{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T22:21:23Z","timestamp":1777414883370,"version":"3.51.4"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T00:00:00Z","timestamp":1750809600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T00:00:00Z","timestamp":1750809600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004721","name":"The University of Tokyo","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004721","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging. Inform. med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Deep-learning models for prostate cancer detection typically require large datasets, limiting clinical applicability across institutions due to domain shift issues. This study aimed to develop a few-shot learning deep-learning model for prostate cancer detection on multiparametric MRI that requires minimal training data and to compare its diagnostic performance with experienced radiologists. In this retrospective study, we used 99 cases (80 positive, 19 negative) of biopsy-confirmed prostate cancer (2017\u20132022), with 20 cases for training, 5 for validation, and 74 for testing. A 2D transformer model was trained on T2-weighted, diffusion-weighted, and apparent diffusion coefficient map images. Model predictions were compared with two radiologists using Matthews correlation coefficient (MCC) and F1 score, with 95% confidence intervals (CIs) calculated via bootstrap method. The model achieved an MCC of 0.297 (95% CI: 0.095\u20130.474) and F1 score of 0.707 (95% CI: 0.598\u20130.847). Radiologist 1 had an MCC of 0.276 (95% CI: 0.054\u20130.484) and F1 score of 0.741; Radiologist 2 had an MCC of 0.504 (95% CI: 0.289\u20130.703) and F1 score of 0.871, showing that the model performance was comparable to Radiologist 1. External validation on the Prostate158 dataset revealed that ImageNet pretraining substantially improved model performance, increasing study-level ROC-AUC from 0.464 to 0.636 and study-level PR-AUC from 0.637 to 0.773 across all architectures. Our findings demonstrate that few-shot deep-learning models can achieve clinically relevant performance when using pretrained transformer architectures, offering a promising approach to address domain shift challenges across institutions.<\/jats:p>","DOI":"10.1007\/s10278-025-01581-9","type":"journal-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T12:02:16Z","timestamp":1750852936000},"page":"1619-1631","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Few-Shot Learning for Prostate Cancer Detection on MRI: Comparative Analysis with Radiologists\u2019 Performance"],"prefix":"10.1007","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7688-3075","authenticated-orcid":false,"given":"Yosuke","family":"Yamagishi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasutaka","family":"Baba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Suzuki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshitaka","family":"Okada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kent","family":"Kanao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masafumi","family":"Oyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,25]]},"reference":[{"key":"1581_CR1","doi-asserted-by":"publisher","unstructured":"Naik N, Tokas T, Shetty DK, et al. Role of Deep Learning in Prostate Cancer Management: Past, Present and Future Based on a Comprehensive Literature Review. J Clin Med. 2022;11(13):3575. https:\/\/doi.org\/10.3390\/jcm11133575.","DOI":"10.3390\/jcm11133575"},{"key":"1581_CR2","doi-asserted-by":"publisher","unstructured":"Yan Y, Shao L, Liu Z, et al. Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study. Cancers (Basel). 2021;13(12):3098. https:\/\/doi.org\/10.3390\/cancers13123098.","DOI":"10.3390\/cancers13123098"},{"key":"1581_CR3","doi-asserted-by":"publisher","unstructured":"Khosravi P, Lysandrou M, Eljalby M, et al. A Deep Learning Approach to Diagnostic Classification of Prostate Cancer Using Pathology\u2013Radiology Fusion. J Magn Reson Imaging. 2021;54(2):462\u2013471. https:\/\/doi.org\/10.1002\/jmri.27599.","DOI":"10.1002\/jmri.27599"},{"key":"1581_CR4","doi-asserted-by":"publisher","unstructured":"Shiradkar R, Panda A, Leo P, et al. T1, T2 MR Fingerprinting Measurements of Prostate Cancer and Prostatitis Correlate with Deep Learning Derived Estimates of Epithelium, Lumen and Stromal Composition on Corresponding Whole Mount Histopathology. Eur Radiol. 2021;31(3):1336\u20131346. https:\/\/doi.org\/10.1007\/s00330-020-07214-9.","DOI":"10.1007\/s00330-020-07214-9"},{"key":"1581_CR5","doi-asserted-by":"publisher","unstructured":"Schelb P, Wang X, Radtke JP, et al. Simulated clinical deployment of fully automatic deep learning for clinical prostate MRI assessment. Eur Radiol. 2021;31(1):302\u2013313. https:\/\/doi.org\/10.1007\/s00330-020-07086-z.","DOI":"10.1007\/s00330-020-07086-z"},{"key":"1581_CR6","doi-asserted-by":"publisher","unstructured":"Hiremath A, Shiradkar R, Merisaari H, et al. Test-retest repeatability of a deep learning architecture in detecting and segmenting clinically significant prostate cancer on apparent diffusion coefficient (ADC) maps. Eur Radiol. 2021;31(1):379\u2013391. https:\/\/doi.org\/10.1007\/s00330-020-07065-4.","DOI":"10.1007\/s00330-020-07065-4"},{"key":"1581_CR7","doi-asserted-by":"publisher","unstructured":"Hosseinzadeh M, Saha A, Brand P, Slootweg I, de Rooij M, Huisman H. Deep learning-assisted prostate cancer detection on bi-parametric MRI: minimum training data size requirements and effect of prior knowledge. Eur Radiol. 2022;32(4):2224\u20132234. https:\/\/doi.org\/10.1007\/s00330-021-08320-y.","DOI":"10.1007\/s00330-021-08320-y"},{"key":"1581_CR8","doi-asserted-by":"publisher","unstructured":"Torralba A, Efros AA. Unbiased look at dataset bias. CVPR 2011. 2011. p. 1521\u20131528. https:\/\/doi.org\/10.1109\/CVPR.2011.5995347.","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"1581_CR9","doi-asserted-by":"publisher","unstructured":"Yoo S, Gujrathi I, Haider MA, Khalvati F. Prostate Cancer Detection using Deep Convolutional Neural Networks. Sci Rep. Nature Publishing Group; 2019;9(1):19518. https:\/\/doi.org\/10.1038\/s41598-019-55972-4.","DOI":"10.1038\/s41598-019-55972-4"},{"key":"1581_CR10","doi-asserted-by":"publisher","unstructured":"Tejani AS, Klontzas ME, Gatti AA, et al. Checklist for Artificial Intelligence in Medical Imaging (CLAIM): 2024 Update. Radiology: Artificial Intelligence. Radiological Society of North America; 2024;6(4):e240300. https:\/\/doi.org\/10.1148\/ryai.240300.","DOI":"10.1148\/ryai.240300"},{"key":"1581_CR11","doi-asserted-by":"publisher","unstructured":"Harris CR, Millman KJ, Walt SJ van der, et al. Array programming with NumPy. Nature. Springer Science and Business Media LLC; 2020;585(7825):357\u2013362. https:\/\/doi.org\/10.1038\/s41586-020-2649-2.","DOI":"10.1038\/s41586-020-2649-2"},{"key":"1581_CR12","doi-asserted-by":"publisher","unstructured":"Singh SP, Wang L, Gupta S, Goli H, Padmanabhan P, Guly\u00e1s B. 3D Deep Learning on Medical Images: A Review. Sensors. Multidisciplinary Digital Publishing Institute; 2020;20(18):5097. https:\/\/doi.org\/10.3390\/s20185097.","DOI":"10.3390\/s20185097"},{"key":"1581_CR13","doi-asserted-by":"publisher","unstructured":"Liu Z, Lin Y, Cao Y, et al. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. arXiv; 2021. https:\/\/doi.org\/10.48550\/arXiv.2103.14030.","DOI":"10.48550\/arXiv.2103.14030"},{"key":"1581_CR14","doi-asserted-by":"publisher","unstructured":"Ridnik T, Ben-Baruch E, Noy A, Zelnik-Manor L. ImageNet-21K Pretraining for the Masses. arXiv; 2021. https:\/\/doi.org\/10.48550\/arXiv.2104.10972.","DOI":"10.48550\/arXiv.2104.10972"},{"key":"1581_CR15","doi-asserted-by":"publisher","unstructured":"Russakovsky O, Deng J, Su H, et al. ImageNet Large Scale Visual Recognition Challenge. arXiv; 2015. https:\/\/doi.org\/10.48550\/arXiv.1409.0575.","DOI":"10.48550\/arXiv.1409.0575"},{"key":"1581_CR16","doi-asserted-by":"publisher","unstructured":"Wightman R. PyTorch Image Models. GitHub repository. GitHub; 2019. https:\/\/doi.org\/10.5281\/zenodo.4414861.","DOI":"10.5281\/zenodo.4414861"},{"key":"1581_CR17","doi-asserted-by":"publisher","unstructured":"Loshchilov I, Hutter F. Decoupled Weight Decay Regularization. arXiv; 2019. https:\/\/doi.org\/10.48550\/arXiv.1711.05101.","DOI":"10.48550\/arXiv.1711.05101"},{"key":"1581_CR18","doi-asserted-by":"publisher","unstructured":"Buslaev A, Iglovikov VI, Khvedchenya E, Parinov A, Druzhinin M, Kalinin AA. Albumentations: Fast and Flexible Image Augmentations. Information. 2020;11(2). https:\/\/doi.org\/10.3390\/info11020125.","DOI":"10.3390\/info11020125"},{"key":"1581_CR19","doi-asserted-by":"publisher","unstructured":"Paszke A, Gross S, Massa F, et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library. arXiv; 2019. https:\/\/doi.org\/10.48550\/arXiv.1912.01703.","DOI":"10.48550\/arXiv.1912.01703"},{"key":"1581_CR20","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research. 2011;12:2825\u20132830."},{"key":"1581_CR21","doi-asserted-by":"publisher","unstructured":"Tiu E, Talius E, Patel P, Langlotz CP, Ng AY, Rajpurkar P. Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning. Nat Biomed Eng. Nature Publishing Group; 2022;6(12):1399\u20131406. https:\/\/doi.org\/10.1038\/s41551-022-00936-9.","DOI":"10.1038\/s41551-022-00936-9"},{"key":"1581_CR22","doi-asserted-by":"publisher","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. Int J Comput Vis. 2020;128(2):336\u2013359. https:\/\/doi.org\/10.1007\/s11263-019-01228-7.","DOI":"10.1007\/s11263-019-01228-7"},{"key":"1581_CR23","doi-asserted-by":"publisher","unstructured":"Adams LC, Makowski MR, Engel G, et al. Prostate158 - An expert-annotated 3T MRI dataset and algorithm for prostate cancer detection. Computers in Biology and Medicine. 2022;148:105817. https:\/\/doi.org\/10.1016\/j.compbiomed.2022.105817.","DOI":"10.1016\/j.compbiomed.2022.105817"},{"key":"1581_CR24","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. 2016. p. 770\u2013778. https:\/\/openaccess.thecvf.com\/content_cvpr_2016\/html\/He_Deep_Residual_Learning_CVPR_2016_paper.html. Accessed May 20, 2025.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1581_CR25","unstructured":"Wightman R, Touvron H, Jegou H. ResNet strikes back: An improved training procedure in timm. 2021. https:\/\/openreview.net\/forum?id=NG6MJnVl6M5. Accessed May 20, 2025."},{"key":"1581_CR26","unstructured":"Tan M, Le Q. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning. PMLR; 2019. p. 6105\u20136114. https:\/\/proceedings.mlr.press\/v97\/tan19a.html. Accessed May 20, 2025."},{"key":"1581_CR27","unstructured":"Tan M, Le Q. EfficientNetV2: Smaller Models and Faster Training. Proceedings of the 38th International Conference on Machine Learning. PMLR; 2021. p. 10096\u201310106. https:\/\/proceedings.mlr.press\/v139\/tan21a.html. Accessed May 20, 2025."},{"key":"1581_CR28","doi-asserted-by":"crossref","unstructured":"Liu Z, Mao H, Wu C-Y, Feichtenhofer C, Darrell T, Xie S. A ConvNet for the 2020s. 2022. p. 11976\u201311986. https:\/\/openaccess.thecvf.com\/content\/CVPR2022\/html\/Liu_A_ConvNet_for_the_2020s_CVPR_2022_paper.html. Accessed May 20, 2025.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"1581_CR29","doi-asserted-by":"crossref","unstructured":"Woo S, Debnath S, Hu R, et al. ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders. 2023. p. 16133\u201316142. https:\/\/openaccess.thecvf.com\/content\/CVPR2023\/html\/Woo_ConvNeXt_V2_Co-Designing_and_Scaling_ConvNets_With_Masked_Autoencoders_CVPR_2023_paper.html. Accessed May 20, 2025.","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"1581_CR30","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, et al. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. 2020. https:\/\/openreview.net\/forum?id=YicbFdNTTy. Accessed May 20, 2025."},{"key":"1581_CR31","doi-asserted-by":"publisher","unstructured":"Touvron H, Cord M, J\u00e9gou H. DeiT III: Revenge of the ViT. Computer Vision \u2013 ECCV 2022. Springer, Cham; 2022. p. 516\u2013533. https:\/\/doi.org\/10.1007\/978-3-031-20053-3_30.","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"1581_CR32","unstructured":"MaxViT: Multi-axis Vision Transformer | SpringerLink. https:\/\/link-springer-com.utokyo.idm.oclc.org\/chapter\/10.1007\/978-3-031-20053-3_27. Accessed May 20, 2025."},{"key":"1581_CR33","doi-asserted-by":"publisher","unstructured":"Yu W, Si C, Zhou P, et al. MetaFormer Baselines for Vision. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(2):896\u2013912. https:\/\/doi.org\/10.1109\/TPAMI.2023.3329173.","DOI":"10.1109\/TPAMI.2023.3329173"},{"key":"1581_CR34","unstructured":"Gu A, Dao T. Mamba: Linear-Time Sequence Modeling with Selective State Spaces. 2024. https:\/\/openreview.net\/forum?id=tEYskw1VY2#discussion. Accessed May 20, 2025."},{"key":"1581_CR35","doi-asserted-by":"publisher","unstructured":"Hatamizadeh A, Kautz J. MambaVision: A Hybrid Mamba-Transformer Vision Backbone. arXiv; 2025. https:\/\/doi.org\/10.48550\/arXiv.2407.08083.","DOI":"10.48550\/arXiv.2407.08083"},{"key":"1581_CR36","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Dollar P. Focal Loss for Dense Object Detection. 2017. p. 2980\u20132988. https:\/\/openaccess.thecvf.com\/content_iccv_2017\/html\/Lin_Focal_Loss_for_ICCV_2017_paper.html. Accessed May 20, 2025.","DOI":"10.1109\/ICCV.2017.324"},{"key":"1581_CR37","doi-asserted-by":"publisher","unstructured":"Aldoj N, Lukas S, Dewey M, Penzkofer T. Semi-automatic classification of prostate cancer on multi-parametric MR imaging using a multi-channel 3D convolutional neural network. Eur Radiol. 2020;30(2):1243\u20131253. https:\/\/doi.org\/10.1007\/s00330-019-06417-z.","DOI":"10.1007\/s00330-019-06417-z"},{"key":"1581_CR38","doi-asserted-by":"publisher","unstructured":"Chen Q, Hu S, Long P, Lu F, Shi Y, Li Y. A Transfer Learning Approach for Malignant Prostate Lesion Detection on Multiparametric MRI. Technol Cancer Res Treat. 2019;18:1533033819858363. https:\/\/doi.org\/10.1177\/1533033819858363.","DOI":"10.1177\/1533033819858363"},{"key":"1581_CR39","doi-asserted-by":"publisher","unstructured":"Armato SG, Huisman H, Drukker K, et al. PROSTATEx Challenges for computerized classification of prostate lesions from multiparametric magnetic resonance images. J Med Imaging (Bellingham). 2018;5(4):044501. https:\/\/doi.org\/10.1117\/1.JMI.5.4.044501.","DOI":"10.1117\/1.JMI.5.4.044501"},{"key":"1581_CR40","doi-asserted-by":"publisher","unstructured":"Zhang S, Xu Y, Usuyama N, et al. BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. arXiv; 2024. https:\/\/doi.org\/10.48550\/arXiv.2303.00915.","DOI":"10.48550\/arXiv.2303.00915"},{"key":"1581_CR41","doi-asserted-by":"publisher","unstructured":"Hamamci IE, Er S, Almas F, et al. A foundation model utilizing chest CT volumes and radiology reports for supervised-level zero-shot detection of abnormalities. arXiv; 2024. https:\/\/doi.org\/10.48550\/arXiv.2403.17834.","DOI":"10.48550\/arXiv.2403.17834"},{"key":"1581_CR42","doi-asserted-by":"publisher","unstructured":"D\u2019Antonoli TA, Berger LK, Indrakanti AK, et al. TotalSegmentator MRI: Sequence-Independent Segmentation of 59 Anatomical Structures in MR images. arXiv; 2024. https:\/\/doi.org\/10.48550\/arXiv.2405.19492.","DOI":"10.48550\/arXiv.2405.19492"},{"key":"1581_CR43","doi-asserted-by":"publisher","unstructured":"Dhinagar NJ, Santhalingam V, Lawrence KE, Laltoo E, Thompson PM. Few-Shot Classification of Autism Spectrum Disorder using Site-Agnostic Meta-Learning and Brain MRI. arXiv; 2023. https:\/\/doi.org\/10.48550\/arXiv.2303.08224.","DOI":"10.48550\/arXiv.2303.08224"},{"key":"1581_CR44","doi-asserted-by":"publisher","unstructured":"Di Martino A, Yan C-G, Li Q, et al. The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Mol Psychiatry. Nature Publishing Group; 2014;19(6):659\u2013667. https:\/\/doi.org\/10.1038\/mp.2013.78.","DOI":"10.1038\/mp.2013.78"}],"container-title":["Journal of Imaging Informatics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-025-01581-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-025-01581-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-025-01581-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T16:23:52Z","timestamp":1776875032000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10278-025-01581-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,25]]},"references-count":44,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["1581"],"URL":"https:\/\/doi.org\/10.1007\/s10278-025-01581-9","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2025.01.19.25320503","asserted-by":"object"}]},"ISSN":["2948-2933"],"issn-type":[{"value":"2948-2933","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,25]]},"assertion":[{"value":"7 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This retrospective study was conducted at a single institution and approved by the Institutional Review Board of Saitama Medical University International Medical Center.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}