{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T07:35:34Z","timestamp":1779348934443,"version":"3.51.4"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004047","name":"Karolinska Institute","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004047","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Tissue detection is a crucial first step in most digital pathology applications. By applying image segmentation algorithms, all tissue is delineated and background discarded from further analyses, improving both computational efficiency and analytical results. Details of the segmentation algorithm are rarely reported, and there is a lack of studies investigating the downstream effects of a poor segmentation algorithm. Disregarding tissue detection quality could jeopardize patient safety if diagnostically relevant parts of the specimen are excluded from analysis in clinical applications. This study aims to determine whether performance of downstream tasks is sensitive to the tissue detection method, and to compare the performance of a classical and an AI-based tissue detection approach. To this end, we trained an AI model for Gleason grading of prostate cancer in whole slide images (WSIs) using two different tissue detection algorithms: thresholding (classical) and UNet++ (AI). A total of 33,823 WSIs scanned on seven digital pathology scanners were used to train the segmentation AI model. The downstream Gleason grading algorithm was trained and tested using 70,524 WSIs from 13 clinical sites scanned on 13 different scanners. On the slides where tissue could be detected by both algorithms, no significant difference in overall Gleason grading performance was observed. There was a decrease from 118 (0.43%) to 24 (0.09%) fully undetected tissue samples when switching from thresholding-based tissue detection to AI-based, suggesting this AI model may be more reliable than the classical model for avoiding total failures on slides with unusual appearance. Moreover, tissue detection dependent clinically significant variations in AI grading were observed in 3.5% of malignant slides, highlighting the role of tissue detection for optimal clinical performance of diagnostic AI.<\/jats:p>","DOI":"10.1038\/s41598-026-52148-9","type":"journal-article","created":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T04:45:26Z","timestamp":1778647526000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["The impact of tissue detection on diagnostic artificial intelligence algorithms in prostate digital pathology"],"prefix":"10.1038","volume":"16","author":[{"given":"Sol Erika","family":"Boman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nita","family":"Mulliqi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anders","family":"Blilie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyi","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kelvin","family":"Szolnoky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Einar","family":"Gudlaugsson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emiel A.M.","family":"Janssen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Svein R.","family":"Kjosavik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9","family":"Asenjo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcello","family":"Gambacorta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paolo","family":"Libretti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcin","family":"Braun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radzislaw","family":"Kordek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roman","family":"\u0141owicki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kristina","family":"Hotakainen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P\u00e4ivi","family":"V\u00e4re","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bodil Ginnerup","family":"Pedersen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karina Dalsgaard","family":"S\u00f8rensen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benedicte Parm","family":"Ulh\u00f8i","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lars","family":"Egevad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kimmo","family":"Kartasalo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,13]]},"reference":[{"key":"52148_CR1","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1146\/annurev-cancerbio-062822-010523","volume":"8","author":"M Omar","year":"2024","unstructured":"Omar, M., Alexanderani, M. K., Valencia, I., Loda, M. & Marchionni, L. Applications of digital pathology in cancer: A comprehensive review. Annu. Rev. Cancer Biol. 8, 245\u2013268 (2024).","journal-title":"Annu. Rev. Cancer Biol."},{"key":"52148_CR2","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1001\/jama.2017.14585","volume":"318","author":"B Ehteshami Bejnordi","year":"2017","unstructured":"Ehteshami Bejnordi, B. et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 318, 2199\u20132210 (2017).","journal-title":"JAMA"},{"key":"52148_CR3","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1016\/S1470-2045(19)30738-7","volume":"21","author":"P Str\u00f6m","year":"2020","unstructured":"Str\u00f6m, P. et al. Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study. Lancet Oncol. 21, 222\u2013232 (2020).","journal-title":"Lancet Oncol."},{"key":"52148_CR4","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s41698-024-00539-4","volume":"8","author":"PC Neto","year":"2024","unstructured":"Neto, P. C. et al. An interpretable machine learning system for colorectal cancer diagnosis from pathology slides. NPJ Precis Oncol. 8, 56 (2024).","journal-title":"NPJ Precis Oncol."},{"key":"52148_CR5","doi-asserted-by":"publisher","first-page":"100496","DOI":"10.1016\/j.modpat.2024.100496","volume":"37","author":"A Giammanco","year":"2024","unstructured":"Giammanco, A. et al. Fast-track development and multi-institutional clinical validation of an artificial intelligence algorithm for detection of lymph node metastasis in colorectal cancer. Mod. Pathol. 37, 100496 (2024).","journal-title":"Mod. Pathol."},{"key":"52148_CR6","doi-asserted-by":"publisher","first-page":"1054","DOI":"10.1038\/s41591-019-0462-y","volume":"25","author":"JN Kather","year":"2019","unstructured":"Kather, J. N. et al. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat. Med. 25, 1054\u20131056 (2019).","journal-title":"Nat. Med."},{"key":"52148_CR7","doi-asserted-by":"publisher","first-page":"1650","DOI":"10.1016\/j.ccell.2023.08.002","volume":"41","author":"SJ Wagner","year":"2023","unstructured":"Wagner, S. J. et al. Transformer-based biomarker prediction from colorectal cancer histology: A large-scale multicentric study. Cancer Cell. 41, 1650\u20131661e4 (2023).","journal-title":"Cancer Cell."},{"key":"52148_CR8","doi-asserted-by":"publisher","first-page":"e763","DOI":"10.1016\/S2589-7500(21)00180-1","volume":"3","author":"M Bilal","year":"2021","unstructured":"Bilal, M. et al. Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study. Lancet Digit. Health. 3, e763\u2013e772 (2021).","journal-title":"Lancet Digit. Health"},{"key":"52148_CR9","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1002\/cjp2.312","volume":"9","author":"B Guo","year":"2023","unstructured":"Guo, B. et al. Predicting microsatellite instability and key biomarkers in colorectal cancer from H&E-stained images: Achieving state-of-the-art predictive performance with fewer data using Swin Transformer. J. Pathol. Clin. Res. 9, 223\u2013235 (2023).","journal-title":"J. Pathol. Clin. Res."},{"key":"52148_CR10","doi-asserted-by":"publisher","first-page":"3462","DOI":"10.1093\/bioinformatics\/btac343","volume":"38","author":"P Weitz","year":"2022","unstructured":"Weitz, P. et al. Transcriptome-wide prediction of prostate cancer gene expression from histopathology images using co-expression-based convolutional neural networks. Bioinformatics 38, 3462\u20133469 (2022).","journal-title":"Bioinformatics"},{"key":"52148_CR11","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-022-09559-4","volume":"22","author":"V Dadhania","year":"2022","unstructured":"Dadhania, V. et al. Leveraging artificial intelligence to predict ERG gene fusion status in prostate cancer. BMC Cancer 22, 494 (2022).","journal-title":"BMC Cancer"},{"key":"52148_CR12","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.21.00131","volume":"6","author":"W Huang","year":"2022","unstructured":"Huang, W. et al. A novel artificial intelligence-powered method for prediction of early recurrence of prostate cancer after prostatectomy and cancer drivers. JCO Clin. Cancer Inform. 6, e2100131 (2022).","journal-title":"JCO Clin. Cancer Inform."},{"key":"52148_CR13","doi-asserted-by":"publisher","first-page":"e33","DOI":"10.1016\/S2589-7500(23)00208-X","volume":"6","author":"X Jiang","year":"2024","unstructured":"Jiang, X. et al. End-to-end prognostication in colorectal cancer by deep learning: A retrospective, multicentre study. Lancet Digit. Health 6, e33\u2013e43 (2024).","journal-title":"Lancet Digit. Health"},{"key":"52148_CR14","doi-asserted-by":"publisher","first-page":"102111","DOI":"10.1016\/j.labinv.2024.102111","volume":"104","author":"DY Zhang","year":"2024","unstructured":"Zhang, D. Y. et al. Implementation of digital pathology and artificial intelligence in routine pathology practice. Lab. Invest. 104, 102111 (2024).","journal-title":"Lab. Invest."},{"key":"52148_CR15","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.5858\/arpa.2022-0066-OA","volume":"147","author":"P Raciti","year":"2023","unstructured":"Raciti, P. et al. Clinical validation of artificial intelligence-augmented pathology diagnosis demonstrates significant gains in diagnostic accuracy in prostate cancer detection. Arch. Pathol. Lab. Med. 147, 1178\u20131185 (2023).","journal-title":"Arch. Pathol. Lab. Med."},{"key":"52148_CR16","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1111\/his.15153","volume":"84","author":"PJ van Diest","year":"2024","unstructured":"van Diest, P. J. et al. Pros and cons of artificial intelligence implementation in diagnostic pathology. Histopathology 84, 924\u2013934 (2024).","journal-title":"Histopathology"},{"key":"52148_CR17","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1136\/jclinpath-2020-206908","volume":"74","author":"EA Rakha","year":"2021","unstructured":"Rakha, E. A. et al. Current and future applications of artificial intelligence in pathology: A clinical perspective. J. Clin. Pathol. 74, 409\u2013414 (2021).","journal-title":"J. Clin. Pathol."},{"key":"52148_CR18","doi-asserted-by":"publisher","first-page":"1021","DOI":"10.1002\/mp.13964","volume":"47","author":"C-M Chen","year":"2020","unstructured":"Chen, C.-M., Huang, Y.-S., Fang, P.-W., Liang, C.-W. & Chang, R.-F. A computer-aided diagnosis system for differentiation and delineation of malignant regions on whole-slide prostate histopathology image using spatial statistics and multidimensional DenseNet. Med. Phys. 47, 1021\u20131033 (2020).","journal-title":"Med. Phys."},{"key":"52148_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105637","volume":"195","author":"J Silva-Rodr\u00edguez","year":"2020","unstructured":"Silva-Rodr\u00edguez, J., Colomer, A., Sales, M. A., Molina, R. & Naranjo, V. Going deeper through the Gleason scoring scale: An automatic end-to-end system for histology prostate grading and cribriform pattern detection. Comput. Methods Programs Biomed. 195, 105637 (2020).","journal-title":"Comput. Methods Programs Biomed."},{"key":"52148_CR20","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-90444-8","volume":"11","author":"M Khened","year":"2021","unstructured":"Khened, M., Kori, A., Rajkumar, H., Krishnamurthi, G. & Srinivasan, B. A generalized deep learning framework for whole-slide image segmentation and analysis. Sci. Rep. 11, 11579 (2021).","journal-title":"Sci. Rep."},{"issue":"3","key":"52148_CR21","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12030768","volume":"12","author":"M Tsuneki","year":"2022","unstructured":"Tsuneki, M., Abe, M. & Kanavati, F. A deep learning model for prostate adenocarcinoma classification in needle biopsy whole-slide images using transfer learning. Diagnostics\u00a012 (3), 768. https:\/\/doi.org\/10.3390\/diagnostics12030768 (2022).","journal-title":"Diagnostics"},{"issue":"19","key":"52148_CR22","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14194744","volume":"14","author":"M Tsuneki","year":"2022","unstructured":"Tsuneki, M., Abe, M. & Kanavati, F. Transfer learning for adenocarcinoma classifications in the transurethral resection of prostate whole-slide images. Cancers 14 (19), 4744. https:\/\/doi.org\/10.3390\/cancers14194744 (2022).","journal-title":"Cancers"},{"key":"52148_CR23","doi-asserted-by":"publisher","first-page":"e681","DOI":"10.1016\/S2589-7500(24)00150-X","volume":"6","author":"I Heckenbach","year":"2024","unstructured":"Heckenbach, I. et al. Deep learning assessment of senescence-associated nuclear morphologies in mammary tissue from healthy female donors to predict future risk of breast cancer: A retrospective cohort study. Lancet Digit. Health 6, e681\u2013e690 (2024).","journal-title":"Lancet Digit. Health"},{"key":"52148_CR24","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.annonc.2021.09.007","volume":"33","author":"Y Wang","year":"2022","unstructured":"Wang, Y. et al. Improved breast cancer histological grading using deep learning. Ann. Oncol. 33, 89\u201398 (2022).","journal-title":"Ann. Oncol."},{"key":"52148_CR25","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.7.5.057501","volume":"7","author":"JD Bukowy","year":"2020","unstructured":"Bukowy, J. D. et al. Accurate segmentation of prostate cancer histomorphometric features using a weakly supervised convolutional neural network. J. Med. Imaging 7, 057501 (2020).","journal-title":"J. Med. Imaging"},{"key":"52148_CR26","doi-asserted-by":"publisher","first-page":"1232","DOI":"10.1038\/s41591-022-01768-5","volume":"28","author":"OL Saldanha","year":"2022","unstructured":"Saldanha, O. L. et al. Swarm learning for decentralized artificial intelligence in cancer histopathology. Nat. Med. 28, 1232\u20131239 (2022).","journal-title":"Nat. Med."},{"key":"52148_CR27","unstructured":"Campanella, G., Silva, V. W. K. & Fuchs, T. J. Terabyte-scale Deep Multiple Instance Learning for Classification and Localization in Pathology. arXiv [cs.CV] (2018)."},{"key":"52148_CR28","doi-asserted-by":"publisher","first-page":"e786","DOI":"10.1016\/S2589-7500(23)00148-6","volume":"5","author":"M Bilal","year":"2023","unstructured":"Bilal, M. et al. Development and validation of artificial intelligence-based prescreening of large-bowel biopsies taken in the UK and Portugal: a retrospective cohort study. Lancet Digit. Health. 5, e786\u2013e797 (2023).","journal-title":"Lancet Digit. Health"},{"key":"52148_CR29","doi-asserted-by":"publisher","unstructured":"van Treeck, M. et al. DeepMed: A unified, modular pipeline for end-to-end deep learning in computational pathology. (2021). https:\/\/doi.org\/10.1101\/2021.12.19.473344","DOI":"10.1101\/2021.12.19.473344"},{"key":"52148_CR30","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1186\/s12859-024-05758-x","volume":"25","author":"JM Dolezal","year":"2024","unstructured":"Dolezal, J. M. et al. Slideflow: deep learning for digital histopathology with real-time whole-slide visualization. BMC Bioinform. 25, 134 (2024).","journal-title":"BMC Bioinform."},{"key":"52148_CR31","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1038\/s43856-022-00186-5","volume":"2","author":"J Pocock","year":"2022","unstructured":"Pocock, J. et al. TIAToolbox as an end-to-end library for advanced tissue image analytics. Commun. Med. 2, 120 (2022).","journal-title":"Commun. Med."},{"key":"52148_CR32","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","volume":"5","author":"MY Lu","year":"2021","unstructured":"Lu, M. Y. et al. Data-efficient and weakly supervised computational pathology on whole-slide images. Nat. Biomed. Eng. 5, 555\u2013570 (2021).","journal-title":"Nat. Biomed. Eng."},{"issue":"1","key":"52148_CR33","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1146\/annurev-cancerbio-061521-092038","volume":"7","author":"D Cifci","year":"2023","unstructured":"Cifci, D., Veldhuizen, G. P., Foersch, S. & Kather, J. N. AI in computational pathology of cancer: Improving diagnostic workflows and clinical outcomes? Annu. Rev. Cancer Biol.\u00a07 (1), 57\u201371. https:\/\/doi.org\/10.1146\/annurev-cancerbio-061521-092038 (2023).","journal-title":"Annu. Rev. Cancer Biol."},{"key":"52148_CR34","doi-asserted-by":"publisher","unstructured":"B\u00e1ndi, P. et al. Comparison of Different Methods for Tissue Segmentation in Histopathological Whole-Slide Images. Preprint at (2017). https:\/\/doi.org\/10.48550\/ARXIV.1703.05990","DOI":"10.48550\/ARXIV.1703.05990"},{"key":"52148_CR35","doi-asserted-by":"publisher","unstructured":"Mulliqi, N. et al. Foundation Models -- A Panacea for Artificial Intelligence in Pathology? Preprint at (2025). https:\/\/doi.org\/10.48550\/arXiv.2502.21264","DOI":"10.48550\/arXiv.2502.21264"},{"key":"52148_CR36","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu, N. A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9, 62\u201366 (1979).","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"52148_CR37","doi-asserted-by":"publisher","first-page":"100715","DOI":"10.1016\/j.modpat.2025.100715","volume":"38","author":"X Ji","year":"2025","unstructured":"Ji, X. et al. Physical Color Calibration of Digital Pathology Scanners for Robust Artificial Intelligence\u2013Assisted Cancer Diagnosis. Mod. Pathol. 38, 100715 (2025).","journal-title":"Mod. Pathol."},{"key":"52148_CR38","doi-asserted-by":"publisher","first-page":"7761","DOI":"10.1038\/s41467-022-34945-8","volume":"13","author":"H Olsson","year":"2022","unstructured":"Olsson, H. et al. Estimating diagnostic uncertainty in artificial intelligence assisted pathology using conformal prediction. Nat. Commun. 13, 7761 (2022).","journal-title":"Nat. Commun."},{"key":"52148_CR39","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/s00428-022-03326-3","volume":"481","author":"K Kartasalo","year":"2022","unstructured":"Kartasalo, K. et al. Detection of perineural invasion in prostate needle biopsies with deep neural networks. Virchows Arch. Int. J. Pathol. 481, 73\u201382 (2022).","journal-title":"Virchows Arch. Int. J. Pathol."},{"key":"52148_CR40","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1038\/s41591-021-01620-2","volume":"28","author":"W Bulten","year":"2022","unstructured":"Bulten, W. et al. Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge. Nat. Med. 28, 154\u2013163 (2022).","journal-title":"Nat. Med."},{"key":"52148_CR41","doi-asserted-by":"publisher","first-page":"5115","DOI":"10.1158\/0008-5472.CAN-21-0482","volume":"81","author":"Y Wang","year":"2021","unstructured":"Wang, Y. et al. Predicting Molecular Phenotypes from Histopathology Images: A Transcriptome-Wide Expression-Morphology Analysis in Breast Cancer. Cancer Res. 81, 5115\u20135126 (2021).","journal-title":"Cancer Res."},{"key":"52148_CR42","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1016\/S0302-2838(26)00802-X","volume":"89","author":"A Camilloni","year":"2026","unstructured":"Camilloni, A. et al. A0754 Validation of a multimodal deep learning model for predicting biochemical recurrence in men undergoing radiation therapy. Eur. Urol. 89, S1\u2013S2 (2026).","journal-title":"Eur. Urol."},{"key":"52148_CR43","doi-asserted-by":"publisher","unstructured":"Ali, P. J. M. et al. Validation of Diagnostic Artificial Intelligence Models for Prostate Pathology in a Middle Eastern Cohort. Preprint at (2025). https:\/\/doi.org\/10.48550\/ARXIV.2512.17499","DOI":"10.48550\/ARXIV.2512.17499"},{"key":"52148_CR44","doi-asserted-by":"publisher","unstructured":"Szolnoky, K. et al. Finding Holes: Pathologist Level Performance Using AI for Cribriform Morphology Detection in Prostate Cancer. Preprint at (2025). https:\/\/doi.org\/10.48550\/ARXIV.2510.13995","DOI":"10.48550\/ARXIV.2510.13995"},{"key":"52148_CR45","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1038\/s43856-025-01185-y","volume":"5","author":"A Blilie","year":"2025","unstructured":"Blilie, A. et al. Artificial intelligence-assisted prostate cancer diagnosis for reduced use of immunohistochemistry. Commun. Med. 5, 425 (2025).","journal-title":"Commun. Med."},{"key":"52148_CR46","doi-asserted-by":"publisher","DOI":"10.1101\/2024.07.04.24309948","author":"N Mulliqi","year":"2024","unstructured":"Mulliqi, N. et al. Study protocol: Development and retrospective validation of an artificial intelligence system for diagnostic assessment of prostate biopsies. medRxiv https:\/\/doi.org\/10.1101\/2024.07.04.24309948 (2024).","journal-title":"medRxiv"},{"key":"52148_CR47","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-00889-5_1","volume":"11045","author":"Z Zhou","year":"2018","unstructured":"Zhou, Z., Siddiquee, M. M. R., Tajbakhsh, N., Liang, J. & UNet++ A nested U-Net architecture for medical image segmentation. Deep Learn. Med. Image Anal. Multimodal Learn. Clin. Decis. Support. 11045, 3\u201311 (2018).","journal-title":"Deep Learn. Med. Image Anal. Multimodal Learn. Clin. Decis. Support"},{"key":"52148_CR48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1505.04597","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional networks for biomedical image segmentation. arXiv https:\/\/doi.org\/10.48550\/ARXIV.1505.04597 (2015).","journal-title":"arXiv"},{"key":"52148_CR49","unstructured":"Iakubovskii, P. Segmentation Models Pytorch. (2019). https:\/\/github.com\/qubvel-org\/segmentation_models.pytorch"},{"key":"52148_CR50","doi-asserted-by":"publisher","unstructured":"Loshchilov, I. & Hutter, F. Decoupled Weight Decay Regularization. Preprint at (2017). https:\/\/doi.org\/10.48550\/ARXIV.1711.05101","DOI":"10.48550\/ARXIV.1711.05101"},{"key":"52148_CR51","doi-asserted-by":"publisher","unstructured":"Ilse, M., Tomczak, J. M. & Welling, M. Attention-based Deep Multiple Instance Learning. Preprint at (2018). https:\/\/doi.org\/10.48550\/ARXIV.1802.04712","DOI":"10.48550\/ARXIV.1802.04712"},{"key":"52148_CR52","doi-asserted-by":"publisher","unstructured":"Tan, M. & Le, Q. V. EfficientNetV2: Smaller Models and Faster Training. (2021). https:\/\/doi.org\/10.48550\/ARXIV.2104.00298","DOI":"10.48550\/ARXIV.2104.00298"},{"key":"52148_CR53","doi-asserted-by":"publisher","first-page":"29224","DOI":"10.1038\/s41598-024-79838-6","volume":"14","author":"BG Hill","year":"2024","unstructured":"Hill, B. G., Koback, F. L. & Schilling, P. L. The risk of shortcutting in deep learning algorithms for medical imaging research. Sci. Rep. 14, 29224 (2024).","journal-title":"Sci. Rep."},{"key":"52148_CR54","doi-asserted-by":"publisher","first-page":"e58","DOI":"10.1016\/S2589-7500(23)00219-4","volume":"6","author":"A Vafaei Sadr","year":"2024","unstructured":"Vafaei Sadr, A. et al. Operational greenhouse-gas emissions of deep learning in digital pathology: A modelling study. Lancet Digit. Health 6, e58\u2013e69 (2024).","journal-title":"Lancet Digit. Health"},{"key":"52148_CR55","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1002\/num.20129","volume":"22","author":"M Patra","year":"2006","unstructured":"Patra, M. & Karttunen, M. Stencils with isotropic discretization error for differential operators. Numer. Methods Partial Differ. Equ. 22, 936\u2013953 (2006).","journal-title":"Numer. Methods Partial Differ. Equ."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52148-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52148-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52148-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:02:17Z","timestamp":1778691737000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52148-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,13]]},"references-count":55,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["52148"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-52148-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,13]]},"assertion":[{"value":"26 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"N.M., L.E., and K.K. are shareholders of Clinsight AB.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"This study included data gathered in one or more collection rounds at participating international sites between 2012 and 2024. All datasets were de-identified at their respective sites and subsequently transferred to Karolinska Institutet in an anonymized format. This study complies with the Helsinki Declaration. The patient sample collection was approved by the Stockholm Regional Ethics Committee (permits 2012\/572\u2009\u2212\u200931\/1, 2012\/438\u2009\u2212\u200931\/3, and 2018\/845\u2009\u2212\u200932), the Swedish Ethical Review Authority (permit 2019\u201305220), and the Regional Committee for Medical and Health Research Ethics in Western Norway (permits REC\/Vest 80924, REK 2017\/71). Informed consent was obtained from patients in the Swedish dataset and was waived for other data cohorts due to the use of de-identified prostate specimens in a retrospective setting. Patient involvement in this study was supported by the Swedish Prostate Cancer Society.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical considerations"}}],"article-number":"14968"}}