[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85904-en":3,"doc-seo-85904-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85904,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","TVT-PAPD: Pathology-Aware Prototype Distillation for Self-Supervised Whole Slide Image Classification","Self-supervised learning (SSL) enables transferable representations from large unlabeled whole slide images (WSIs), yet many methods primarily learn generic visual features and miss pathology-specific morphological patterns essential for disease characterization. TVT-PAPD introduces a Tiny Vision Transformer (TVT) coupled with Pathology-Aware Prototype Distillation (PAPD), using a learnable pathology prototype bank to preserve representative tissue morphology and align consistent discriminative representations. Experiments on TCGA LGG/GBM and IPD-Brain report weighted F1-scores of 93.02% and 90.23%, with strong cross-cohort generalization and improved interpretability.","arXiv :2607 . 10406v1 [ cs .CV] 11 Jul 2026  \nTVT-PAPD: PATHOLOGY-AWARE PROTOTYPE DISTILLATION FOR SELF-SUPERVISED WHOLE SLIDE IMAGE CLASSIFICATION  \nRamesh Naidu Laveti1 , Jaya Sreevalsan-Nair1 T K Srikanth  \n1E-Health Research Center,  \nInternational Institute of Information Technology Bangalore, Karnataka 560100, India.  \n[https://ehrc.iiitb.ac.in/](https://ehrc.iiitb.ac.in/)  \nJuly 10, 2026  \nABSTRACT  \nSelf-supervised learning (SSL) has emerged as an effective paradigm for learning transferable representations from large-scale unlabeled whole slide images (WSIs) . However, existing SSL methods primarily learn generic visual features and often fail to explicitly capture pathology-specific morphological patterns that are critical for disease characterization. To address this limitation, we propose Tiny Vision Transformer with Pathology-Aware Prototype Distillation (TVT-PAPD) . This self-supervised pathology representation learning framework integrates a Tiny Vision Transformer (TVT) with a novel Pathology-Aware Prototype Distillation (PAPD) module. PAPD employs a learnable pathology prototype bank to discover and preserve representative tissue morphology patterns, encouraging semantically similar pathological regions to learn consistent and discriminative representations. The proposed framework enhances pathology-aware feature learning while maintaining computational efficiency with 90M parameters. Experiments on the Cancer Genome Atlas (TCGA)  \nlow-grade glioma (LGG)/glioblastoma (GBM) dataset and the Indian Pathology Brain (IPD-Brain) dataset demonstrate that TVT-PAPD achieves weighted F1-scores of 93.02% and 90.23%, respectively, for LGG-GBM classification, while exhibiting strong cross-cohort generalization across independent glioma datasets.  \nFurthermore, the learned prototypes capture meaningful patterns in tissue morphology, improving the interpretability of the representation. These results highlight the effectiveness of pathology-aware prototype distillation for efficient, robust, and interpretable WSI analysis in computational pathology.  \nKeywords Computational Pathology, Whole Slide Images, Self-Supervised Learning, Vision Transformers, Pathology-Aware Prototype Distillation, Foundation Models, Histopathology Image Analysis, Glioma Classification.  \n1 Introduction  \nDigital pathology has transformed computational pathology by enabling the digitization of histopathological slides into high-resolution WSIs [1] . These gigapixel-scale images contain rich morphological information for automated diagnosis, prognosis, and disease screening [2, 3] . However, their massive size and tissue heterogeneity make efficient WSI analysis challenging [4] . Furthermore, staining variability and limited expert annotations further complicate robust model development [5, 6] . Consequently, WSIs are typically processed as collections of image patches [4] . Transformerbased architectures have substantially improved WSI analysis by modeling long-range contextual dependencies beyond the limited receptive fields of convolutional neural networks (CNNs) . Recent approaches, including Vision Transformer (ViT) [7], Clustering-constrained Attention Multiple Instance Learning (CLAM) [8], Transformer-based Multiple Instance Learning (TransMIL) [9], and Hierarchical Image Pyramid Transformer (HIPT) [10], have achieved strong performance in pathology image analysis, while pathology foundation models such as GigaPath [11] and Virchow [12] have demonstrated the benefits of large-scale pretraining. Nevertheless, these models often require considerable computational resources.  \n∗ [jnair@iiitb.ac.in](jnair@iiitb.ac.in)  \n. JULY 10, 2026  \nAlgorithm 1 Tissue Patch Selection for TVT-PAPD  \nRequire: Whole slide image I, patch size P, background threshold τ  \nEnsure: Tissue patch set P  \n1: Initialize retained patch set P ← 0/  \n2: for each grid location (x, y) in I with stride P do  \n3: t ← CropPatch (I, x, y, P)  \n4: ρ ← BackgroundRatio (t )  \n5: if ρ","cbCaivsHCH3gnRNW","https://ap.wps.com/l/cbCaivsHCH3gnRNW","pdf",3109202,4,1,13,"English","en",105,"# Introduction\n## Digital pathology and WSI challenges\n## Self-supervised learning and pathology foundation models\n# Methodology\n## Algorithm: Tissue patch selection for TVT-PAPD","[{\"question\":\"What problem does TVT-PAPD address in existing self-supervised WSI learning?\",\"answer\":\"Existing SSL methods often learn generic visual features and fail to explicitly capture pathology-specific morphological patterns needed for diagnostically meaningful tissue characterization. TVT-PAPD targets this by incorporating pathology-aware distillation.\"},{\"question\":\"How does Pathology-Aware Prototype Distillation (PAPD) work?\",\"answer\":\"PAPD uses a learnable pathology prototype bank to discover and preserve representative tissue morphology patterns. During self-supervised training, teacher–student prototype distributions are aligned to encourage consistent and discriminative representations.\"},{\"question\":\"What performance results are reported for glioma classification?\",\"answer\":\"On TCGA LGG/GBM, TVT-PAPD achieves a weighted F1-score of 93.02%, and on the IPD-Brain dataset it achieves 90.23%. The results also indicate strong cross-cohort generalization and improved interpretability from learned prototypes.\"}]",1784207066,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"tvt-papd-pathology-aware-prototype-distillation-for-self-supervised-whole-slide-image-classification","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/tvt-papd-pathology-aware-prototype-distillation-for-self-supervised-whole-slide-image-classification/85904/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does TVT-PAPD address in existing self-supervised WSI learning?","Question",{"text":75,"@type":76},"Existing SSL methods often learn generic visual features and fail to explicitly capture pathology-specific morphological patterns needed for diagnostically meaningful tissue characterization. TVT-PAPD targets this by incorporating pathology-aware distillation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does Pathology-Aware Prototype Distillation (PAPD) work?",{"text":80,"@type":76},"PAPD uses a learnable pathology prototype bank to discover and preserve representative tissue morphology patterns. During self-supervised training, teacher–student prototype distributions are aligned to encourage consistent and discriminative representations.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance results are reported for glioma classification?",{"text":84,"@type":76},"On TCGA LGG/GBM, TVT-PAPD achieves a weighted F1-score of 93.02%, and on the IPD-Brain dataset it achieves 90.23%. The results also indicate strong cross-cohort generalization and improved interpretability from learned prototypes.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]