{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:36:31Z","timestamp":1767339391300,"version":"build-2065373602"},"reference-count":43,"publisher":"Institution of Engineering and Technology (IET)","issue":"3","license":[{"start":{"date-parts":[[2024,3,24]],"date-time":"2024-03-24T00:00:00Z","timestamp":1711238400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62303275"],"award-info":[{"award-number":["62303275"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020194","name":"Wellcome \/ EPSRC Centre for Interventional and Surgical Sciences","doi-asserted-by":"publisher","award":["203145Z\/16\/Z"],"award-info":[{"award-number":["203145Z\/16\/Z"]}],"id":[{"id":"10.13039\/501100020194","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["CAAI Trans on Intel Tech"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Automated prostate cancer detection in magnetic resonance imaging (MRI) scans is of significant importance for cancer patient management. Most existing computer\u2010aided diagnosis systems adopt segmentation methods while object detection approaches recently show promising results. The authors have (1) carefully compared performances of most\u2010developed segmentation and object detection methods in localising prostate imaging reporting and data system (PIRADS)\u2010labelled prostate lesions on MRI scans; (2) proposed an additional customised set of lesion\u2010level localisation sensitivity and precision; (3) proposed efficient ways to ensemble the segmentation and object detection methods for improved performances. The ground\u2010truth (GT) perspective lesion\u2010level sensitivity and prediction\u2010perspective lesion\u2010level precision are reported, to quantify the ratios of true positive voxels being detected by algorithms over the number of voxels in the GT labelled regions and predicted regions. The two networks are trained independently on 549 clinical patients data with PIRADS\u2010V2 as GT labels, and tested on 161 internal and 100 external MRI scans. At the lesion level, nnDetection outperforms nnUNet for detecting both PIRADS \u2265 3 and PIRADS \u2265 4 lesions in majority cases. For example, at the average false positive prediction per patient being 3, nnDetection achieves a greater Intersection\u2010of\u2010Union (IoU)\u2010based sensitivity than nnUNet for detecting PIRADS \u2265 3 lesions, being 80.78%\u00a0\u00b1\u00a01.50% versus 60.40%\u00a0\u00b1\u00a01.64% (\n                    <jats:italic>p<\/jats:italic>\n                    \u00a0&lt;\u00a00.01). At the voxel level, nnUnet is in general superior or comparable to nnDetection. The proposed ensemble methods achieve improved or comparable lesion\u2010level accuracy, in all tested clinical scenarios. For example, at 3 false positives, the lesion\u2010wise ensemble method achieves 82.24%\u00a0\u00b1\u00a01.43% sensitivity versus 80.78%\u00a0\u00b1\u00a01.50% (nnDetection) and 60.40%\u00a0\u00b1\u00a01.64% (nnUNet) for detecting PIRADS \u2265 3 lesions. Consistent conclusions are also drawn from results on the external data set.\n                  <\/jats:p>","DOI":"10.1049\/cit2.12318","type":"journal-article","created":{"date-parts":[[2024,3,24]],"date-time":"2024-03-24T23:29:50Z","timestamp":1711322990000},"page":"689-702","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Segmentation versus detection: Development and evaluation of deep learning models for prostate imaging reporting and data system lesions localisation on Bi\u2010parametric prostate magnetic resonance imaging"],"prefix":"10.1049","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8903-1561","authenticated-orcid":false,"given":"Zhe","family":"Min","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering Shandong University  Jinan China"},{"name":"Centre for Medical Image Computing and Wellcome\/EPSRC Centre for Interventional &amp; Surgical Sciences University College London  London UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fernando J.","family":"Bianco","sequence":"additional","affiliation":[{"name":"Urological Research Network  Miami Lakes Florida USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianye","family":"Yang","sequence":"additional","affiliation":[{"name":"Centre for Medical Image Computing and Wellcome\/EPSRC Centre for Interventional &amp; Surgical Sciences University College London  London UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Yan","sequence":"additional","affiliation":[{"name":"Centre for Medical Image Computing and Wellcome\/EPSRC Centre for Interventional &amp; Surgical Sciences University College London  London UK"},{"name":"City University of Hong Kong  Hong Kong China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyi","family":"Shen","sequence":"additional","affiliation":[{"name":"Centre for Medical Image Computing and Wellcome\/EPSRC Centre for Interventional &amp; Surgical Sciences University College London  London UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Cohen","sequence":"additional","affiliation":[{"name":"Urological Research Network  Miami Lakes Florida USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rachael","family":"Rodell","sequence":"additional","affiliation":[{"name":"Centre for Medical Image Computing and Wellcome\/EPSRC Centre for Interventional &amp; Surgical Sciences University College London  London UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dean C.","family":"Barratt","sequence":"additional","affiliation":[{"name":"Centre for Medical Image Computing and Wellcome\/EPSRC Centre for Interventional &amp; Surgical Sciences University College London  London UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yipeng","family":"Hu","sequence":"additional","affiliation":[{"name":"Centre for Medical Image Computing and Wellcome\/EPSRC Centre for Interventional &amp; Surgical Sciences University College London  London UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2024,3,24]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/ijc.33588"},{"key":"e_1_2_12_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59719-1_58"},{"key":"e_1_2_12_4_1","article-title":"Prostattention\u2010net: a deep attention model for prostate cancer segmentation by aggressiveness in mri scans","volume":"102347","author":"Duran A.","year":"2022","journal-title":"Med. Image Anal."},{"key":"e_1_2_12_5_1","first-page":"56","volume-title":"Annual Conference on Medical Image Understanding and Analysis","author":"Min Z.","year":"2021"},{"key":"e_1_2_12_6_1","article-title":"End\u2010to\u2010end prostate cancer detection in bpmri via 3d cnns: effect of attention mechanisms, clinical\u00a0priori and decoupled false positive reduction","author":"Saha A.","year":"2021","journal-title":"arXiv preprint arXiv:2101.03244"},{"key":"e_1_2_12_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2019.10.024"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.1056\/nejmoa1801993"},{"key":"e_1_2_12_9_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2020.7589"},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0140\u20106736(16)32401\u20101"},{"key":"e_1_2_12_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2020.09.042"},{"key":"e_1_2_12_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2014.2303821"},{"key":"e_1_2_12_13_1","article-title":"Encoding clinical priori in 3d convolutional neural networks for prostate cancer detection in bpmri","author":"Saha A.","year":"2020","journal-title":"arXiv preprint arXiv:2011.00263"},{"key":"e_1_2_12_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14517"},{"key":"e_1_2_12_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59710-8_50"},{"key":"e_1_2_12_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010020\u201007065\u20104"},{"key":"e_1_2_12_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2015.08.052"},{"key":"e_1_2_12_18_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019190938"},{"key":"e_1_2_12_19_1","first-page":"193","volume-title":"Medical Imaging with Deep Learning","author":"Duran A.","year":"2020"},{"key":"e_1_2_12_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.adro.2020.01.005"},{"key":"e_1_2_12_21_1","doi-asserted-by":"crossref","unstructured":"Yan W. et\u00a0al.:The Impact of Using Voxel\u2010Level Segmentation Metrics on Evaluating Multifocal Prostate Cancer Localisation(2022).https:\/\/doi.org\/10.48550\/ARXIV.2203.16415","DOI":"10.1007\/978-3-031-17721-7_14"},{"key":"e_1_2_12_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010020\u201001008\u2010z"},{"key":"e_1_2_12_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87240-3_51"},{"key":"e_1_2_12_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_12_25_1","first-page":"424","volume-title":"International Conference on Medical Image Computing and Computer\u2010Assisted Intervention","author":"\u00c7i\u00e7ek \u00d6.","year":"2016"},{"key":"e_1_2_12_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2019.2959609"},{"key":"e_1_2_12_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_12_28_1","article-title":"Anatomical and diagnostic bayesian segmentation in prostate mri \u2212 should different clinical objectives mandate different loss functions?","author":"Saha A.","year":"2021","journal-title":"arXiv preprint arXiv:2110.12889"},{"key":"e_1_2_12_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2019.2901928"},{"key":"e_1_2_12_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI45749.2020.9098338"},{"key":"e_1_2_12_31_1","article-title":"Attention u\u2010net: learning where to look for the pancreas","author":"Oktay O.","year":"2018","journal-title":"arXiv preprint arXiv:1804.03999"},{"key":"e_1_2_12_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11726-9_21"},{"key":"e_1_2_12_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2013.12.002"},{"key":"e_1_2_12_34_1","article-title":"A large annotated medical image dataset for the development and evaluation of segmentation algorithms","author":"Simpson A.L.","year":"2019","journal-title":"arXiv preprint arXiv:1902.09063"},{"key":"e_1_2_12_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263\u2010019\u201001247\u20104"},{"key":"e_1_2_12_36_1","article-title":"J. Faster r\u2010cnn: towards real\u2010time object detection with region proposal networks","author":"Ren S.","year":"2015","journal-title":"arXiv preprint arXiv:1506.01497"},{"key":"e_1_2_12_37_1","first-page":"2961","volume-title":"Roceedings of the IEEE International Conference on Computer Vision","author":"He K.","year":"2017"},{"key":"e_1_2_12_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_2_12_39_1","first-page":"171","volume-title":"Machine Learning for Health Workshop","author":"Jaeger P.F.","year":"2020"},{"key":"e_1_2_12_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.06.015"},{"key":"e_1_2_12_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2018.08.007"},{"key":"e_1_2_12_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cct.2013.06.005"},{"key":"e_1_2_12_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.juro.2018.07.001"},{"key":"e_1_2_12_44_1","article-title":"Mutual information\u2010based us segmentation for unseen domain generalization","author":"Bi Y.","year":"2023","journal-title":"arXiv preprint arXiv:2303.12649"}],"container-title":["CAAI Transactions on Intelligence Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.12318","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T12:18:49Z","timestamp":1761653929000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cit2.12318"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,24]]},"references-count":43,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["10.1049\/cit2.12318"],"URL":"https:\/\/doi.org\/10.1049\/cit2.12318","archive":["Portico"],"relation":{},"ISSN":["2468-6557","2468-2322"],"issn-type":[{"type":"print","value":"2468-6557"},{"type":"electronic","value":"2468-2322"}],"subject":[],"published":{"date-parts":[[2024,3,24]]},"assertion":[{"value":"2023-03-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-12","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}