{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T16:05:11Z","timestamp":1781625911937,"version":"3.54.5"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100010767","name":"Innovative Medicines Initiative","doi-asserted-by":"publisher","award":["945358"],"award-info":[{"award-number":["945358"]}],"id":[{"id":"10.13039\/501100010767","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010767","name":"Innovative Medicines Initiative","doi-asserted-by":"publisher","award":["945358"],"award-info":[{"award-number":["945358"]}],"id":[{"id":"10.13039\/501100010767","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010767","name":"Innovative Medicines Initiative","doi-asserted-by":"publisher","award":["945358"],"award-info":[{"award-number":["945358"]}],"id":[{"id":"10.13039\/501100010767","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Accurate tumor detection in digital pathology whole-slide images (WSIs) is crucial for cancer diagnosis and treatment planning. Multiple Instance Learning (MIL) has emerged as a widely used approach for weakly-supervised tumor detection with large-scale data without the need for manual annotations. However, traditional MIL methods often depend on classification tasks that require tumor-free cases as negative examples, which are challenging to obtain in real-world clinical workflows, especially for surgical resection specimens. We address this limitation by reformulating tumor detection as a\n                    <jats:italic>regression<\/jats:italic>\n                    task, estimating tumor percentages from WSIs, a clinically available target across multiple cancer types. In this paper, we provide an analysis of the proposed weakly-supervised regression framework by applying it to multiple organs, specimen types and clinical scenarios. We characterize the robustness of our framework to tumor percentage as a noisy regression target, and introduce a novel concept of\n                    <jats:italic>\u201camplification technique\u201d<\/jats:italic>\n                    to improve tumor detection sensitivity when learning from small tumor regions. Finally, we provide interpretable insights into the model\u2019s predictions by analyzing visual attention and logit maps. Our code is available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/imi-bigpicture\/tumor-percentage-mil-regression\" ext-link-type=\"uri\">https:\/\/github.com\/imi-bigpicture\/tumor-percentage-mil-regression<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1038\/s41598-025-27158-8","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T14:16:44Z","timestamp":1764857804000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Weakly supervised regression enables interpretable tumor detection in whole-slide histopathology without negative cases"],"prefix":"10.1038","volume":"15","author":[{"given":"Marina","family":"D\u2019Amato","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeroen","family":"van der Laak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Ciompi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"key":"27158_CR1","unstructured":"Aswolinskiy, W., 2023. pathology-whole-slide-packer. https:\/\/github.com\/DIAGNijmegen\/pathology-whole-slide-packer."},{"key":"27158_CR2","doi-asserted-by":"publisher","unstructured":"Aswolinskiy, W., et al. Neural image compression for non-small cell lung cancer subtype classification in HE stained whole-slide images, in\u00a0Medical Imaging 2021: Digital Pathology, SPIE. 1 \u2013 7. (2021)\u00a0https:\/\/doi.org\/10.1117\/12.2581943.","DOI":"10.1117\/12.2581943"},{"key":"27158_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.anndiagpath.2020.151490","volume":"46","author":"MCA Balkenhol","year":"2020","unstructured":"Balkenhol, M. C. A. et al. Histological subtypes in triple negative breast cancer are associated with specific information on survival. Annals of Diagnostic Pathology 46, 151490. https:\/\/doi.org\/10.1016\/j.anndiagpath.2020.151490 (2020).","journal-title":"Annals of Diagnostic Pathology"},{"key":"27158_CR4","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.8242","volume":"7","author":"P B\u00e1ndi","year":"2019","unstructured":"B\u00e1ndi, P., Balkenhol, M., van Ginneken, B., van der Laak, J. & Litjens, G. Resolution-agnostic tissue segmentation in whole-slide histopathology images with convolutional neural networks. PeerJ 7, e8242. https:\/\/doi.org\/10.7717\/peerj.8242 (2019).","journal-title":"PeerJ"},{"key":"27158_CR5","doi-asserted-by":"publisher","first-page":"8398","DOI":"10.1038\/s41598-023-35491-z","volume":"13","author":"J Bokhorst","year":"2023","unstructured":"Bokhorst, J. et al. Deep learning for multi-class semantic segmentation enables colorectal cancer detection and classification in digital pathology images 13, 8398. https:\/\/doi.org\/10.1038\/s41598-023-35491-z (2023).","journal-title":"Deep learning for multi-class semantic segmentation enables colorectal cancer detection and classification in digital pathology images"},{"key":"27158_CR6","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1038\/s41591-019-0508-1","volume":"25","author":"G Campanella","year":"2019","unstructured":"Campanella, G. et al. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nature Medicine 25, 1301\u20131309. https:\/\/doi.org\/10.1038\/s41591-019-0508-1 (2019).","journal-title":"Nature Medicine"},{"key":"27158_CR7","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/j.patcog.2017.10.009","volume":"77","author":"MA Carbonneau","year":"2018","unstructured":"Carbonneau, M. A., Cheplygina, V., Granger, E. & Gagnon, G. Multiple Instance Learning: A Survey of Problem Characteristics and Applications. Pattern Recognition 77, 329\u2013353. https:\/\/doi.org\/10.1016\/j.patcog.2017.10.009 (2018).","journal-title":"Pattern Recognition"},{"key":"27158_CR8","doi-asserted-by":"crossref","unstructured":"Chen, R.J., et al. Scaling vision transformers to gigapixel images via hierarchical self-supervised learning, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 16144\u201316155 (2022).","DOI":"10.1109\/CVPR52688.2022.01567"},{"key":"27158_CR9","doi-asserted-by":"publisher","unstructured":"Chikontwe, P., Kim, M., Nam, S.J., Go, H. & Park, S.H. Multiple instance learning with center embeddings for histopathology classification, in International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. 519\u2013528 (2020). https:\/\/doi.org\/10.1007\/978-3-030-59722-1_50.","DOI":"10.1007\/978-3-030-59722-1_50"},{"key":"27158_CR10","doi-asserted-by":"publisher","unstructured":"Contreras, N.S.L., et al. Benchmarking hierarchical image pyramid transformer for the classification of colon biopsies and polyps histopathology images, 1\u20134 (2024). https:\/\/doi.org\/10.1109\/isbi56570.2024.10635841.","DOI":"10.1109\/isbi56570.2024.10635841"},{"key":"27158_CR11","doi-asserted-by":"publisher","unstructured":"Cruz-Roa, A., et al. Automatic detection of invasive ductal carcinoma in whole slide images with convolutional neural networks, in Medical Imaging 2014: Digital Pathology, SPIE. 904103 (2014).\u00a0https:\/\/doi.org\/10.1117\/12.2043872.","DOI":"10.1117\/12.2043872"},{"key":"27158_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102881","volume":"88","author":"S Dooper","year":"2023","unstructured":"Dooper, S. et al. Gigapixel end-to-end training using streaming and attention. Medical Image Analysis 88, 102881. https:\/\/doi.org\/10.1016\/j.media.2023.102881 (2023).","journal-title":"Medical Image Analysis"},{"key":"27158_CR13","doi-asserted-by":"publisher","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. https:\/\/doi.org\/10.1001\/jama.2017.14585 (2017).","DOI":"10.1001\/jama.2017.14585"},{"key":"27158_CR14","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1038\/s41467-024-45589-1","volume":"15","author":"OSM El Nahhas","year":"2024","unstructured":"El Nahhas, O. S. M. et al. Regression-based Deep-Learning predicts molecular biomarkers from pathology slides. Nature Communications 15, 1253. https:\/\/doi.org\/10.1038\/s41467-024-45589-1 (2024).","journal-title":"Nature Communications"},{"key":"27158_CR15","doi-asserted-by":"publisher","first-page":"4323","DOI":"10.3390\/electronics12204323","volume":"12","author":"S Fatima","year":"2023","unstructured":"Fatima, S., Ali, S. & Kim, H. C. A Comprehensive Review on Multiple Instance Learning. Electronics 12, 4323. https:\/\/doi.org\/10.3390\/electronics12204323 (2023).","journal-title":"Electronics"},{"key":"27158_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103063","volume":"93","author":"DJ Geijs","year":"2024","unstructured":"Geijs, D. J. et al. Detection and subtyping of basal cell carcinoma in whole-slide histopathology using weakly-supervised learning. Medical Image Analysis 93, 103063. https:\/\/doi.org\/10.1016\/j.media.2023.103063 (2024).","journal-title":"Medical Image Analysis"},{"key":"27158_CR17","doi-asserted-by":"publisher","unstructured":"Graziani, M., et al. Attention-based Interpretable Regression of Gene Expression in Histology, Interpretability of Machine Intelligence in Medical Image Computing. 44\u201360 (2022)\u00a0https:\/\/doi.org\/10.1007\/978-3-031-17976-1_5.","DOI":"10.1007\/978-3-031-17976-1_5"},{"key":"27158_CR18","unstructured":"Grisi, C. hs2p. https:\/\/github.com\/clemsgrs\/hs2p. (2023)."},{"key":"27158_CR19","doi-asserted-by":"publisher","first-page":"14043","DOI":"10.1038\/s41598-019-50313-x","volume":"9","author":"M Halicek","year":"2019","unstructured":"Halicek, M. et al. Head and Neck Cancer Detection in Digitized Whole-Slide Histology Using Convolutional Neural Networks. Scientific Reports 9, 14043. https:\/\/doi.org\/10.1038\/s41598-019-50313-x (2019).","journal-title":"Scientific Reports"},{"key":"27158_CR20","unstructured":"Ilse, M., Tomczak, J.M. & Welling, M. Attention-based Deep Multiple Instance Learning, in: Proceedings of the 35th International Conference on Machine Learning, 2127\u20132136 (2018)."},{"key":"27158_CR21","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1016\/0895-4356(94)90193-7","volume":"47","author":"N Krieger","year":"1994","unstructured":"Krieger, N., Hiatt, R. A., Sagebiel, R. W., Clark, W. H. & Mihm, M. C. Inter-observer variability among pathologists\u2019 evaluation of malignant melanoma: Effects upon an analytic study. Journal of Clinical Epidemiology 47, 897\u2013902. https:\/\/doi.org\/10.1016\/0895-4356(94)90193-7 (1994).","journal-title":"Journal of Clinical Epidemiology"},{"key":"27158_CR22","doi-asserted-by":"publisher","unstructured":"Lerousseau, M., et al. Weakly supervised pan-cancer segmentation tool, Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021. https:\/\/doi.org\/10.1007\/978-3-030-87237-3_24. (2021).","DOI":"10.1007\/978-3-030-87237-3_24"},{"key":"27158_CR23","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. Nature Biomedical Engineering 5, 555\u2013570. https:\/\/doi.org\/10.1038\/s41551-020-00682-w (2021).","journal-title":"Nature Biomedical Engineering"},{"key":"27158_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106856","volume":"159","author":"JM Marr\u00f3n-Esquivel","year":"2023","unstructured":"Marr\u00f3n-Esquivel, J. M., Duran-Lopez, L., Linares-Barranco, A. & Dominguez-Morales, J. P. A comparative study of the inter-observer variability on Gleason grading against Deep Learning-based approaches for prostate cancer. Computers in Biology and Medicine 159, 106856. https:\/\/doi.org\/10.1016\/j.compbiomed.2023.106856 (2023).","journal-title":"Computers in Biology and Medicine"},{"key":"27158_CR25","doi-asserted-by":"publisher","unstructured":"Pinckaers, H., Bulten, W. & Litjens, G. High resolution whole prostate biopsy classification using streaming stochastic gradient descent, in Medical Imaging 2019: Digital Pathology. https:\/\/doi.org\/10.1117\/12.2512817. (2019).","DOI":"10.1117\/12.2512817"},{"key":"27158_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101890","volume":"68","author":"M van Rijthoven","year":"2021","unstructured":"van Rijthoven, M., Balkenhol, M., Silina, K., van der Laak, J. & Ciompi, F. Hooknet: Multi-resolution convolutional neural networks for semantic segmentation in histopathology whole-slide images. Medical Image Analysis 68, 101890. https:\/\/doi.org\/10.1016\/j.media.2020.101890 (2021).","journal-title":"Medical Image Analysis"},{"key":"27158_CR27","doi-asserted-by":"publisher","unstructured":"Schirris, Y. et al. WeakSTIL: Weak whole-slide image level stromal tumor infiltrating lymphocyte scores are all you need. SPIE Medical Imaging 2022, https:\/\/doi.org\/10.1117\/12.2611528 (2022).","DOI":"10.1117\/12.2611528"},{"key":"27158_CR28","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1109\/TPAMI.2019.2936841","volume":"43","author":"D Tellez","year":"2021","unstructured":"Tellez, D., Litjens, G., van der Laak, J. & Ciompi, F. Neural image compression for gigapixel histopathology image analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 43, 567\u2013578. https:\/\/doi.org\/10.1109\/TPAMI.2019.2936841 (2021).","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"27158_CR29","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1038\/s41591-021-01343-4","volume":"27","author":"J van der Laak","year":"2021","unstructured":"van der Laak, J., Litjens, G. & Ciompi, F. Deep learning in histopathology: The path to the clinic. Nature Medicine 27, 775\u2013784. https:\/\/doi.org\/10.1038\/s41591-021-01343-4 (2021).","journal-title":"Nature Medicine"},{"key":"27158_CR30","doi-asserted-by":"publisher","first-page":"3950","DOI":"10.1109\/TCYB.2019.2935141","volume":"50","author":"X Wang","year":"2020","unstructured":"Wang, X. et al. Weakly Supervised Deep Learning for Whole Slide Lung Cancer Image Analysis. IEEE transactions on cybernetics 50, 3950\u20133962. https:\/\/doi.org\/10.1109\/TCYB.2019.2935141 (2020).","journal-title":"IEEE transactions on cybernetics"},{"key":"27158_CR31","doi-asserted-by":"publisher","unstructured":"Weitz, P., Wang, Y., Hartman, J. & Rantalainen, M. An investigation of attention mechanisms in histopathology whole-slide-image analysis for regression objectives, in 2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), 611\u2013619 (IEEE, Montreal, BC, Canada, 2021).\u00a0https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00074.","DOI":"10.1109\/ICCVW54120.2021.00074"},{"key":"27158_CR32","doi-asserted-by":"publisher","unstructured":"Xia, T., Kumar, A., Feng, D. & Kim, J. Patch-level Tumor Classification in Digital Histopathology Images with Domain Adapted Deep Learning, in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC),\u00a0644\u2013647 (IEEE, Honolulu,\u00a0HI, 2018). https:\/\/doi.org\/10.1109\/EMBC.2018.8512353.","DOI":"10.1109\/EMBC.2018.8512353"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27158-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27158-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27158-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:01:27Z","timestamp":1781622087000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27158-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["27158"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-27158-8","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]},"assertion":[{"value":"10 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Jeroen van der Laak is a member of the advisory boards of Philips, the Netherlands and ContextVision, Sweden, and received research funding from Philips, the Netherlands, ContextVision, Sweden, and Sectra, Sweden. He is chief scientific officer and a shareholder of Aiosyn BV, the Netherlands. Francesco Ciompi is shareholder of Aiosyn BV, the Netherlands. All the remaining authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"43145"}}