{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T22:38:58Z","timestamp":1787697538837,"version":"build-2784847793"},"reference-count":33,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2023,10,19]],"date-time":"2023-10-19T00:00:00Z","timestamp":1697673600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010738","name":"Stavanger Universitetssjukehus","doi-asserted-by":"publisher","award":["F12604F"],"award-info":[{"award-number":["F12604F"]}],"id":[{"id":"10.13039\/501100010738","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Magnetic Resonance Imaging"],"published-print":{"date-parts":[[2024,8]]},"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Aging is the most important risk factor for prostate cancer (PC). Imaging techniques can be useful to measure age\u2010related changes associated with the transition to diverse pathological states. However, biomarkers of aging from prostate magnetic resonance imaging (MRI) remain to be explored.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>To develop an aging biomarker from prostate MRI and to examine its relationship with clinically significant PC (csPC, Gleason score \u22657) risk occurrence.<\/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>Four hundred and sixty\u2010eight (65.97\u2009\u00b1\u20096.91\u2009years) biopsied males, contributing 7243 prostate MRI slices. A deep learning (DL) model was trained on 3223 MRI slices from 81 low\u2010grade PC (Gleason score \u22646) and 131 negative patients, defined as non\u2010csPC. The model was tested on 90 negative, 52 low\u2010grade (142 non\u2010csPC), and 114 csPC patients.<\/jats:p><\/jats:sec><jats:sec><jats:title>Field Strength\/Sequence<\/jats:title><jats:p>3\u2010T, axial T2\u2010weighted spin sequence.<\/jats:p><\/jats:sec><jats:sec><jats:title>Assessment<\/jats:title><jats:p>Chronological age was defined as the age of the participant at the time of the visit. Prostate\u2010specific antigen (PSA), prostate volume, Gleason, and Prostate Imaging\u2010Reporting and Data System (PI\u2010RADS) scores were also obtained. Manually annotated prostate masks were used to crop the MRI slices, and a DL model was trained with those from non\u2010csPC patients to estimate the age of the patients. Following, we obtained the prostate age gap (PAG) on previously unseen csPC and non\u2010csPC cropped MRI exams. PAG was defined as the estimated model age minus the patient's age. Finally, the relationship between PAG and csPC risk occurrence was assessed through an adjusted multivariate logistic regression by PSA levels, age, prostate volume, and PI\u2010RADS\u2009\u2265\u20093 score.<\/jats:p><\/jats:sec><jats:sec><jats:title>Statistical Tests<\/jats:title><jats:p><jats:italic>T<\/jats:italic>\u2010test, Mann\u2013Whitney <jats:italic>U<\/jats:italic> test, permutation test, receiver operating characteristics (ROC), area under the curve (AUC), and odds ratio (OR). A <jats:italic>P<\/jats:italic> value &lt;0.05 was considered statistically significant.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>After adjusting, there was a significant difference in the odds of csPC (OR\u2009=\u20093.78, 95% confidence interval [CI]: 2.32\u20136.16). Further, PAG showed a significantly larger bootstrapped AUC to discriminate between csPC and non\u2010csPC than that of adjusted PI\u2010RADS\u2009\u2265\u20093 (AUC\u2009=\u20090.981, 95% CI: 0.975\u20130.987).<\/jats:p><\/jats:sec><jats:sec><jats:title>Data Conclusion<\/jats:title><jats:p>PAG may be associated with the risk of csPC and could outperform other PC risk factors.<\/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 3<\/jats:p><\/jats:sec>","DOI":"10.1002\/jmri.29090","type":"journal-article","created":{"date-parts":[[2023,10,19]],"date-time":"2023-10-19T13:39:42Z","timestamp":1697722782000},"page":"458-468","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Prostate Age Gap: An <scp>MRI<\/scp> Surrogate Marker of Aging for Prostate Cancer Detection"],"prefix":"10.1002","volume":"60","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7544-0797","authenticated-orcid":false,"given":"Alvaro","family":"Fernandez\u2010Quilez","sequence":"first","affiliation":[{"name":"Department of Computer Science and Electrical Engineering University of Stavanger  Stavanger Norway"},{"name":"SMIL, Department of Radiology Stavanger University Hospital  Stavanger Norway"},{"name":"Department of Medical Epidemiology and Biostatistics Karolinska Institutet  Stockholm Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Nordstr\u00f6m","sequence":"additional","affiliation":[{"name":"Department of Medical Epidemiology and Biostatistics Karolinska Institutet  Stockholm Sweden"},{"name":"Department of Clinical Sciences Danderyd Hospital, Karolinska Institutet  Stockholm Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fredrik","family":"J\u00e4derling","sequence":"additional","affiliation":[{"name":"Department of Radiology Capio Saint G\u00f6ran Hospital  Stockholm Sweden"},{"name":"Department of Molecular Medicine and Surgery Karolinska Institutet  Stockholm Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Svein Reidar","family":"Kjosavik","sequence":"additional","affiliation":[{"name":"General Practice and Care Coordination Research Group Stavanger University Hospital  Stavanger Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Eklund","sequence":"additional","affiliation":[{"name":"Department of Medical Epidemiology and Biostatistics Karolinska Institutet  Stockholm Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,10,19]]},"reference":[{"key":"e_1_2_6_2_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1113135"},{"key":"e_1_2_6_3_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-021-02230-y"},{"key":"e_1_2_6_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(15)00361-7"},{"key":"e_1_2_6_5_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMe0901166"},{"key":"e_1_2_6_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2013.12.062"},{"key":"e_1_2_6_7_1","article-title":"Prostate MRI, with or without MRI\u2010targeted biopsy, and systematic biopsy for detecting prostate cancer","volume":"4","author":"Drost FJ","year":"2019","journal-title":"Cochrane Database Syst Rev"},{"key":"e_1_2_6_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(16)32401-1"},{"key":"e_1_2_6_9_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1801993"},{"key":"e_1_2_6_10_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2100852"},{"key":"e_1_2_6_11_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.223128"},{"key":"e_1_2_6_12_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2016152542"},{"key":"e_1_2_6_13_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-015-0344-1"},{"key":"e_1_2_6_14_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2017.5667"},{"key":"e_1_2_6_15_1","doi-asserted-by":"publisher","DOI":"10.14740\/wjon1191"},{"key":"e_1_2_6_16_1","doi-asserted-by":"publisher","DOI":"10.1186\/1741-7015-12-26"},{"issue":"2","key":"e_1_2_6_17_1","article-title":"Biomarkers of ageing: Current state\u2010of\u2010art, challenges, and opportunities. MedComm\u2013future","volume":"2","author":"Chen R","year":"2023","journal-title":"Medicine"},{"key":"e_1_2_6_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2666-7568(23)00143-5"},{"key":"e_1_2_6_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11427-023-2305-0"},{"key":"e_1_2_6_20_1","first-page":"1","article-title":"Deep learning\u2010based age estimation from chest CT scans","author":"Azarfar G","year":"2023","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"e_1_2_6_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2666-7568(23)00133-2"},{"key":"e_1_2_6_22_1","unstructured":"SahaA BosmaJ TwiltJ et al.Artificial Intelligence and Radiologists at Prostate Cancer Detection in MRI\u2014The PI\u2010CAI Challenge. In:Medical Imaging with Deep Learning short paper track2023Apr 28.https:\/\/doi.org\/10.5281\/zenodo.6667655"},{"key":"e_1_2_6_23_1","unstructured":"RolfsnesES ThangngatP Eftest\u00f8lT et al.Reconsidering evaluation practices in modular systems: On the propagation of errors in MRI prostate cancer detection. arXiv preprint arXiv:2309.08381.2023Sep 15."},{"key":"e_1_2_6_24_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition;2016. p 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_6_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-13163-9"},{"key":"e_1_2_6_26_1","unstructured":"LindeijerTN YtredalTM Eftest\u00f8lT et al.Leveraging multi\u2010view data without annotations for prostate MRI segmentation: A contrastive approach. arXiv preprint arXiv:2308.06477.2023Aug 12."},{"key":"e_1_2_6_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(21)00348-X"},{"key":"e_1_2_6_28_1","doi-asserted-by":"publisher","DOI":"10.1111\/bju.13465"},{"key":"e_1_2_6_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.euo.2021.09.001"},{"key":"e_1_2_6_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102155"},{"key":"e_1_2_6_31_1","doi-asserted-by":"crossref","unstructured":"Fernandez\u2010QuilezA Eftest\u00f8lT KjosavikSR GoodwinM OppedalK.Contrasting axial T2w MRI for prostate cancer triage: A self\u2010supervised learning approach. In2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI);2022Mar 28. p 1\u20135. IEEE.","DOI":"10.1109\/ISBI52829.2022.9761573"},{"key":"e_1_2_6_32_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019190938"},{"key":"e_1_2_6_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-022-00161-9"},{"key":"e_1_2_6_34_1","unstructured":"KurbatskayaA Jaramillo\u2010JimenezA Ochoa\u2010GomezJF Br\u00f8nnickK Fernandez\u2010QuilezA.Assessing gender fairness in EEG\u2010based machine learning detection of Parkinson's disease: A multi\u2010center study. arXiv preprint arXiv:2303.06376.2023Mar 11."}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.29090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T11:16:55Z","timestamp":1721992615000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.29090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,19]]},"references-count":33,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["10.1002\/jmri.29090"],"URL":"https:\/\/doi.org\/10.1002\/jmri.29090","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,19]]},"assertion":[{"value":"2023-08-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-10-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-10-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}