{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T17:11:27Z","timestamp":1789837887703,"version":"4.0.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T00:00:00Z","timestamp":1765843200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T00:00:00Z","timestamp":1765843200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Manipal Academy of Higher Education, Manipal"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The increasing complexity of whole slide images in histopathology requires models that would be accurate across magnifications while being robust to visual, topological, and contextual variations in the setting. Thus far, existing approaches have either failed to generalize across various resolutions, have ignored the inherent structural relationships within tissue architecture, or have not integrated a mechanism to adaptively prioritize samples during training. Aside from this, most approaches do not consider both pixel-level appearance and morphological context, which restricts their diagnostic reliability sets. This research aims to address these limitations by providing a framework for Multiscale Tumor Characterization by synergizing RepVGG-DINO encoders, self-distilled visual transformers, and hierarchical attentions. The Pathology-Adaptive Uncertainty-Aware Consistency (PAUAC) Framework ensures consistency in prediction across 10 and 40 and introduces a dual-branch consistency model with uncertainty-weighted KL divergence regularization. The Structural Attention-Constrained Graph Regularizer (SACGR) which is a topology-aware visual encoding technique focuses on constrains attention in the ViT decoders thereby embedding spatial priors from superpixel-based graphs into them. The Multiscale Pathology Curriculum Scheduler (MPCS) creates a sample prioritization mechanism based on entropy, guiding the training from simpler to more complex tissue patterns. The Transformer-Driven Dual-Modality Morphometry Network integrates H&amp;E image features with Voronoi-based nuclear morphometry using cross-modal self-attention to enhance representational richness for the process. Finally, the Contrastive Cell-Contextual Representation Alignment (CCCRA) module improves embedding consistency across different magnifications by using positional contrastive learning sets. The combination of these modules brings measurable improvements (+2.3% Dice score, +21% faster convergence, +3.7% accuracy for morphologically ambiguous samples, and +12.6% normalized mutual information in embeddings) sets. This work marks a great leap in tumor characterization within histopathology, establishing resolution-aware, topology-constrained, and morphology-fused learning in an interpretable and scalable manner for the process.<\/jats:p>","DOI":"10.1038\/s41598-025-27748-6","type":"journal-article","created":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T10:24:11Z","timestamp":1765880651000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Multiscale tumor characterization in histopathology via self-distilled transformers and topology-aware visual encoding"],"prefix":"10.1038","volume":"15","author":[{"given":"Tanvir H.","family":"Sardar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"P.","family":"Naresh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sk Mahmudul","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Praveen","family":"Kulkarni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajesh","family":"T. M","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"B. M.","family":"Ahamed Shafeeq","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,16]]},"reference":[{"key":"27748_CR1","doi-asserted-by":"publisher","DOI":"10.1186\/s40644-024-00814-4","author":"A Surov","year":"2024","unstructured":"Surov, A., Borggrefe, J., H\u00f6hn, A. & Meyer, H. Associations between ADC histogram analysis values and tumor-micro milieu in uterine cervical cancer. Cancer Imaging https:\/\/doi.org\/10.1186\/s40644-024-00814-4 (2024).","journal-title":"Cancer Imaging"},{"key":"27748_CR2","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-024-00765-w","author":"S Patkar","year":"2024","unstructured":"Patkar, S. et al. Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images. npj Precis. Oncol. https:\/\/doi.org\/10.1038\/s41698-024-00765-w (2024).","journal-title":"npj Precis. Oncol."},{"key":"27748_CR3","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-75602-y","author":"DH Lee","year":"2024","unstructured":"Lee, D. H. & Lee, J. Y. A comprehensive study on the feasibility and diagnostic potential of fluctuation imaging in liver tumor assessment. Sci. Rep. https:\/\/doi.org\/10.1038\/s41598-024-75602-y (2024).","journal-title":"Sci. Rep."},{"key":"27748_CR4","doi-asserted-by":"publisher","DOI":"10.1186\/s13046-024-03262-x","author":"J G\u00f6tze","year":"2025","unstructured":"G\u00f6tze, J. et al. Identification and characterization of tumor and stromal derived liquid biopsy analytes in pancreatic ductal adenocarcinoma. J. Exp. Clin. Cancer Res. https:\/\/doi.org\/10.1186\/s13046-024-03262-x (2025).","journal-title":"J. Exp. Clin. Cancer Res."},{"key":"27748_CR5","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-49017-2","author":"A Darbandsari","year":"2024","unstructured":"Darbandsari, A. et al. AI-based histopathology image analysis reveals a distinct subset of endometrial cancers. Nat. Commun. https:\/\/doi.org\/10.1038\/s41467-024-49017-2 (2024).","journal-title":"Nat. Commun."},{"issue":"5-6","key":"27748_CR6","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1007\/s10495-025-02118-9","volume":"30","author":"SE Johnson","year":"2025","unstructured":"Johnson, S. E. et al. An in vivo imaging approach for simultaneously assessing tumor response and cytotoxicity-induced tissue response in chemotherapy. Apoptosis 30(5\u20136), 1515\u20131524. https:\/\/doi.org\/10.1007\/s10495-025-02118-9 (2025).","journal-title":"Apoptosis"},{"key":"27748_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.107967","volume":"109","author":"X Xie","year":"2025","unstructured":"Xie, X. et al. PIF-Net: A parallel interweave fusion network for knee joint segmentation. Biomed. Signal Process. Control 109, 107967 (2025).","journal-title":"Biomed. Signal Process. Control"},{"issue":"2","key":"27748_CR8","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1016\/j.bbe.2024.04.001","volume":"44","author":"X Xie","year":"2024","unstructured":"Xie, X. et al. Discriminative features pyramid network for medical image segmentation. Biocybern. Biomed. Eng. 44(2), 327\u2013340 (2024).","journal-title":"Biocybern. Biomed. Eng."},{"key":"27748_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.104437","volume":"81","author":"X Xie","year":"2023","unstructured":"Xie, X. et al. Canet: Context aware network with dual-stream pyramid for medical image segmentation. Biomed. Signal Process. Control 81, 104437 (2023).","journal-title":"Biomed. Signal Process. Control"},{"issue":"34","key":"27748_CR10","doi-asserted-by":"publisher","first-page":"21273","DOI":"10.1007\/s00521-024-10287-y","volume":"36","author":"AA Wafa","year":"2024","unstructured":"Wafa, A. A., Essa, R. M., Abohany, A. A. & Abdelkader, H. E. Integrating deep learning for accurate gastrointestinal cancer classification: a comprehensive analysis of MSI and MSS patterns using histopathology data. Neural Comput. Appl. 36(34), 21273\u201321305. https:\/\/doi.org\/10.1007\/s00521-024-10287-y (2024).","journal-title":"Neural Comput. Appl."},{"key":"27748_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/s10143-024-03157-7","author":"SM Kaushal-Deep","year":"2024","unstructured":"Kaushal-Deep, S. M. et al. Intraoperative variations in intra-axial brain tumor size after craniotomy: a prospective study with histopathological and tumor tissue composition correlation, introducing concepts of tumor expansion and tumor surfacing. Neurosurg. Rev. https:\/\/doi.org\/10.1007\/s10143-024-03157-7 (2024).","journal-title":"Neurosurg. Rev."},{"key":"27748_CR12","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-66744-0","author":"B Peng","year":"2024","unstructured":"Peng, B. et al. Comprehensive landscape of m6A regulator-related gene patterns and tumor microenvironment infiltration characterization in gastric cancer. Sci. Rep. https:\/\/doi.org\/10.1038\/s41598-024-66744-0 (2024).","journal-title":"Sci. Rep."},{"issue":"9","key":"27748_CR13","doi-asserted-by":"publisher","first-page":"1811","DOI":"10.1007\/s11095-024-03762-7","volume":"41","author":"V Laney","year":"2024","unstructured":"Laney, V. et al. MR Molecular image guided treatment of pancreatic cancer with targeted ECO\/mir-200c nanoparticles in immunocompetent mouse tumor models. Pharm. Res. 41(9), 1811\u20131825. https:\/\/doi.org\/10.1007\/s11095-024-03762-7 (2024).","journal-title":"Pharm. Res."},{"key":"27748_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10887-z","author":"JJW Siet","year":"2024","unstructured":"Siet, J. J. W. et al. A comprehensive review of tubule formation in histopathology images: advancement in tubule and tumor detection techniques. Artif. Intell. Rev. https:\/\/doi.org\/10.1007\/s10462-024-10887-z (2024).","journal-title":"Artif. Intell. Rev."},{"key":"27748_CR15","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-024-00745-0","author":"S Ramesh","year":"2024","unstructured":"Ramesh, S. et al. Artificial intelligence-based morphologic classification and molecular characterization of neuroblastic tumors from digital histopathology. npj Precis. Oncol. https:\/\/doi.org\/10.1038\/s41698-024-00745-0 (2024).","journal-title":"npj Precis. Oncol."},{"key":"27748_CR16","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-024-00749-w","author":"\u00d3 Lapuente-Santana","year":"2024","unstructured":"Lapuente-Santana, \u00d3., Kant, J. & Eduati, F. Integrating histopathology and transcriptomics for spatial tumor microenvironment profiling in a melanoma case study. npj Precis. Oncol. https:\/\/doi.org\/10.1038\/s41698-024-00749-w (2024).","journal-title":"npj Precis. Oncol."},{"key":"27748_CR17","doi-asserted-by":"publisher","DOI":"10.1038\/s41523-025-00730-1","author":"I Zerdes","year":"2025","unstructured":"Zerdes, I. et al. Machine learning-based spatial characterization of tumor-immune microenvironment in the EORTC 10994\/BIG 1\u201300 early breast cancer trial. npj Breast Cancer https:\/\/doi.org\/10.1038\/s41523-025-00730-1 (2025).","journal-title":"npj Breast Cancer"},{"key":"27748_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-025-04172-x","author":"JJW Siet","year":"2025","unstructured":"Siet, J. J. W. et al. Quantitative measurement of tubules in breast histopathology using a textural discriminant approach signal. Image Video Process. https:\/\/doi.org\/10.1007\/s11760-025-04172-x (2025).","journal-title":"Image Video Process."},{"issue":"3","key":"27748_CR19","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/s11307-025-02007-2","volume":"27","author":"M Omura","year":"2025","unstructured":"Omura, M. et al. Attenuation estimation and acoustic characterization of mouse lymph node tumor using high-frequency ultrasound. Mol. Imaging Biol. 27(3), 379\u2013388. https:\/\/doi.org\/10.1007\/s11307-025-02007-2 (2025).","journal-title":"Mol. Imaging Biol."},{"issue":"3","key":"27748_CR20","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1007\/s11517-024-03224-7","volume":"63","author":"MM Sani","year":"2024","unstructured":"Sani, M. M., Royat, A. & Baghshah, M. S. Classification of breast cancer histopathology images using a modified supervised contrastive learning method. Med. Biol. Eng. Comput. 63(3), 721\u2013731. https:\/\/doi.org\/10.1007\/s11517-024-03224-7 (2024).","journal-title":"Med. Biol. Eng. Comput."},{"key":"27748_CR21","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-93192-1","author":"R Jaidee","year":"2025","unstructured":"Jaidee, R. et al. Establishment and genomic profiling of cholangiocarcinoma cells with functional characterization. Sci. Rep. https:\/\/doi.org\/10.1038\/s41598-025-93192-1 (2025).","journal-title":"Sci. Rep."},{"key":"27748_CR22","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-87279-y","author":"M Mascarenhas","year":"2025","unstructured":"Mascarenhas, M. et al. Artificial intelligence for automatic diagnosis and pleomorphic morphological characterization of malignant biliary strictures using digital cholangioscopy. Sci. Rep. https:\/\/doi.org\/10.1038\/s41598-025-87279-y (2025).","journal-title":"Sci. Rep."},{"key":"27748_CR23","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-025-11683-1","author":"NP Haag","year":"2025","unstructured":"Haag, N. P. et al. Photon-counting computed tomography in esophageal cancer: correlation of iodine concentration with histopathology and treatment response to neoadjuvant radiochemotherapy. Euro. Radiol. https:\/\/doi.org\/10.1007\/s00330-025-11683-1 (2025).","journal-title":"Euro. Radiol."},{"key":"27748_CR24","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-97343-2","author":"MM Javadi","year":"2025","unstructured":"Javadi, M. M., Soleimani, N. & Zandi, A. Enhancing breast cancer immunotherapy using gold nanoparticles carrying tumor antigens. Sci. Rep. https:\/\/doi.org\/10.1038\/s41598-025-97343-2 (2025).","journal-title":"Sci. Rep."},{"key":"27748_CR25","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-57943-y","author":"MM Benimam","year":"2025","unstructured":"Benimam, M. M. et al. Statistical analysis of spatial patterns in tumor microenvironment images. Nat. Commun. https:\/\/doi.org\/10.1038\/s41467-025-57943-y (2025).","journal-title":"Nat. Commun."},{"issue":"9","key":"27748_CR26","doi-asserted-by":"publisher","first-page":"1334","DOI":"10.1038\/s43018-024-00787-0","volume":"5","author":"J Fernandez-Mateos","year":"2024","unstructured":"Fernandez-Mateos, J. et al. Tumor evolution metrics predict recurrence beyond 10 years in locally advanced prostate cancer. Nat. Cancer 5(9), 1334\u20131351. https:\/\/doi.org\/10.1038\/s43018-024-00787-0 (2024).","journal-title":"Nat. Cancer"},{"key":"27748_CR27","doi-asserted-by":"publisher","DOI":"10.1007\/s00210-025-04063-5","author":"EA Mohamad","year":"2025","unstructured":"Mohamad, E. A., Fikry, E. M. & Rageh, M. M. Antitumor activity of functionalized iron oxide nanoparticles in Ehrlich tumor carcinoma-bearing mice enhanced by magnetic field. Naunyn-Schmiedeberg\u2019s Arch. Pharmacol. https:\/\/doi.org\/10.1007\/s00210-025-04063-5 (2025).","journal-title":"Naunyn-Schmiedeberg\u2019s Arch. Pharmacol."},{"key":"27748_CR28","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-025-00868-y","author":"AL Hunt","year":"2025","unstructured":"Hunt, A. L. et al. Real-time functional proteomics enhances therapeutic targeting in precision oncology molecular tumor boards. Precis. Oncol. https:\/\/doi.org\/10.1038\/s41698-025-00868-y (2025).","journal-title":"Precis. Oncol."},{"key":"27748_CR29","doi-asserted-by":"publisher","unstructured":"Wang, X.\u00a0et al. TransPath: Transformer-based self-supervised learning for histopathological image classification. In: de Bruijne, M.,\u00a0et al.\u00a0Medical image computing and computer assisted intervention \u2013 MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science 12908. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-87237-3_18 (2021)","DOI":"10.1007\/978-3-030-87237-3_18"},{"key":"27748_CR30","doi-asserted-by":"publisher","first-page":"110","DOI":"10.3390\/math11010110","volume":"11","author":"X Jin","year":"2023","unstructured":"Jin, X., Huang, T., Wen, K., Chi, M. & An, H. HistoSSL: self-supervised representation learning for classifying histopathology images. Mathematics 11, 110. https:\/\/doi.org\/10.3390\/math11010110 (2023).","journal-title":"Mathematics"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27748-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27748-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27748-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:05:39Z","timestamp":1766066739000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27748-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,16]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["27748"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-27748-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,16]]},"assertion":[{"value":"30 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 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":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"The authors confirm that the research conducted for this study complies with the relevant ethical guidelines and regulations. No humans or animals have been considered for the work.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"43897"}}