{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T04:16:37Z","timestamp":1783656997935,"version":"3.55.0"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.knosys.2026.116582","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:54:24Z","timestamp":1783061664000},"page":"116582","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["An enhanced spatial-frequency fusion modulation for multi-instance learning on whole slide images"],"prefix":"10.1016","volume":"350","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0211-5886","authenticated-orcid":false,"given":"Bin","family":"Deng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghong","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8610-5920","authenticated-orcid":false,"given":"Chuanbo","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhipeng","family":"Mai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weigang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhien","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junying","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116582_b1","article-title":"Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries.","author":"Freddie","year":"2018","journal-title":"CA: Cancer J. Clin."},{"key":"10.1016\/j.knosys.2026.116582_b2","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1146\/annurev-cancerbio-061521-092038","article-title":"AI in computational pathology of cancer: improving diagnostic workflows and clinical outcomes?","author":"Cifci","year":"2023","journal-title":"Annu. Rev. Cancer Biol."},{"key":"10.1016\/j.knosys.2026.116582_b3","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1038\/s41374-020-00514-0","article-title":"Artificial intelligence and computational pathology","author":"Cui","year":"2021","journal-title":"Lab. Invest."},{"key":"10.1016\/j.knosys.2026.116582_b4","doi-asserted-by":"crossref","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":"10.1016\/j.knosys.2026.116582_b5","unstructured":"M. Ilse, J. Tomczak, M. Welling, Attention-based deep multiple instance learning, in: International Conference on Machine Learning, 2018, pp. 2127\u20132136."},{"key":"10.1016\/j.knosys.2026.116582_b6","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","article-title":"Data-efficient and weakly supervised computational pathology on whole-slide images","author":"Lu","year":"2021","journal-title":"Nat. Biomed. Eng."},{"key":"10.1016\/j.knosys.2026.116582_b7","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.knosys.2026.116582_b8","first-page":"2136","article-title":"Transmil: Transformer based correlated multiple instance learning for whole slide image classification","volume":"vol. 34","author":"Shao","year":"2021"},{"key":"10.1016\/j.knosys.2026.116582_b9","doi-asserted-by":"crossref","first-page":"btad114","DOI":"10.1093\/bioinformatics\/btad114","article-title":"Targeting tumor heterogeneity: multiplex-detection-based multiple instance learning for whole slide image classification","author":"Wang","year":"2023","journal-title":"Bioinformatics"},{"key":"10.1016\/j.knosys.2026.116582_b10","unstructured":"A. Gu, T. Dao, Mamba: Linear-Time Sequence Modeling with Selective State Spaces, in: First Conference on Language Modeling, 2024."},{"key":"10.1016\/j.knosys.2026.116582_b11","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"594","article-title":"Structured state space models for multiple instance learning in digital pathology","author":"Fillioux","year":"2023"},{"key":"10.1016\/j.knosys.2026.116582_b12","series-title":"2024 IEEE International Conference on Bioinformatics and Biomedicine","first-page":"3200","article-title":"MamMIL: Multiple instance learning for whole slide images with state space models","author":"Fang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116582_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.107378","article-title":"BAWGNet: Boundary aware wavelet guided network for the nuclei segmentation in histopathology images","volume":"165","author":"Imtiaz","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.knosys.2026.116582_b14","series-title":"From classical machine learning to emerging foundation models: Review on multimodal data integration for cancer research","author":"Muneer","year":"2025"},{"key":"10.1016\/j.knosys.2026.116582_b15","doi-asserted-by":"crossref","unstructured":"B. Li, Y. Li, K.W. Eliceiri, Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 14318\u201314328.","DOI":"10.1109\/CVPR46437.2021.01409"},{"key":"10.1016\/j.knosys.2026.116582_b16","doi-asserted-by":"crossref","unstructured":"H. Zhang, Y. Meng, Y. Zhao, Y. Qiao, X. Yang, S.E. Coupland, Y. Zheng, Dtfd-mil: Double-tier feature distillation multiple instance learning for histopathology whole slide image classification, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 18802\u201318812.","DOI":"10.1109\/CVPR52688.2022.01824"},{"key":"10.1016\/j.knosys.2026.116582_b17","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"296","article-title":"Mambamil: Enhancing long sequence modeling with sequence reordering in computational pathology","author":"Yang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116582_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2025.108966","article-title":"Dynamic hypergraph representation for bone metastasis analysis","author":"Chen","year":"2025","journal-title":"Comput. Methods Programs Biomed."},{"key":"10.1016\/j.knosys.2026.116582_b19","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"45","article-title":"AEM: attention entropy maximization for multiple instance learning based whole slide image classification","author":"Zhang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116582_b20","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.compmedimag.2014.11.010","article-title":"Computer-aided diagnosis from weak supervision: A benchmarking study","volume":"42","author":"Kandemir","year":"2015","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.knosys.2026.116582_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109300","article-title":"Multi-scale multi-instance contrastive learning for whole slide image classification","volume":"138","author":"Zhang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116582_b22","doi-asserted-by":"crossref","unstructured":"Y. Xiong, Z. Zeng, R. Chakraborty, M. Tan, G. Fung, Y. Li, V. Singh, Nystr\u00f6mformer: A nystr\u00f6m-based algorithm for approximating self-attention, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2021, pp. 14138\u201314148.","DOI":"10.1609\/aaai.v35i16.17664"},{"key":"10.1016\/j.knosys.2026.116582_b23","series-title":"Digital Image Processing: Principles and Applications","author":"Baxes","year":"1994"},{"key":"10.1016\/j.knosys.2026.116582_b24","series-title":"2022 7th International Conference on Automation, Control and Robotics Engineering","first-page":"189","article-title":"Fourier ViT: A multi-scale vision transformer with Fourier transform for histopathological image classification","author":"Duan","year":"2022"},{"key":"10.1016\/j.knosys.2026.116582_b25","first-page":"2008","article-title":"FourierMIL: Fourier filtering-based multiple instance learning for whole slide image analysis","author":"Zheng","year":"2024","journal-title":"BioRxiv"},{"key":"10.1016\/j.knosys.2026.116582_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.106812","article-title":"FDTrans: Frequency domain transformer model for predicting subtypes of lung cancer using multimodal data","volume":"158","author":"Cai","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.knosys.2026.116582_b27","series-title":"FreqU-FNet: Frequency-aware U-net for imbalanced medical image segmentation","author":"Xing","year":"2025"},{"key":"10.1016\/j.knosys.2026.116582_b28","unstructured":"L. Zhu, B. Liao, Q. Zhang, X. Wang, W. Liu, X. Wang, Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model, in: Forty-First International Conference on Machine Learning, 2024."},{"key":"10.1016\/j.knosys.2026.116582_b29","series-title":"The Thirty-Eighth Annual Conference on Neural Information Processing Systems","article-title":"VMamba: Visual state space model","author":"Liu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116582_b30","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.knosys.2026.116582_b31","series-title":"The next layer: Augmenting foundation models with structure-preserving and attention-guided learning for local patches to global context awareness in computational pathology","author":"Waqas","year":"2025"},{"key":"10.1016\/j.knosys.2026.116582_b32","first-page":"54152","article-title":"Scattering vision transformer: Spectral mixing matters","volume":"vol. 36","author":"Patro","year":"2023"},{"key":"10.1016\/j.knosys.2026.116582_b33","doi-asserted-by":"crossref","first-page":"2199","DOI":"10.1001\/jama.2017.14585","article-title":"Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer","author":"Bejnordi","year":"2017","journal-title":"Jama"},{"issue":"10","key":"10.1016\/j.knosys.2026.116582_b34","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/ng.2764","article-title":"The cancer genome atlas pan-cancer analysis project","volume":"45","author":"Weinstein","year":"2013","journal-title":"Nature Genet."},{"key":"10.1016\/j.knosys.2026.116582_b35","doi-asserted-by":"crossref","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a general-purpose foundation model for computational pathology","author":"Chen","year":"2024","journal-title":"Nature Med."},{"issue":"8035","key":"10.1016\/j.knosys.2026.116582_b36","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1038\/s41586-024-07894-z","article-title":"A pathology foundation model for cancer diagnosis and prognosis prediction","volume":"634","author":"Wang","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.knosys.2026.116582_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.108370","article-title":"CFATrans: Brain tumor segmentation from MRIs using consecutive fusion-attention transformer with convolutional networks and a composite loss function","volume":"112","author":"Goceri","year":"2026","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.knosys.2026.116582_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.108083","article-title":"BRMSA-net: Disclosing concealed colorectal polyps in colonoscopy images via boundary recalibration and multi-scale aggregation network","volume":"110","author":"Sebai","year":"2025","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.knosys.2026.116582_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.126290","article-title":"An efficient network with CNN and transformer blocks for glioma grading and brain tumor classification from MRIs","volume":"268","author":"Goceri","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.116582_b40","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122672","article-title":"Vision transformer based classification of gliomas from histopathological images","volume":"241","author":"Goceri","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.116582_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.108138","article-title":"A convolution and transformer-based method with effective stain normalization for breast cancer detection from whole slide images","volume":"110","author":"Goceri","year":"2025","journal-title":"Biomed. Signal Process. Control."},{"issue":"9","key":"10.1016\/j.knosys.2026.116582_b42","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/s10462-024-10897-x","article-title":"GAN based augmentation using a hybrid loss function for dermoscopy images","volume":"57","author":"Goceri","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.knosys.2026.116582_b43","doi-asserted-by":"crossref","first-page":"46191","DOI":"10.1007\/s11042-025-20760-y","article-title":"A hybrid attention-based deep learning model for segmentation of livers and liver tumors from CT scans","volume":"84","author":"Goceri","year":"2025","journal-title":"Multimedia Tools Appl."},{"key":"10.1016\/j.knosys.2026.116582_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127445","article-title":"Nuclei segmentation using attention aware and adversarial networks","volume":"579","author":"Goceri","year":"2024","journal-title":"Neurocomputing"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126013080?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126013080?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T03:39:05Z","timestamp":1783654745000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126013080"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":44,"alternative-id":["S0950705126013080"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116582","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"An enhanced spatial-frequency fusion modulation for multi-instance learning on whole slide images","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116582","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116582"}}