{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T04:29:43Z","timestamp":1786768183692,"version":"build-2736575974"},"reference-count":36,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Histopathology foundation models (FMs) have become widely used as patch-level feature extractors in computational pathology (CPath), where domain shift is a central challenge, yet their generalization ability across acquisition centers and scanning platforms remains insufficiently studied. In this work, we evaluate the domain generalization of ten state-of-the-art FMs on two multi-source datasets with different supervision settings: SemiCOL, a colorectal cancer cohort of 499 whole-slide images (WSIs) for weakly labeled slide-level binary tumor classification, and BEETLE, a breast cancer cohort of 583 WSIs for patch-level four-class tissue classification. In an ablation-style setting, FMs are used as patch-level feature extractors, with patch embeddings mean-pooled into slide-level representations for SemiCOL, and a lightweight multi-layer perceptron trained for slide-level and patch-level classification on SemiCOL and BEETLE, respectively. To test FM domain generalization, we use three evaluation protocols: a Baseline source-mixed 5-fold cross-validation (CV) and two leave-source-out CV settings that assess cross-center and cross-scanner performance. On SemiCOL, all FMs achieve near-saturated performance, indicating stable performance under acquisition-source domain shift for slide-level Tumor vs. Benign classification. In contrast, BEETLE reveals clear generalization gaps, with scanner-induced domain shift more challenging than center-induced domain shift, and class-wise results showing that performance losses concentrate in epithelial discrimination. Overall, Virchow2 shows the strongest robustness across all evaluated protocols. These findings show that standard source-mixed CV can overestimate domain generalization across centers and scanners, and that FM choice matters in multi-source cohorts, especially for more challenging CPath tasks, where cross-domain failures are more visible.<\/jats:p>","DOI":"10.3390\/jimaging12080381","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T17:01:35Z","timestamp":1786640495000},"page":"381","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Domain Generalization of Histopathology Foundation Models in Multicenter, Multi-Scanner Cohorts: A Comparative Benchmark"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3879-876X","authenticated-orcid":false,"given":"Hafsa","family":"Akebli","sequence":"first","affiliation":[{"name":"Department of Mathematics, Computer Science and Physics, University of Udine, 33100 Udine, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0144-3802","authenticated-orcid":false,"given":"Vincenzo","family":"Della Mea","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Computer Science and Physics, University of Udine, 33100 Udine, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"100357","DOI":"10.1016\/j.jpi.2023.100357","article-title":"Computational pathology: A survey review and the way forward","volume":"15","author":"Hosseini","year":"2024","journal-title":"J. Pathol. Inform."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.intonc.2025.03.004","article-title":"Computational pathology: A comprehensive review of recent developments in digital and intelligent pathology","volume":"1","author":"Huang","year":"2025","journal-title":"Intell. Oncol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"102996","DOI":"10.1016\/j.media.2023.102996","article-title":"On the challenges and perspectives of foundation models for medical image analysis","volume":"91","author":"Zhang","year":"2024","journal-title":"Med. Image Anal."},{"key":"ref_4","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., and El-Nouby, A. (2024). DINOv2: Learning Robust Visual Features without Supervision. arXiv."},{"key":"ref_5","unstructured":"Zhou, J., Wei, C., Wang, H., Shen, W., Xie, C., Yuille, A., and Kong, T. (2022). iBOT: Image BERT Pre-Training with Online Tokenizer. arXiv."},{"key":"ref_6","unstructured":"Zimmermann, E., Vorontsov, E., Viret, J., Casson, A., Zelechowski, M., Shaikovski, G., Tenenholtz, N., Hall, J., Fuchs, T., and Fusi, N. (2024). Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology. arXiv."},{"key":"ref_7","first-page":"A68","article-title":"The Cancer Genome Atlas (TCGA) an immeasurable source of knowledge","volume":"19","author":"Tomczak","year":"2015","journal-title":"Contemp. Oncol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1038\/s41586-024-07441-w","article-title":"A whole-slide foundation model for digital pathology from real-world data","volume":"630","author":"Xu","year":"2024","journal-title":"Nature"},{"key":"ref_9","unstructured":"Saillard, C., Jenatton, R., Llinares-L\u00f3pez, F., Mariet, Z., Cahan\u00e9, D., Durand, E., and Vert, J.P. (2025, December 05). H-Optimus-0. Available online: https:\/\/github.com\/bioptimus\/releases\/tree\/main\/models\/h-optimus\/v0."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1038\/s41698-025-00799-8","article-title":"A comprehensive evaluation of histopathology foundation models for ovarian cancer subtype classification","volume":"9","author":"Breen","year":"2025","journal-title":"NPJ Precis. Oncol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"102680","DOI":"10.1016\/j.compmedimag.2025.102680","article-title":"Benchmarking pathology foundation models for predicting microsatellite instability in colorectal cancer histopathology","volume":"127","author":"Bilal","year":"2026","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Akebli, H., Mea, V.D., and Roitero, K. (2025, January 18\u201321). Benchmarking Feature Extractors for Prostate Cancer Detection Using Graph Attention Networks: A Focus on Foundation Models. Proceedings of the 2025 IEEE 13th International Conference on Healthcare Informatics (ICHI), Rende, Italy.","DOI":"10.1109\/ICHI64645.2025.00099"},{"key":"ref_13","unstructured":"Ali, S., Hogg, D.C., and Peckham, M. (2026). Benchmarking Histopathology Foundation Models in a Multi-center Dataset for Skin Cancer Subtyping. Proceedings of the Medical Image Understanding and Analysis, Springer."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3640","DOI":"10.1038\/s41467-025-58796-1","article-title":"A clinical benchmark of public self-supervised pathology foundation models","volume":"16","author":"Campanella","year":"2025","journal-title":"Nat. Commun."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/s41551-025-01516-3","article-title":"Benchmarking foundation models as feature extractors for weakly supervised computational pathology","volume":"10","author":"Neidlinger","year":"2026","journal-title":"Nat. Biomed. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"110031","DOI":"10.1016\/j.compbiomed.2025.110031","article-title":"Benchmarking pathology foundation models: Adaptation strategies and scenarios","volume":"190","author":"Lee","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1109\/JBHI.2020.3032060","article-title":"Measuring Domain Shift for Deep Learning in Histopathology","volume":"25","author":"Stacke","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3724391","article-title":"Domain Generalization in Computational Pathology: Survey and Guidelines","volume":"57","author":"Jahanifar","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wilm, F., Fragoso, M., Bertram, C.A., Stathonikos, N., \u00d6ttl, M., Qiu, J., Klopfleisch, R., Maier, A., Aubreville, M., and Breininger, K. (2023, January 18\u201321). Mind the Gap: Scanner-Induced Domain Shifts Pose Challenges for Representation Learning in Histopathology. Proceedings of the 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), Cartagena, Colombia.","DOI":"10.1109\/ISBI53787.2023.10230458"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"11485","DOI":"10.1038\/s41467-025-66300-y","article-title":"Knowledge-guided adaptation of pathology foundation models effectively improves cross-domain generalization and demographic fairness","volume":"16","author":"Huang","year":"2025","journal-title":"Nat. Commun."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Jeong, W.K., Kim, H.J., Deng, Z., Shen, Y., Aviles-Rivero, A.I., and Zhang, S. (2026). Pathology Foundation Models Are Scanner Sensitive: Benchmark and Mitigation with Contrastive ScanGen Loss. Proceedings of the Foundation Models for General Medical AI, Springer.","DOI":"10.1007\/978-3-032-07845-2"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"100327","DOI":"10.1016\/j.modpat.2023.100327","article-title":"Artificial Intelligence-Based Tool for Tumor Detection and Quantitative Tissue Analysis in Colorectal Specimens","volume":"36","author":"Griem","year":"2023","journal-title":"Mod. Pathol."},{"key":"ref_23","unstructured":"Lems, C., Tessier, L., Bokhorst, J.M., van Rijthoven, M., Aswolinskiy, W., Pozzi, M., Klubickova, N., Dintzis, S., Campora, M., and Balkenhol, M. (2025). A Multicentric Dataset for Training and Benchmarking Breast Cancer Segmentation in H&E Slides. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kang, M., Song, H., Park, S., Yoo, D., and Pereira, S. (2023, January 17\u201324). Benchmarking Self-Supervised Learning on Diverse Pathology Datasets. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00326"},{"key":"ref_25","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., and Deny, S. (2021, January 18\u201324). Barlow Twins: Self-Supervised Learning via Redundancy Reduction. Proceedings of the 38th International Conference on Machine Learning, Virtual."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"102559","DOI":"10.1016\/j.media.2022.102559","article-title":"Transformer-based unsupervised contrastive learning for histopathological image classification","volume":"81","author":"Wang","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 11\u201317). Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Los Alamitos, CA, USA.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., and He, K. (2021, January 11\u201317). An Empirical Study of Training Self-Supervised Vision Transformers. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Los Alamitos, CA, USA.","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1038\/s41591-024-02856-4","article-title":"A visual-language foundation model for computational pathology","volume":"30","author":"Lu","year":"2024","journal-title":"Nat. Med."},{"key":"ref_30","unstructured":"Filiot, A., Jacob, P., Kain, A.M., and Saillard, C. (2024). Phikon-v2, A large and public feature extractor for biomarker prediction. arXiv."},{"key":"ref_31","unstructured":"Nechaev, D., Pchelnikov, A., and Ivanova, E. (2024). Hibou: A Family of Foundational Vision Transformers for Pathology. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a General-Purpose Foundation Model for Computational Pathology","volume":"30","author":"Chen","year":"2024","journal-title":"Nat. Med."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"123893","DOI":"10.1016\/j.eswa.2024.123893","article-title":"Exploring Multiple Instance Learning (MIL): A brief survey","volume":"250","author":"Waqas","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"e220232","DOI":"10.1148\/ryai.220232","article-title":"A Guide to Cross-Validation for Artificial Intelligence in Medical Imaging","volume":"5","author":"Bradshaw","year":"2023","journal-title":"Radiol. Artif. Intell."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Leinonen, T., Wong, D., Vasankari, A., Wahab, A., Nadarajah, R., Kaisti, M., and Airola, A. (2024). Empirical investigation of multi-source cross-validation in clinical ECG classification. Comput. Biol. Med., 183.","DOI":"10.1016\/j.compbiomed.2024.109271"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"861","DOI":"10.21105\/joss.00861","article-title":"UMAP: Uniform Manifold Approximation and Projection","volume":"3","author":"McInnes","year":"2018","journal-title":"J. Open Source Softw."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/8\/381\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T04:19:18Z","timestamp":1786767558000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/8\/381"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":36,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["jimaging12080381"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12080381","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]}}}