02701."},{"key":"e_1_2_7_23_1","doi-asserted-by":"crossref","unstructured":"SudreCH LiW VercauterenT OurselinS JorgeCardoso M.Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. Deep learning in medical image analysis and multimodal learning for clinical decision support. In:Third International Workshop DLMIA 2017 and 7th International Workshop;2017 p240\u2013248.","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"e_1_2_7_24_1","unstructured":"LoshchilovI HutterF.Decoupled weight decay regularization. International conference on learning representations (ICLR). New Orleans;2019.https:\/\/arxiv.org\/abs\/1711.05101"},{"key":"e_1_2_7_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.27429"},{"key":"e_1_2_7_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-022-09113-7"},{"key":"e_1_2_7_27_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.984626"},{"key":"e_1_2_7_28_1","doi-asserted-by":"crossref","unstructured":"PiantadosiG MarroneS GalliA SansoneM SansoneC.DCE\u2010MRI breast lesions segmentation with a 3TP U\u2010net deep convolutional neural network. In:IEEE 32nd International Symposium on Computer\u2010Based Medical Systems (CBMS);2019 p628\u2013633.","DOI":"10.1109\/CBMS.2019.00130"},{"key":"e_1_2_7_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2865671"},{"key":"e_1_2_7_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.105093"},{"key":"e_1_2_7_31_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27758"},{"key":"e_1_2_7_32_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.200231"},{"key":"e_1_2_7_33_1","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/2413706"},{"key":"e_1_2_7_34_1","doi-asserted-by":"publisher","DOI":"10.3390\/computers8030052"},{"key":"e_1_2_7_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-019-06020-2"}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.28960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T16:30:51Z","timestamp":1715272251000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.28960"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,19]]},"references-count":34,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["10.1002\/jmri.28960"],"URL":"https:\/\/doi.org\/10.1002\/jmri.28960","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,19]]},"assertion":[{"value":"2023-06-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-08-03","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-08-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}