{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T15:32:08Z","timestamp":1773243128730,"version":"3.50.1"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s10044-026-01642-x","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:54:46Z","timestamp":1773172486000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Context-aware feature refinement with orthogonal regularization for whole slide image classification"],"prefix":"10.1007","volume":"29","author":[{"given":"Shicheng","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Zefeng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jikai","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Boyuan","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Jiayun","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"1642_CR1","doi-asserted-by":"publisher","first-page":"78409","DOI":"10.1109\/ACCESS.2024.3403538","volume":"12","author":"D Barbosa","year":"2024","unstructured":"Barbosa D, Ferreira M, Junior GB, Salgado M, Cunha A (2024) Multiple instance learning in medical images: a systematic review. IEEE Access 12:78409\u201378422. https:\/\/doi.org\/10.1109\/ACCESS.2024.3403538. (Accessed 2026\u201301-08)","journal-title":"IEEE Access"},{"key":"1642_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.prp.2025.156006","volume":"271","author":"J Yu","year":"2025","unstructured":"Yu J, Chen H, Hu L, Wu B, Zhou S, Zhu J, Jiang Y, Han S, Wang Z (2025) Exploring multi-instance learning in whole slide imaging: Current and future perspectives. Pathol Res Pract 271:156006. https:\/\/doi.org\/10.1016\/j.prp.2025.156006","journal-title":"Pathol Res Pract"},{"key":"1642_CR3","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, Van Der Laak JAWM, Van Ginneken B, S\u00e1nchez CI (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60\u201388. https:\/\/doi.org\/10.1016\/j.media.2017.07.005. (Accessed 2026\u201301-08)","journal-title":"Med Image Anal"},{"key":"1642_CR4","doi-asserted-by":"publisher","first-page":"1070072","DOI":"10.3389\/fmed.2022.1070072","volume":"9","author":"H Zhang","year":"2023","unstructured":"Zhang H, He Y, Wu X, Huang P, Qin W, Wang F, Ye J, Huang X, Liao Y, Chen H, Guo L, Shi X, Luo L (2023) PathNarratives: data annotation for pathological human-AI collaborative. Front Med Diagnos 9:1070072. https:\/\/doi.org\/10.3389\/fmed.2022.1070072. (Accessed 2026\u201301-08)","journal-title":"Front Med Diagnos"},{"key":"1642_CR5","doi-asserted-by":"publisher","unstructured":"Pantanowitz L, Farahani N, Parwani A. Whole slide imaging in pathology: advantages, limitations, and emerging perspectives, 23 https:\/\/doi.org\/10.2147\/PLMI.S59826. Accessed 2026\u201301-08","DOI":"10.2147\/PLMI.S59826"},{"key":"1642_CR6","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/j.compmedimag.2014.11.010","volume":"42","author":"M Kandemir","year":"2015","unstructured":"Kandemir M, Hamprecht FA (2015) Computer-aided diagnosis from weak supervision: a benchmarking study. Comput Med Imaging Graph 42:44\u201350. https:\/\/doi.org\/10.1016\/j.compmedimag.2014.11.010. (Accessed 2026\u201301-08)","journal-title":"Comput Med Imaging Graph"},{"key":"1642_CR7","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1512.03385.  Accessed 2026\u201301-08","DOI":"10.48550\/arXiv.1512.03385"},{"key":"1642_CR8","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: transformers for image recognition at scale. arxiv:2010.11929"},{"key":"1642_CR9","unstructured":"Zhu L, Liao B, Zhang Q, Wang X, Liu W, Wang X (2024) Vision mamba: efficient visual representation learning with bidirectional state space model. arxiv:2401.09417"},{"key":"1642_CR10","unstructured":"Liu Y, Tian Y, Zhao Y, Yu H, Xie L, Wang Y, Ye Q, Jiao J, Liu Y (2024) VMamba: visual state space model. arxiv:2401.10166"},{"issue":"12","key":"1642_CR11","doi-asserted-by":"publisher","first-page":"8515","DOI":"10.1016\/j.asr.2025.04.009","volume":"75","author":"H Song","year":"2025","unstructured":"Song H, Xie J, Duan Y, Xie X, Zhou Y, Wang W (2025) CMKD-net: a cross-modal knowledge distillation method for remote sensing image classification. Adv Space Res 75(12):8515\u20138534. https:\/\/doi.org\/10.1016\/j.asr.2025.04.009. (Accessed 2026-02-08)","journal-title":"Adv Space Res"},{"issue":"7","key":"1642_CR12","doi-asserted-by":"publisher","first-page":"1002","DOI":"10.3390\/sym17071002","volume":"17","author":"H Song","year":"2025","unstructured":"Song H, Xie J, Liang L, Su Y, Xiao Y, Zhang X, Ouyang Y, Li X, Chen S, Li Y (2025) Symmetrical learning and transferring: efficient knowledge distillation for remote sensing image classification. Symmetry 17(7):1002. https:\/\/doi.org\/10.3390\/sym17071002. (Accessed 2026-02-08)","journal-title":"Symmetry"},{"issue":"2","key":"1642_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.33166\/AETiC.2025.02.001","volume":"9","author":"H Song","year":"2025","unstructured":"Song H, Xie J, Zhang Y, Zhou Y, Wang W, Duan Y, Xie X (2025) Efficient object detection in remote sensing images using quantitative augmentation and competitive learning. Annals Emerg Technol Comput 9(2):1\u201319. https:\/\/doi.org\/10.33166\/AETiC.2025.02.001. (Accessed 2026\u201302-08)","journal-title":"Annals Emerg Technol Comput"},{"key":"1642_CR14","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. arxiv:2103.14030","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1642_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102559","volume":"81","author":"X Wang","year":"2022","unstructured":"Wang X, Yang S, Zhang J, Wang M, Zhang J, Yang W, Huang J, Han X (2022) Transformer-based unsupervised contrastive learning for histopathological image classification. Med Image Anal 81:102559. https:\/\/doi.org\/10.1016\/j.media.2022.102559. (Accessed 2025\u201311-10)","journal-title":"Med Image Anal"},{"key":"1642_CR16","doi-asserted-by":"publisher","unstructured":"Ilse M, Tomczak JM, Welling M. Attention-based deep multiple instance learning. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1802.04712.  Accessed 2025\u201312-18","DOI":"10.48550\/arXiv.1802.04712"},{"issue":"6","key":"1642_CR17","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","volume":"5","author":"MY Lu","year":"2021","unstructured":"Lu MY, Williamson DFK, Chen TY, Chen RJ, Barbieri M, Mahmood F (2021) Data-efficient and weakly supervised computational pathology on whole-slide images. Nat Biomed Eng 5(6):555\u2013570. https:\/\/doi.org\/10.1038\/s41551-020-00682-w. (Accessed 2025-12-18)","journal-title":"Nat Biomed Eng"},{"key":"1642_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-031-73668-1_8","volume-title":"Computer Vision \u2013 ECCV 2024","author":"Y Zhang","year":"2025","unstructured":"Zhang Y, Li H, Sun Y, Zheng S, Zhu C, Yang L (2025) Attention-challenging multiple instance learning for whole slide image classification. In: Leonardis A, Ricci E, Roth S, Russakovsky O, Sattler T, Varol G (eds) Computer Vision \u2013 ECCV 2024. Lecture Notes in Computer Science. Springer, Berlin, pp 125\u2013143. https:\/\/doi.org\/10.1007\/978-3-031-73668-1_8 (Accessed 2025\u201312-18)"},{"key":"1642_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1007\/978-3-032-04927-8_62","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025","author":"D Reisenb\u00fcchler","year":"2026","unstructured":"Reisenb\u00fcchler D, Deng R, Matek C, Feuerhake F, Merhof D (2026) Top-down attention-based multiple instance learning for whole slide image analysis. In: Gee JC, Alexander DC, Hong J, Iglesias JE, Sudre CH, Venkataraman A, Golland P, Kim JH, Park J (eds) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025. Lecture Notes in Computer Science. Springer, Berlin, pp 651\u2013660. https:\/\/doi.org\/10.1007\/978-3-032-04927-8_62 (Accessed 2026\u201301-08)"},{"key":"1642_CR20","first-page":"2136","volume":"34","author":"Z Shao","year":"2021","unstructured":"Shao Z, Bian H, Chen Y, Wang Y, Zhang J, Ji X, Zhang Y (2021) TransMIL: transformer based correlated multiple instance learning for whole slide image classification. Adv Neural Inf Process Syst 34:2136\u20132147","journal-title":"Adv Neural Inf Process Syst"},{"key":"1642_CR21","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2023","unstructured":"Lin X, Sun S, Huang W, Sheng B, Li P, Feng DD (2023) EAPT: efficient attention pyramid transformer for image processing. IEEE Trans Multimedia 25:50\u201361. https:\/\/doi.org\/10.1109\/TMM.2021.3120873. (Accessed 2026\u201301-09)","journal-title":"IEEE Trans Multimedia"},{"key":"1642_CR22","unstructured":"Hui L, Belkin M, Nakkiran P. Limitations of neural collapse for understanding generalization in deep learning. arXiv Version Number: 1. 10.48550\/ARXIV.2202.08384. arxiv:2202.08384 Accessed 2026\u201301-08"},{"key":"1642_CR23","doi-asserted-by":"crossref","unstructured":"Omathil GG, Sreeja CS. Co adaptation vs signal altering regularization layer in deep learning: A trade off analysis via node redundancy and transfer learning. In: 2025 IEEE 6th india council international subsections conference (INDISCON), pp. 1\u20138. IEEE. https:\/\/doi.org\/10.1109\/INDISCON66021.2025.11252043.https:\/\/ieeexplore.ieee.org\/document\/11252043\/ Accessed 2026-01-08","DOI":"10.1109\/INDISCON66021.2025.11252043"},{"key":"1642_CR24","doi-asserted-by":"crossref","unstructured":"Song H, Tang J, Xiao H, Hu J.: ethinking overfitting of multiple instance learning for whole slide image classification. In: 2023 IEEE international conference on multimedia and expo (ICME), pp. 546\u2013551. IEEE. https:\/\/doi.org\/10.1109\/ICME55011.2023.00100.https:\/\/ieeexplore.ieee.org\/document\/10219719\/ Accessed 2026-01-08","DOI":"10.1109\/ICME55011.2023.00100"},{"key":"1642_CR25","series-title":": Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/978-3-032-04984-1_38","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025","author":"J Lou","year":"2026","unstructured":"Lou J, Pan Q, Yang Q, Ji B (2026) PCR-MIL: Phenotype clustering reinforced multiple instance learning for whole slide image classification. In: Gee JC, Alexander DC, Hong J, Iglesias JE, Sudre CH, Venkataraman A, Golland P, Kim JH, Park J (eds) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025. : Lecture Notes in Computer Science. Springer, Berlin, pp 395\u2013404. https:\/\/doi.org\/10.1007\/978-3-032-04984-1_38 (Accessed 2026-01-08)"},{"issue":"8","key":"1642_CR26","doi-asserted-by":"publisher","first-page":"5717","DOI":"10.1007\/s00371-023-03131-2","volume":"40","author":"X Li","year":"2024","unstructured":"Li X, Yang B, Chen T, Gao Z, Li H (2024) Multiple instance learning-based two-stage metric learning network for whole slide image classification. Vis Comput 40(8):5717\u20135732. https:\/\/doi.org\/10.1007\/s00371-023-03131-2. (Accessed 2026-01-09)","journal-title":"Vis Comput"},{"key":"1642_CR27","doi-asserted-by":"crossref","unstructured":"Li B, Li Y, Eliceiri KW. Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14313\u201314323. IEEE. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01409.https:\/\/ieeexplore.ieee.org\/document\/9578683\/ Accessed 2025-12-18","DOI":"10.1109\/CVPR46437.2021.01409"},{"key":"1642_CR28","doi-asserted-by":"publisher","unstructured":"Kim J, Wong B, Fu H, Qui\u00f1ones WR, Ko Y, Yi MY. MicroMIL: Graph-Based Multiple Instance Learning for Context-Aware Diagnosis with Microscopic Images. arXiv Version Number: 4. https:\/\/doi.org\/10.48550\/ARXIV.2407.21604.  Accessed 2026\u201301-08","DOI":"10.48550\/ARXIV.2407.21604"},{"key":"1642_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2025.108966","volume":"271","author":"Y Chen","year":"2025","unstructured":"Chen Y, Li J, Zhu L, Xu Y, Guan T, Shi H, He Y, Han A (2025) Dynamic hypergraph representation for bone metastasis analysis. Comput Methods Programs Biomed 271:108966. https:\/\/doi.org\/10.1016\/j.cmpb.2025.108966. (Accessed 2026\u201301-08)","journal-title":"Comput Methods Programs Biomed"},{"key":"1642_CR30","unstructured":"Zhang Y, Zhou Z, Liu W, Zhang M. Rethinking multi-instance learning through graph-driven fusion: A dual-path approach to adaptive representation"},{"key":"1642_CR31","doi-asserted-by":"crossref","unstructured":"Ngo BH, Do-Tran N-T, Nguyen T-N, Jeon H-G, Choi TJ (2024) Learning cnn on vit: A hybrid model to explicitly class-specific boundaries for domain adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 28545\u201328554","DOI":"10.1109\/CVPR52733.2024.02697"},{"key":"1642_CR32","unstructured":"Ngo BH, Bui DC, Do-Tran N-T, Choi TJ (2024) HiGDA: hierarchical graph of nodes to learn local-to-global topology for semi-supervised domain adaptation. arxiv:2412.11819"},{"key":"1642_CR33","doi-asserted-by":"publisher","unstructured":"Hu J, Shen L, Albanie S, Sun G, Wu E. Squeeze-and-Excitation Networks. arXiv Version Number: 4. https:\/\/doi.org\/10.48550\/ARXIV.1709.01507.  Accessed 2026\u201301-08","DOI":"10.48550\/ARXIV.1709.01507"},{"key":"1642_CR34","doi-asserted-by":"publisher","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS. CBAM: convolutional block attention module. arXiv Version Number: 2. https:\/\/doi.org\/10.48550\/ARXIV.1807.06521.  Accessed 2026\u201301-08","DOI":"10.48550\/ARXIV.1807.06521"},{"issue":"12","key":"1642_CR35","doi-asserted-by":"publisher","first-page":"7096","DOI":"10.1109\/TCSVT.2023.3275314","volume":"33","author":"W Zhou","year":"2023","unstructured":"Zhou W, Zhang H, Yan W, Lin W (2023) MMSMCNet: Modal memory sharing and morphological complementary networks for RGB-t urban scene semantic segmentation. IEEE Trans Circuits Syst Video Technol 33(12):7096\u20137108. https:\/\/doi.org\/10.1109\/TCSVT.2023.3275314. (Accessed 2026-02-10)","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"1642_CR36","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1109\/TMM.2021.3086618","volume":"24","author":"W Zhou","year":"2022","unstructured":"Zhou W, Lin X, Lei J, Yu L, Hwang J-N (2022) MFFENet: Multiscale feature fusion and enhancement network for RGB-thermal urban road scene parsing. IEEE Trans Multimedia 24:2526\u20132538. https:\/\/doi.org\/10.1109\/TMM.2021.3086618. (Accessed 2026\u201302-10)","journal-title":"IEEE Trans Multimedia"},{"issue":"1","key":"1642_CR37","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1109\/TITS.2023.3306368","volume":"25","author":"S Dong","year":"2024","unstructured":"Dong S, Zhou W, Xu C, Yan W (2024) EGFNet: Edge-aware guidance fusion network for RGB\u2013thermal urban scene parsing. IEEE Trans Intell Transport Syst 25(1):657\u2013669. https:\/\/doi.org\/10.1109\/TITS.2023.3306368. (Accessed 2026-02-10)","journal-title":"IEEE Trans Intell Transport Syst"},{"key":"1642_CR38","doi-asserted-by":"publisher","first-page":"3483","DOI":"10.1109\/TMM.2022.3161852","volume":"25","author":"W Zhou","year":"2023","unstructured":"Zhou W, Yang E, Lei J, Wan J, Yu L (2023) PGDENet: Progressive guided fusion and depth enhancement network for RGB-d indoor scene parsing. IEEE Trans Multimedia 25:3483\u20133494. https:\/\/doi.org\/10.1109\/TMM.2022.3161852. (Accessed 2026\u201302-10)","journal-title":"IEEE Trans Multimedia"},{"key":"1642_CR39","doi-asserted-by":"publisher","first-page":"2192","DOI":"10.1109\/TMM.2021.3077767","volume":"24","author":"W Zhou","year":"2022","unstructured":"Zhou W, Zhu Y, Lei J, Wan J, Yu L (2022) CCAFNet: Crossflow and cross-scale adaptive fusion network for detecting salient objects in RGB-d images. IEEE Trans Multimedia 24:2192\u20132204. https:\/\/doi.org\/10.1109\/TMM.2021.3077767. (Accessed 2026\u201302-10)","journal-title":"IEEE Trans Multimedia"},{"issue":"3","key":"1642_CR40","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1109\/TCSVT.2021.3077058","volume":"32","author":"W Zhou","year":"2022","unstructured":"Zhou W, Guo Q, Lei J, Yu L, Hwang J-N (2022) ECFFNet: Effective and consistent feature fusion network for RGB-t salient object detection. IEEE Trans Circuits Syst Video Technol 32(3):1224\u20131235. https:\/\/doi.org\/10.1109\/TCSVT.2021.3077058. (Accessed 2026-02-10)","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"3","key":"1642_CR41","doi-asserted-by":"publisher","first-page":"4132","DOI":"10.1109\/TNNLS.2021.3105484","volume":"36","author":"W Zhou","year":"2025","unstructured":"Zhou W, Guo Q, Lei J, Yu L, Hwang J-N (2025) IRFR-net: Interactive recursive feature-reshaping network for detecting salient objects in RGB-d images. IEEE Trans Neural Netw Learning Syst 36(3):4132\u20134144. https:\/\/doi.org\/10.1109\/TNNLS.2021.3105484. (Accessed 2026-02-10)","journal-title":"IEEE Trans Neural Netw Learning Syst"},{"key":"1642_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.111898","volume":"160","author":"S Umirzakova","year":"2025","unstructured":"Umirzakova S, Mardieva S, Muksimova S, Baltayev J, Cho YI (2025) Iterative contextual and adaptive strategies for enhanced monocular depth estimation. Eng Appl Artif Intell 160:111898. https:\/\/doi.org\/10.1016\/j.engappai.2025.111898","journal-title":"Eng Appl Artif Intell"},{"key":"1642_CR43","doi-asserted-by":"publisher","unstructured":"Chen RJ, Chen C, Li Y, Chen TY, Trister AD, Krishnan RG, Mahmood F. Scaling vision transformers to gigapixel images via hierarchical self-supervised learning. arXiv Version Number: 1. https:\/\/doi.org\/10.48550\/ARXIV.2206.02647.  Accessed 2026\u201301-08","DOI":"10.48550\/ARXIV.2206.02647"},{"key":"1642_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104253","volume":"131","author":"J Li","year":"2021","unstructured":"Li J, Li W, Sisk A, Ye H, Wallace WD, Speier W, Arnold CW (2021) A multi-resolution model for histopathology image classification and localization with multiple instance learning. Comput Biol Med 131:104253. https:\/\/doi.org\/10.1016\/j.compbiomed.2021.104253. (Accessed 2026\u201301-08)","journal-title":"Comput Biol Med"},{"issue":"1","key":"1642_CR45","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1109\/TMI.2022.3202248","volume":"42","author":"P Huang","year":"2023","unstructured":"Huang P, He P, Tian S, Ma M, Feng P, Xiao H, Mercaldo F, Santone A, Qin J (2023) A ViT-AMC network with adaptive model fusion and multiobjective optimization for interpretable laryngeal tumor grading from histopathological images. IEEE Trans Med Imaging 42(1):15\u201328. https:\/\/doi.org\/10.1109\/TMI.2022.3202248. (Accessed 2026-01-08)","journal-title":"IEEE Trans Med Imaging"},{"key":"1642_CR46","doi-asserted-by":"publisher","unstructured":"Xiong C, Chen H, Sung JJY, King I. Diagnose Like a Pathologist: Transformer-Enabled Hierarchical Attention-Guided Multiple Instance Learning for Whole Slide Image Classification. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2301.08125.  Accessed 2026\u201301-08","DOI":"10.48550\/arXiv.2301.08125"},{"key":"1642_CR47","doi-asserted-by":"publisher","unstructured":"Shi Z, Zhang J, Kong J, Wang F. Integrative graph-transformer framework for histopathology whole slide image representation and classification. In: Linguraru, M.G., Dou, Q., Feragen, A., Giannarou, S., Glocker, B., Lekadir, K., Schnabel, J.A. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024 vol. 15011, pp. 341\u2013350. Springer. DOI: https:\/\/doi.org\/10.1007\/978-3-031-72120-5_32.Series Title: Lecture Notes in Computer Science. Accessed 2025-12-18","DOI":"10.1007\/978-3-031-72120-5_32."},{"issue":"12","key":"1642_CR48","doi-asserted-by":"publisher","first-page":"8747","DOI":"10.1007\/s00371-024-03269-7","volume":"40","author":"M Liang","year":"2024","unstructured":"Liang M, Jiang X, Cao J, Li B, Wang L, Chen Q, Zhang C, Zhao Y (2024) CAF-AHGCN: context-aware attention fusion adaptive hypergraph convolutional network for human-interpretable prediction of gigapixel whole-slide image. Vis Comput 40(12):8747\u20138765. https:\/\/doi.org\/10.1007\/s00371-024-03269-7. (Accessed 2026-01-09)","journal-title":"Vis Comput"},{"issue":"1","key":"1642_CR49","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"1642_CR50","doi-asserted-by":"crossref","unstructured":"Chen Y-C, Lu C-S (2023) Rankmix: data augmentation for weakly supervised learning of classifying whole slide images with diverse sizes and imbalanced categories. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 23936\u201323945","DOI":"10.1109\/CVPR52729.2023.02292"},{"key":"1642_CR51","doi-asserted-by":"crossref","unstructured":"Gadermayr M, Koller L, Tschuchnig M, Stangassinger LM, Kreutzer C, Couillard-Despres S, Oostingh GJ, Hittmair A (2023) Mixup-mil: novel data augmentation for multiple instance learning and a study on thyroid cancer diagnosis","DOI":"10.1007\/978-3-031-43987-2_46"},{"key":"1642_CR52","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110698","volume":"156","author":"H Zhang","year":"2024","unstructured":"Zhang H, Ma Y, Zhang K, Zheng N, Lai S (2024) Fmgnet: an efficient feature-multiplex group network for real-time vision task. Pattern Recogn 156:110698. https:\/\/doi.org\/10.1016\/j.patcog.2024.110698","journal-title":"Pattern Recogn"},{"issue":"2","key":"1642_CR53","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 (2021) Neural image compression for gigapixel histopathology image analysis. IEEE Trans Pattern Anal Mach Intell 43(2):567\u2013578. https:\/\/doi.org\/10.1109\/TPAMI.2019.2936841. (Accessed 2026-01-08)","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1642_CR54","doi-asserted-by":"publisher","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G. A simple framework for contrastive learning of visual representations. arXiv Version Number: 3. https:\/\/doi.org\/10.48550\/ARXIV.2002.05709.  Accessed 2026\u201301-08","DOI":"10.48550\/ARXIV.2002.05709"},{"key":"1642_CR55","doi-asserted-by":"crossref","unstructured":"He K, Fan H, Wu Y, Xie S, Girshick R. Momentum contrast for unsupervised visual representation learning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9726\u20139735. IEEE. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00975.https:\/\/ieeexplore.ieee.org\/document\/9157636\/ Accessed 2026-01-08","DOI":"10.1109\/CVPR42600.2020.00975"},{"issue":"6","key":"1642_CR56","doi-asserted-by":"publisher","first-page":"2301","DOI":"10.1109\/TCSVT.2020.3021128","volume":"31","author":"S Yang","year":"2021","unstructured":"Yang S, Deng W, Wang M, Du J, Hu J (2021) Orthogonality loss: Learning discriminative representations for face recognition. IEEE Trans Circuits Syst Video Technol 31(6):2301\u20132314. https:\/\/doi.org\/10.1109\/TCSVT.2020.3021128. (Accessed 2026-01-08)","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"1642_CR57","doi-asserted-by":"publisher","unstructured":"Bansal N, Chen X, Wang Z. Can we gain more from orthogonality regularizations in training deep CNNs?, arXiv. https:\/\/doi.org\/10.48550\/arXiv.1810.09102.  Accessed 2026\u201301-08","DOI":"10.48550\/arXiv.1810.09102"},{"issue":"1","key":"1642_CR58","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1186\/s40537-025-01299-z","volume":"12","author":"Q Peng","year":"2025","unstructured":"Peng Q, An S, Nie S, Su Y (2025) COLLAR: combating low-rank temporal latent representation for high-dimensional multivariate time series prediction using dynamic koopman regularization. J Big Data 12(1):258. https:\/\/doi.org\/10.1186\/s40537-025-01299-z. (Accessed 2026-02-02)","journal-title":"J Big Data"},{"key":"1642_CR59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110898","volume":"157","author":"Y Su","year":"2025","unstructured":"Su Y, Tan Y, An S, Xing M, Feng Z (2025) Semantic-driven dual consistency learning for weakly supervised video anomaly detection. Pattern Recogn 157:110898. https:\/\/doi.org\/10.1016\/j.patcog.2024.110898. (Accessed 2026\u201302-02)","journal-title":"Pattern Recogn"},{"key":"1642_CR60","doi-asserted-by":"publisher","unstructured":"Peng Q, Zhu S, Su Y, Xing M. Gaze-and-machine dual-driven attention fusion network for medical image classification. In: Huang, D.-S., Chen, W., Pan, Y., Chen, H. (eds.) Advanced Intelligent Computing Technology and Applications, vol. 15869, pp. 402\u2013412. Springer. https:\/\/doi.org\/10.1007\/978-981-95-0036-9_34.Series Title: Lecture Notes in Computer Science. Accessed 2026-02-02","DOI":"10.1007\/978-981-95-0036-9_34."},{"issue":"6","key":"1642_CR61","doi-asserted-by":"publisher","first-page":"065","DOI":"10.1093\/gigascience\/giy065","volume":"7","author":"G Litjens","year":"2018","unstructured":"Litjens G, Bandi P, Ehteshami Bejnordi B, Geessink O, Balkenhol M, Bult P, Halilovic A, Hermsen M, Van De Loo R, Vogels R, Manson QF, Stathonikos N, Baidoshvili A, Van Diest P, Wauters C, Van Dijk M, Van Der Laak J (2018) 1399 h&e-stained sentinel lymph node sections of breast cancer patients: the CAMELYON dataset. Giga Sci 7(6):065. https:\/\/doi.org\/10.1093\/gigascience\/giy065. (Accessed 2025-12-18)","journal-title":"Giga Sci"},{"issue":"10","key":"1642_CR62","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1038\/ng.2764","volume":"45","author":"JN Weinstein","year":"2013","unstructured":"Weinstein JN, Collisson EA, Mills GB, Shaw KRM, Ozenberger BA, Ellrott K, Shmulevich I, Sander C, Stuart JM, The Cancer Genome Atlas Research Network (2013) The cancer genome atlas pan-cancer analysis project. Nat Genet 45(10):1113\u20131120. https:\/\/doi.org\/10.1038\/ng.2764","journal-title":"Nat Genet"},{"key":"1642_CR63","doi-asserted-by":"publisher","unstructured":"Xitong L, Yuanyuan L, Jiawen L, Junru C, Wenting H, Tian G, Jian G, Yonghong H. Camelyon+. Science Data Bank. Version Number: V3. https:\/\/doi.org\/10.57760\/sciencedb.16442.","DOI":"10.57760\/sciencedb.16442."}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01642-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-026-01642-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01642-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:54:52Z","timestamp":1773172492000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-026-01642-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":63,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["1642"],"URL":"https:\/\/doi.org\/10.1007\/s10044-026-01642-x","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]},"assertion":[{"value":"10 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 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":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"62"}}