{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T19:52:37Z","timestamp":1789674757054,"version":"4.0.1"},"reference-count":67,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T00:00:00Z","timestamp":1678665600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P30 CA008748"],"award-info":[{"award-number":["P30 CA008748"]}],"id":[{"id":"10.13039\/100000002","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>Dose escalation radiotherapy enables increased control of prostate cancer (PCa) but requires segmentation of dominant index lesions (DIL). This motivates the development of automated methods for fast, accurate, and consistent segmentation of PCa DIL.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>To construct and validate a model for deep\u2010learning\u2010based automatic segmentation of PCa DIL defined by Gleason score (GS) \u22653+4 from MR images applied to MR\u2010guided radiation therapy. Validate generalizability of constructed models across scanner and acquisition differences.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Five deep\u2010learning networks were evaluated on apparent diffusion coefficient (ADC) MRI from 500 lesions in 365 patients arising from internal training Dataset 1 (156 lesions in 125 patients, 1.5Tesla GE MR with endorectal coil), testing using Dataset 1 (35 lesions in 26 patients), external ProstateX Dataset 2 (299 lesions in 204 patients, 3Tesla Siemens MR), and internal inter\u2010rater Dataset 3 (10 lesions in 10 patients, 3Tesla Philips MR). The five networks include: multiple resolution residually connected network (MRRN) and MRRN regularized in training with deep supervision implemented into the last convolutional block (MRRN\u2010DS), Unet, Unet++, ResUnet, and fast panoptic segmentation (FPSnet) as well as fast panoptic segmentation with smoothed labels (FPSnet\u2010SL). Models were evaluated by volumetric DIL segmentation accuracy using Dice similarity coefficient (DSC) and the balanced F1 measure of detection accuracy, as a function of lesion aggressiveness and size (Dataset 1 and 2), and accuracy with respect to two\u2010raters (on Dataset 3). Upon acceptance for publication segmentation models will be made available in an open\u2010source GitHub repository.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In general, MRRN\u2010DS more accurately segmented tumors than other methods on the testing datasets. MRRN\u2010DS significantly outperformed ResUnet in Dataset2 (DSC of 0.54\u00a0vs. 0.44, <jats:italic>p<\/jats:italic>\u00a0&lt;\u00a00.001) and the Unet++ in Dataset3 (DSC of 0.45\u00a0vs. <jats:italic>p<\/jats:italic>\u00a0=\u00a00.04). FPSnet\u2010SL was similarly accurate as MRRN\u2010DS in Dataset2 (<jats:italic>p<\/jats:italic>\u00a0=\u00a00.30), but MRRN\u2010DS significantly outperformed FPSnet and FPSnet\u2010SL in both Dataset1 (0.60\u00a0vs. 0.51 [<jats:italic>p<\/jats:italic>\u00a0=\u00a00.01] and 0.54 [<jats:italic>p<\/jats:italic>\u00a0=\u00a00.049] respectively) and Dataset3 (0.45\u00a0vs. 0.06 [<jats:italic>p<\/jats:italic>\u00a0=\u00a00.002] and 0.24 [<jats:italic>p<\/jats:italic>\u00a0=\u00a00.004] respectively). Finally, MRRN\u2010DS produced slightly higher agreement with experienced radiologist than two radiologists in Dataset 3 (DSC of 0.45\u00a0vs. 0.41).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>MRRN\u2010DS was generalizable to different MR testing datasets acquired using different scanners. It produced slightly higher agreement with an experienced radiologist than that between two radiologists. Finally, MRRN\u2010DS more accurately segmented aggressive lesions, which are generally candidates for radiative dose ablation.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.16320","type":"journal-article","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T05:55:37Z","timestamp":1677650137000},"page":"4854-4870","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Deep learning\u2010based dominant index lesion segmentation for MR\u2010guided radiation therapy of prostate cancer"],"prefix":"10.1002","volume":"50","author":[{"given":"Josiah","family":"Simeth","sequence":"first","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jue","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anton","family":"Nosov","sequence":"additional","affiliation":[{"name":"Department of Radiology Memorial Sloan Kettering Cancer Center  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Wibmer","sequence":"additional","affiliation":[{"name":"Department of Radiology Memorial Sloan Kettering Cancer Center  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Zelefsky","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Memorial Sloan Kettering Cancer Center  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neelam","family":"Tyagi","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harini","family":"Veeraraghavan","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Memorial Sloan Kettering Cancer Center  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,3,13]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcl.2017.10.012"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2011.11.030"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2007.03.065"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00428\u2010014\u20101557\u2010y"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.adro.2020.01.005"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1186\/1748\u2010717X\u20108\u201084"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2004.04.017"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1097\/COC.0b013e318209cd8f"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1186\/1745\u20106215\u201012\u2010255"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.4172\/2167\u20107964.1000170"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0360\u20103016(98)00089\u20103"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0360\u20103016(98)00091\u20101"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2016152542"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.5301\/tj.5000547"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278\u2010018\u20100160\u20101"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019190938"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102155"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14517"},{"key":"e_1_2_8_20_1","unstructured":"JungW ParkS JungKH HwangSI Prostate cancer segmentation using manifold mixup U\u2010Net. In 2019. Accessed November 8 2021.https:\/\/openreview.net\/forum?id=r1l80Lw45E"},{"key":"e_1_2_8_21_1","unstructured":"KohlS BonekampD SchlemmerHP et\u00a0al.Adversarial networks for the detection of aggressive prostate cancer. In:Conference Paper at MICCAI 2017 ArXiv:1702.08014 [Cs]. Accessed November 8 2021.http:\/\/arxiv.org\/abs\/1702.08014"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ac3c13"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2502220"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2009.2012888"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3359459"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2048612"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2019.01313"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2496296"},{"key":"e_1_2_8_29_1","doi-asserted-by":"crossref","unstructured":"YuL YangX ChenH QinJ HengPA Volumetric ConvNets with mixed residual connections for automated prostate segmentation from 3D MR images. In:Thirty\u2010First AAAI Conference on Artificial Intelligence.2017. Accessed February 11 2022.https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI17\/paper\/view\/14719","DOI":"10.1609\/aaai.v31i1.10510"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40763-5_32"},{"key":"e_1_2_8_31_1","unstructured":"VincentG GuillardG BowesM Fully Automatic Segmentation of the Prostate using Active Appearance Models. Published 2012. Accessed February 11 2022.https:\/\/www.semanticscholar.org\/paper\/Fully\u2010Automatic\u2010Segmentation\u2010of\u2010the\u2010Prostate\u2010using\u2010Vincent\u2010Guillard\/7f8fa4c107a0590149ec8b89dae64e8a7fa5b3d4"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.2842076"},{"key":"e_1_2_8_33_1","doi-asserted-by":"crossref","unstructured":"ZhuQ DuB TurkbeyB ChoykePL YanP Deeply\u2010supervised CNN for prostate segmentation. In:2017 International Joint Conference on Neural Networks (IJCNN). ;2017:178\u2010184.https:\/\/doi.org\/10.1109\/IJCNN.2017.7965852","DOI":"10.1109\/IJCNN.2017.7965852"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2013.2289306"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2508280"},{"key":"e_1_2_8_36_1","doi-asserted-by":"crossref","unstructured":"MilletariF NavabN AhmadiSA.V\u2010Net: fully convolutional neural networks for volumetric medical image segmentation.2016 Fourth International Conference on 3D Vision (3DV).2016:565\u2010571.https:\/\/doi.org\/10.1109\/3DV.2016.79","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15687"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102347"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2857800"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1505935112"},{"key":"e_1_2_8_41_1","volume-title":"StatPearls.","author":"Munjal A","year":"2021"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1046\/j.1464\u2010410x.2002.02669.x"},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.3978\/j.issn.2223\u20104292.2013.08.06"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.5.4.044501"},{"key":"e_1_2_8_45_1","unstructured":"LitjensG DebatsO BarentszJ KarssemeijerN HuismanH SPIE\u2010AAPM PROSTATEx Challenge Data. Published online 2017.https:\/\/doi.org\/10.7937\/K9TCIA.2017.MURS5CL"},{"key":"e_1_2_8_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2021.109647"},{"key":"e_1_2_8_47_1","doi-asserted-by":"crossref","unstructured":"ZhouZ Rahman SiddiqueeMM TajbakhshN LiangJ UNet++: a nested U\u2010net architecture for medical image segmentation. In:StoyanovD TaylorZ CarneiroG et\u00a0al. eds.Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Lecture Notes in Computer Science.Springer International Publishing;2018:3\u201011.https:\/\/doi.org\/10.1007\/978\u20103\u2010030\u201000889\u20105_1","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"e_1_2_8_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2802944"},{"key":"e_1_2_8_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20103\u2010030\u201032226\u20107_25"},{"key":"e_1_2_8_50_1","unstructured":"WangL LeeCY TuZ LazebnikS Training deeper convolutional networks with deep supervision. ArXiv150502496 Cs. Published online May 11 2015. Accessed February 11 2022.http:\/\/arxiv.org\/abs\/1505.02496"},{"key":"e_1_2_8_51_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15765"},{"key":"e_1_2_8_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2969919"},{"key":"e_1_2_8_53_1","doi-asserted-by":"crossref","unstructured":"DengJ DongW SocherR LiLJ LiK Fei\u2010FeiL ImageNet: a large\u2010scale hierarchical image database. In:2009 IEEE Conference on Computer Vision and Pattern Recognition.2009:248\u2010255.https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_8_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"e_1_2_8_55_1","article-title":"PyTorch: an imperative style, high\u2010performance deep learning library","volume":"32","author":"Paszke A","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_8_56_1","unstructured":"KingmaDP BaJ Adam: a method for stochastic optimization. In:Proceedings of the 3rd International Conference on Learning Representations.2015."},{"key":"e_1_2_8_57_1","doi-asserted-by":"crossref","unstructured":"SzegedyC VanhouckeV IoffeS ShlensJ WojnaZ Rethinking the inception architecture for computer vision. In:2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE;2016:2818\u20102826.https:\/\/doi.org\/10.1109\/CVPR.2016.308","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_2_8_58_1","doi-asserted-by":"crossref","unstructured":"OuyangX XueZ ZhanY et\u00a0al.Weakly supervised segmentation framework with uncertainty: a study on pneumothorax segmentation in chest x\u2010ray. In:Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI2019: 22nd International Conference Shenzhen China October 13\u201317 2019 Proceedings Part VI.Springer\u2010Verlag;2019:613\u2010621.https:\/\/doi.org\/10.1007\/978\u20103\u2010030\u201032226\u20107_68","DOI":"10.1007\/978-3-030-32226-7_68"},{"key":"e_1_2_8_59_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586\u2010019\u20101799\u20106"},{"key":"e_1_2_8_60_1","unstructured":"KingBM Rosopa PJ Minium EW.Statistical Reasoning in the Behavioral Sciences (Wiley 2010)."},{"key":"e_1_2_8_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2015.04.012"},{"key":"e_1_2_8_62_1","doi-asserted-by":"publisher","DOI":"10.1186\/1748\u2010717X\u20108\u2010183"},{"key":"e_1_2_8_63_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014\u2010022\u201002035\u20100"},{"key":"e_1_2_8_64_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.7248"},{"key":"e_1_2_8_65_1","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.24558"},{"key":"e_1_2_8_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2008.04.038"},{"key":"e_1_2_8_67_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4871620"},{"key":"e_1_2_8_68_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0222916"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16320","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.16320","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T14:53:34Z","timestamp":1755874414000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16320"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,13]]},"references-count":67,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["10.1002\/mp.16320"],"URL":"https:\/\/doi.org\/10.1002\/mp.16320","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,13]]},"assertion":[{"value":"2022-09-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-01-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-03-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}