{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T03:23:47Z","timestamp":1794885827006,"version":"4.9.1"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>The aggressiveness of prostate cancer is primarily assessed from histopathological data using the Gleason scoring system. Conventional artificial intelligence (AI) approaches can predict Gleason scores, but often lack explainability, which may limit clinical acceptance. Here, we present an alternative, inherently explainable AI that circumvents the need for post-hoc explainability methods. The model was trained on 1,015 tissue microarray core images, annotated with detailed pattern descriptions by 54 international pathologists following standardized guidelines. It uses pathologist-defined terminology and was trained using soft labels to capture data uncertainty. This approach enables robust Gleason pattern segmentation despite high interobserver variability. The model achieved comparable or superior performance to direct Gleason pattern segmentation (Dice score: <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>$${0.713}_{\\pm 0.003}$$<\/jats:tex-math>\n                <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:msub>\n                    <mml:mrow>\n                      <mml:mn>0.713<\/mml:mn>\n                    <\/mml:mrow>\n                    <mml:mrow>\n                      <mml:mo>\u00b1<\/mml:mo>\n                      <mml:mn>0.003<\/mml:mn>\n                    <\/mml:mrow>\n                  <\/mml:msub>\n                <\/mml:math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula> vs. <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>$${0.691}_{\\pm 0.010}$$<\/jats:tex-math>\n                <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:msub>\n                    <mml:mrow>\n                      <mml:mn>0.691<\/mml:mn>\n                    <\/mml:mrow>\n                    <mml:mrow>\n                      <mml:mo>\u00b1<\/mml:mo>\n                      <mml:mn>0.010<\/mml:mn>\n                    <\/mml:mrow>\n                  <\/mml:msub>\n                <\/mml:math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula>) while providing interpretable outputs. We release this dataset to encourage further research on segmentation in medical tasks with high subjectivity and to deepen insights into pathologists\u2019 reasoning.<\/jats:p>","DOI":"10.1038\/s41467-025-64712-4","type":"journal-article","created":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T09:58:26Z","timestamp":1759917506000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Pathologist-like explainable AI for interpretable Gleason grading in prostate cancer"],"prefix":"10.1038","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0375-4689","authenticated-orcid":false,"given":"Gesa","family":"Mittmann","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Laiouar-Pedari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hendrik A.","family":"Mehrtens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah","family":"Haggenm\u00fcller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tabea-Clara","family":"Bucher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0649-9301","authenticated-orcid":false,"given":"Tirtha","family":"Chanda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nadine T.","family":"Gaisa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathias","family":"Wagner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gilbert Georg","family":"Klamminger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tilman T.","family":"Rau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christina","family":"Neppl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eva Maria","family":"Comp\u00e9rat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Gocht","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3145-0541","authenticated-orcid":false,"given":"Monika","family":"Haemmerle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niels J.","family":"Rupp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jula","family":"Westhoff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Irene","family":"Kr\u00fccken","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5559-4980","authenticated-orcid":false,"given":"Maximilian","family":"Seidl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1792-1768","authenticated-orcid":false,"given":"Christian M.","family":"Sch\u00fcrch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0657-6831","authenticated-orcid":false,"given":"Marcus","family":"Bauer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wiebke","family":"Solass","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu Chun","family":"Tam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7480-8828","authenticated-orcid":false,"given":"Florian","family":"Weber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1901-7967","authenticated-orcid":false,"given":"Rainer","family":"Grobholz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaroslaw","family":"Augustyniak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Kalinski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"H\u00f6rner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kirsten D.","family":"Mertz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Constanze","family":"D\u00f6ring","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Erbersdobler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabriele","family":"Deubler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Bremmer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ulrich","family":"Sommer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Brodhun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3969-7637","authenticated-orcid":false,"given":"Jon","family":"Griffin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria Sarah L.","family":"Lenon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kiril","family":"Trpkov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6049-5293","authenticated-orcid":false,"given":"Liang","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8005-4399","authenticated-orcid":false,"given":"Fei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angelique","family":"Levi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoping","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tri Q.","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Amin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessia","family":"Cimadamore","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"Shabaik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Varsha","family":"Manucha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nazeel","family":"Ahmad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nidia","family":"Messias","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesca","family":"Sanguedolce","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diana","family":"Taheri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ezra","family":"Baraban","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liwei","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajal B.","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farshid","family":"Siadat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicole","family":"Swarbrick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyung","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oudai","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siamak","family":"Sakhaie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michelle R.","family":"Downes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7610-7769","authenticated-orcid":false,"given":"Hiroshi","family":"Miyamoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sean R.","family":"Williamson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim","family":"Holland-Letz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7136-298X","authenticated-orcid":false,"given":"Christoph","family":"Wies","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carolin V.","family":"Schneider","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jakob Nikolas","family":"Kather","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5239-2841","authenticated-orcid":false,"given":"Yuri","family":"Tolkach","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3620-5919","authenticated-orcid":false,"given":"Titus J.","family":"Brinker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,8]]},"reference":[{"key":"64712_CR1","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1002\/ijc.33588","volume":"149","author":"J Ferlay","year":"2021","unstructured":"Ferlay, J. et al. Cancer statistics for the year 2020: An overview. Int. J. Cancer 149, 778\u2013789 (2021).","journal-title":"Int. J. Cancer"},{"key":"64712_CR2","first-page":"134","volume":"197","author":"DF Gleason","year":"1974","unstructured":"Gleason, D. F., Mellinger, G. T. & Veterans Administration Cooperative Urological Research Group Prediction of Prognosis for Prostatic Adenocarcinoma by Combined Histological Grading and Clinical Staging. J. Urol. 197, 134\u2013139 (1974).","journal-title":"J. Urol."},{"key":"64712_CR3","doi-asserted-by":"publisher","DOI":"10.1097\/PAS.0000000000001497","volume":"44","author":"GJLH van Leenders","year":"2020","unstructured":"van Leenders, G. J. L. H. et al. The 2019 International Society of Urological Pathology (ISUP) Consensus Conference on Grading of Prostatic Carcinoma. Am. J. Surg. Pathol. 44, e87 (2020).","journal-title":"Am. J. Surg. Pathol."},{"key":"64712_CR4","doi-asserted-by":"publisher","first-page":"461","DOI":"10.5858\/arpa.2020-0015-RA","volume":"145","author":"JI Epstein","year":"2021","unstructured":"Epstein, J. I. et al. The 2019 Genitourinary Pathology Society (GUPS) White Paper on Contemporary Grading of Prostate Cancer. Arch. Pathol. Lab. Med. 145, 461\u2013493 (2021).","journal-title":"Arch. Pathol. Lab. Med."},{"key":"64712_CR5","unstructured":"Leitlinienprogramm Onkologie (Deutsche Krebsgesellschaft, Deutsche Krebshilfe, AWMF). S3-Leitlinie Prostatakarzinom, Langversion 7.0. AWMF Leitlinienregister. Registernummer 043-022OL. https:\/\/www.leitlinienprogramm-onkologie.de\/leitlinien\/prostatakarzinom\/ (2024)."},{"key":"64712_CR6","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1097\/PAS.0000000000000530","volume":"40","author":"JI Epstein","year":"2016","unstructured":"Epstein, J. I. et al. The 2014 International Society of Urological Pathology (ISUP) Consensus Conference on Gleason Grading of Prostatic Carcinoma: Definition of Grading Patterns and Proposal for a New Grading System. Am. J. Surg. Pathol. 40, 244\u2013252 (2016).","journal-title":"Am. J. Surg. Pathol."},{"key":"64712_CR7","doi-asserted-by":"crossref","unstructured":"Epstein, J. I. Prostate cancer grading: a decade after the 2005 modified system. Mod. Pathol. 31 (2018).","DOI":"10.1038\/modpathol.2017.133"},{"key":"64712_CR8","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.1007\/s00432-008-0388-0","volume":"134","author":"M Burchardt","year":"2008","unstructured":"Burchardt, M. et al. Interobserver reproducibility of Gleason grading: evaluation using prostate cancer tissue microarrays. J. Cancer Res. Clin. Oncol. 134, 1071\u20131078 (2008).","journal-title":"J. Cancer Res. Clin. Oncol."},{"key":"64712_CR9","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1016\/j.euf.2021.07.002","volume":"7","author":"K Kartasalo","year":"2021","unstructured":"Kartasalo, K. et al. Artificial intelligence for diagnosis and Gleason grading of prostate cancer in biopsies-current status and next steps. Eur. Urol. Focus 7, 687\u2013691 (2021).","journal-title":"Eur. Urol. Focus"},{"key":"64712_CR10","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1038\/s41379-020-0640-y","volume":"34","author":"W Bulten","year":"2021","unstructured":"Bulten, W. et al. Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists. Mod. Pathol. 34, 660\u2013671 (2021).","journal-title":"Mod. Pathol."},{"key":"64712_CR11","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":"64712_CR12","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1016\/j.euf.2020.11.001","volume":"7","author":"F Marginean","year":"2021","unstructured":"Marginean, F. et al. An artificial intelligence-based support tool for automation and standardisation of Gleason grading in prostate biopsies. Eur. Urol. Focus 7, 995\u20131001 (2021).","journal-title":"Eur. Urol. Focus"},{"key":"64712_CR13","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.media.2018.09.005","volume":"50","author":"G Nir","year":"2018","unstructured":"Nir, G. et al. Automatic grading of prostate cancer in digitized histopathology images: Learning from multiple experts. Med. Image Anal. 50, 167\u2013180 (2018).","journal-title":"Med. Image Anal."},{"key":"64712_CR14","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1109\/JBHI.2019.2944643","volume":"24","author":"D Karimi","year":"2020","unstructured":"Karimi, D. et al. Deep learning-based Gleason grading of prostate cancer from histopathology images-role of multiscale decision aggregation and data augmentation. IEEE J. Biomed. Health Inf. 24, 1413\u20131426 (2020).","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"64712_CR15","doi-asserted-by":"crossref","unstructured":"Hayashi, Y. Black box nature of deep learning for digital pathology: beyond quantitative to qualitative algorithmic performances. Artif. Inteil. Mach. Learn. Digit. Pathol. 95\u2013101 (2020).","DOI":"10.1007\/978-3-030-50402-1_6"},{"key":"64712_CR16","first-page":"359","volume":"4","author":"S Tonekaboni","year":"2019","unstructured":"Tonekaboni, S., Joshi, S., McCradden, M. D. & Goldenberg, A. What clinicians want: contextualizing explainable machine learning for clinical end use. Mach. Learn. Healthc. Conf. 4, 359\u2013380 (2019).","journal-title":"Mach. Learn. Healthc. Conf."},{"key":"64712_CR17","first-page":"50","volume":"38","author":"B Goodman","year":"2017","unstructured":"Goodman, B. & Flaxman, S. European Union regulations on algorithmic decision making and a \u2018right to explanation. AI Mag. 38, 50\u201357 (2017).","journal-title":"AI Mag."},{"key":"64712_CR18","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2019","unstructured":"Selvaraju, R. R. et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vis. 128, 336\u2013359 (2019).","journal-title":"Int. J. Comput. Vis."},{"key":"64712_CR19","doi-asserted-by":"publisher","first-page":"e0130140","DOI":"10.1371\/journal.pone.0130140","volume":"10","author":"S Bach","year":"2015","unstructured":"Bach, S. et al. On Pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS One 10, e0130140 (2015).","journal-title":"PLoS One"},{"key":"64712_CR20","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1145\/2939672.2939778","volume":"16","author":"MT Ribeiro","year":"2016","unstructured":"Ribeiro, M. T., Singh, S. & Guestrin, C. \u2018Why Should I Trust You?\u2019: Explaining the predictions of any classifier. Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. 16, 1135\u20131144 (2016).","journal-title":"Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min."},{"key":"64712_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13014-022-02035-0","volume":"17","author":"DD Gunashekar","year":"2022","unstructured":"Gunashekar, D. D. et al. Explainable AI for CNN-based prostate tumor segmentation in multi-parametric MRI correlated to whole mount histopathology. Radiat. Oncol. 17, 1\u201310 (2022).","journal-title":"Radiat. Oncol."},{"key":"64712_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-018-30535-1","volume":"8","author":"E Arvaniti","year":"2018","unstructured":"Arvaniti, E. et al. Automated Gleason grading of prostate cancer tissue microarrays via deep learning. Sci. Rep. 8, 1\u201311 (2018).","journal-title":"Sci. Rep."},{"key":"64712_CR23","doi-asserted-by":"publisher","first-page":"103865","DOI":"10.1016\/j.compbiomed.2020.103865","volume":"123","author":"M Grazian","year":"2020","unstructured":"Grazian, M., Andrearczyk, V., Marchand-Maillet, S. & M\u00fcller, H. Concept attribution: Explaining CNN decisions to physicians. Comput. Biol. Med. 123, 103865 (2020).","journal-title":"Comput. Biol. Med."},{"key":"64712_CR24","doi-asserted-by":"publisher","first-page":"5346","DOI":"10.3390\/s22145346","volume":"22","author":"D Sauter","year":"2022","unstructured":"Sauter, D. et al. Validating automatic concept-based explanations for AI-based digital histopathology. Sensors 22, 5346 (2022).","journal-title":"Sensors"},{"key":"64712_CR25","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/j.inffus.2021.07.015","volume":"77","author":"CJ Anders","year":"2022","unstructured":"Anders, C. J. et al. Finding and removing Clever Hans: Using explanation methods to debug and improve deep models. Inf. Fusion 77, 261\u2013295 (2022).","journal-title":"Inf. Fusion"},{"key":"64712_CR26","doi-asserted-by":"publisher","first-page":"6021","DOI":"10.1609\/aaai.v34i04.6064","volume":"34","author":"R Tomsett","year":"2020","unstructured":"Tomsett, R., Harborne, D., Chakraborty, S., Gurram, P. & Preece, A. Sanity checks for saliency metrics. AAAI 34, 6021\u20136029 (2020).","journal-title":"AAAI"},{"key":"64712_CR27","unstructured":"Adebayo, J. et al. Sanity Checks for Saliency Maps. Adv. Neural Inf. Process. Syst. 31, (2018)."},{"key":"64712_CR28","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/j.future.2022.03.009","volume":"133","author":"T Evans","year":"2022","unstructured":"Evans, T. et al. The explainability paradox: Challenges for xAI in digital pathology. Future Gener. Comput. Syst. 133, 281\u2013296 (2022).","journal-title":"Future Gener. Comput. Syst."},{"key":"64712_CR29","first-page":"5338","volume":"37","author":"PW Koh","year":"2020","unstructured":"Koh, P. W. et al. Concept Bottleneck Models. Proc. 37th Int. Conf. Mach. Learn. (PMLR) 37, 5338\u20135348 (2020).","journal-title":"Proc. 37th Int. Conf. Mach. Learn. (PMLR)"},{"key":"64712_CR30","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015, Lecture Notes in Computer Science, 9351. Springer, Cham. (2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"64712_CR31","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1037\/h0031619","volume":"76","author":"JL Fleiss","year":"1971","unstructured":"Fleiss, J. L. Measuring nominal scale agreement among many raters. Psychol. Bull. 76, 378\u2013382 (1971).","journal-title":"Psychol. Bull."},{"key":"64712_CR32","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","volume":"33","author":"JR Landis","year":"1977","unstructured":"Landis, J. R. & Koch, G. G. The measurement of observer agreement for categorical data. Biometrics 33, 159\u2013174 (1977).","journal-title":"Biometrics"},{"key":"64712_CR33","doi-asserted-by":"publisher","first-page":"1242","DOI":"10.1097\/PAS.0000000000000442","volume":"39","author":"RB Shah","year":"2015","unstructured":"Shah, R. B. et al. Diagnosis of Gleason pattern 5 prostate adenocarcinoma on core needle biopsy: an interobserver reproducibility study among urologic pathologists. Am. J. Surg. Pathol. 39, 1242\u20131249 (2015).","journal-title":"Am. J. Surg. Pathol."},{"key":"64712_CR34","doi-asserted-by":"publisher","first-page":"1331","DOI":"10.1097\/PAS.0000000000000457","volume":"39","author":"M Zhou","year":"2015","unstructured":"Zhou, M. et al. Diagnosis of \u2018Poorly Formed Glands\u2019 Gleason Pattern 4 Prostatic Adenocarcinoma on Needle Biopsy: An Interobserver Reproducibility Study Among Urologic Pathologists With Recommendations. Am. J. Surg. Pathol. 39, 1331\u20131339 (2015).","journal-title":"Am. J. Surg. Pathol."},{"key":"64712_CR35","first-page":"3990","volume":"11","author":"RB Shah","year":"2021","unstructured":"Shah, R. B. et al. Diagnosis of \u2018cribriform\u2019 prostatic adenocarcinoma: an interobserver reproducibility study among urologic pathologists with recommendations. Am. J. Cancer Res. 11, 3990\u20134001 (2021).","journal-title":"Am. J. Cancer Res."},{"key":"64712_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Z., Popordanoska, T., Bertels, J., Lemmens, R. & Blaschko, M. B. Dice Semimetric Losses: Optimizing the Dice Score with Soft Labels. in Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023 475\u2013485 (2023).","DOI":"10.1007\/978-3-031-43898-1_46"},{"key":"64712_CR37","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1038\/s41592-023-02150-0","volume":"21","author":"A Reinke","year":"2024","unstructured":"Reinke, A. et al. Understanding metric-related pitfalls in image analysis validation. Nat. Methods 21, 182\u2013194 (2024).","journal-title":"Nat. Methods"},{"key":"64712_CR38","doi-asserted-by":"publisher","unstructured":"Leslie, D. Understanding artificial intelligence ethics and safety: A guide for the responsible design and implementation of AI systems in the public sector. The Alan Turing Institute. https:\/\/doi.org\/10.5281\/zenodo.3240529 (2019).","DOI":"10.5281\/zenodo.3240529"},{"key":"64712_CR39","doi-asserted-by":"publisher","first-page":"105637","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 Prog. Biomed. 195, 105637 (2020).","journal-title":"Comput. Methods Prog. Biomed."},{"key":"64712_CR40","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1145\/3233231","volume":"61","author":"ZC Lipton","year":"2018","unstructured":"Lipton, Z. C. The Mythos of Model Interpretability. Commun. ACM 61, 36\u201343 (2018).","journal-title":"Commun. ACM"},{"key":"64712_CR41","first-page":"35218","volume":"36","author":"R Shwartz-Ziv","year":"2023","unstructured":"Shwartz-Ziv, R., Goldblum, M., Li, Y. L., Bruss, C. B. & Wilson, A. G. Simplifying Neural Network Training Under Class Imbalance. Adv. Neural Inf. Process. Syst. (NeurIPS 2023) 36, 35218\u201335245 (2023).","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS 2023)"},{"key":"64712_CR42","doi-asserted-by":"publisher","first-page":"2064","DOI":"10.1038\/s41379-021-00860-4","volume":"34","author":"T Hansum","year":"2021","unstructured":"Hansum, T. et al. Comedonecrosis Gleason pattern 5 is associated with worse clinical outcome in operated prostate cancer patients. Mod. Pathol. 34, 2064\u20132070 (2021).","journal-title":"Mod. Pathol."},{"key":"64712_CR43","doi-asserted-by":"crossref","first-page":"58","DOI":"10.21147\/j.issn.1000-9604.2016.06.02","volume":"28","author":"N Chen","year":"2016","unstructured":"Chen, N. & Zhou, Q. The evolving Gleason grading system. Chin. J. Cancer Res. 28, 58\u201364 (2016).","journal-title":"Chin. J. Cancer Res."},{"key":"64712_CR44","unstructured":"Angelopoulos, A. N. & Bates, S. A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification. Preprint at https:\/\/arXiv.org\/abs\/2107.07511 (2021)."},{"key":"64712_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-023-43095-4","volume":"15","author":"T Chanda","year":"2024","unstructured":"Chanda, T. et al. Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma. Nat. Commun. 15, 1\u201317 (2024).","journal-title":"Nat. Commun."},{"key":"64712_CR46","doi-asserted-by":"crossref","unstructured":"Hamm, C. A. et al. Interactive explainable deep learning model informs prostate cancer diagnosis at MRI. Radiology, e222276 (2023).","DOI":"10.1148\/radiol.222276"},{"key":"64712_CR47","unstructured":"Iczkowski, K. A. Gleason grading. https:\/\/www.pathologyoutlines.com\/topic\/prostategrading.html (2021)."},{"key":"64712_CR48","unstructured":"TissueArray.Com LLC. Tissue Microarray FAQs. http:\/\/www.tissuearray.com\/FAQs (2019)."},{"key":"64712_CR49","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2017.14","volume":"4","author":"Q Zhong","year":"2017","unstructured":"Zhong, Q. et al. A curated collection of tissue microarray images and clinical outcome data of prostate cancer patients. Sci. Data 4, 170014 (2017).","journal-title":"Sci. Data"},{"key":"64712_CR50","doi-asserted-by":"publisher","unstructured":"Arvaniti, E. et al. Replication Data for: Automated Gleason grading of prostate cancer tissue microarrays via deep learning. Harvard Dataverse https:\/\/doi.org\/10.7910\/DVN\/OCYCMP (2018).","DOI":"10.7910\/DVN\/OCYCMP"},{"key":"64712_CR51","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1109\/TMI.2004.828354","volume":"23","author":"SK Warfield","year":"2004","unstructured":"Warfield, S. K., Zou, K. H. & Wells, W. M. Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans. Med. Imaging 23, 903\u2013921 (2004).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"64712_CR52","unstructured":"Plainsight Technologies Inc. Modern Computer Vision Infrastructure. https:\/\/plainsight.ai (2023)."},{"key":"64712_CR53","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee, F., Jaeger, P. F., Kohl, S. A. A., Petersen, J. & Maier-Hein, K. H. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18, 203\u2013211 (2021).","journal-title":"Nat. Methods"},{"key":"64712_CR54","doi-asserted-by":"crossref","unstructured":"Deng, J. et al. ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition 248\u2013255 (2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"64712_CR55","first-page":"6105","volume":"97","author":"M Tan","year":"2019","unstructured":"Tan, M. & Le, Q. V. EfficientNet: Rethinking model scaling for convolutional Neural Networks. Int. Conf. Mach. Learn. 97, 6105\u20136114 (2019).","journal-title":"Int. Conf. Mach. Learn."},{"key":"64712_CR56","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"NA 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":"64712_CR57","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N. & Ahmadi, S.-A. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. 2016 Fourth International Conference on 3D Vision (3DV) 565\u2013571 (2016).","DOI":"10.1109\/3DV.2016.79"},{"key":"64712_CR58","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T. & Koyama, M. Optuna: A Next-generation Hyperparameter Optimization Framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2623\u20132631 (2019).","DOI":"10.1145\/3292500.3330701"},{"key":"64712_CR59","unstructured":"Loshchilov, I. & Hutter, F. Decoupled Weight Decay Regularization. Preprint at https:\/\/arXiv.org\/abs\/1711.05101 (2019)."},{"key":"64712_CR60","doi-asserted-by":"publisher","first-page":"101544","DOI":"10.1016\/j.media.2019.101544","volume":"58","author":"D Tellez","year":"2019","unstructured":"Tellez, D. et al. Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology. Med. Image Anal. 58, 101544 (2019).","journal-title":"Med. Image Anal."},{"key":"64712_CR61","unstructured":"Cardoso, M. J. et al. MONAI: An open-source framework for deep learning in healthcare. Preprint at https:\/\/arXiv.org\/abs\/2211.02701 (2022)."},{"key":"64712_CR62","doi-asserted-by":"crossref","unstructured":"Seabold, S. & Perktold, J. Statsmodels: Econometric and statistical modeling with Python. Proceedings of the 9th Python in Science Conference 57\u201361 (2010).","DOI":"10.25080\/Majora-92bf1922-011"},{"key":"64712_CR63","doi-asserted-by":"publisher","unstructured":"Laiouar-Pedari, S. et al. Pathologist-like explainable AI for interpretable Gleason grading in prostate cancer. Figshare https:\/\/doi.org\/10.6084\/m9.figshare.27301845 (2025).","DOI":"10.6084\/m9.figshare.27301845"},{"key":"64712_CR64","unstructured":"Brinker, T. J. GleasonXAI_Figure_1. BioRender, https:\/\/BioRender.com\/f50n482 (2025)."}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-025-64712-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-025-64712-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-025-64712-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T22:02:20Z","timestamp":1759960940000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-025-64712-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,8]]},"references-count":64,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["64712"],"URL":"https:\/\/doi.org\/10.1038\/s41467-025-64712-4","relation":{},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,8]]},"assertion":[{"value":"3 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"TJB owns a company that develops mobile apps (Smart Health Heidelberg GmbH, Heidelberg, Germany).\u00a0TJB received honoraria from Novartis, Roche and HEINE Optotechnik. JNK declares consulting services for Panakeia, AstraZeneca, MultiplexDx, Mindpeak, Owkin, DoMore Diagnostics, and Bioptimus. Furthermore, he holds shares in StratifAI, Synagen, Tremont AI, and Ignition Labs, has received an institutional research grant from GSK, and has received honoraria from AstraZeneca, Bayer, Daiichi Sankyo, Eisai, Janssen, Merck, MSD, BMS, Roche, Pfizer, and Fresenius. YT declares consulting services for Indica Labs, AstraZeneca, MSD, Pfizer; royalties not related to this study (Indica Labs). CMS is a cofounder and shareholder of Vicinity Bio GmbH, and is a scientific advisor to and has received research funding from Enable Medicine Inc., all outside the current work. HM declares consulting services for PathXL, Invicro, and PathAI, outside of this work. NJR discloses an advisory board function for AbbVie AG, and receipt of a travel grant from Roche Diagnostics, both outside of the scope of the current work. IK has received honoraria from AstraZeneca and Menarini Stemline, as well as gifts\/financial advantages from Roche (conference invitations). NTG received an institutional research grant from Janssen\/Johnson & Johnson and declares consulting services for\/honoraria from AstraZeneca, Janssen, Merck, BMS, Daiichi Sankyo, and Bayer. No other conflicts of interest are declared by any of the authors.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"8959"}}