发表机构
E-Health Research Center, International Institute of Information Technology Bangalore（班加罗尔国际信息技术学院电子健康研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对现有自监督学习方法无法捕捉病理特定形态模式的问题，提出TVT-PAPD框架，集成TVT与PAPD模块，利用可学习原型库增强病理感知特征学习，在相关数据集实验中取得高加权F1分数且跨队列泛化能力强。
AI 中文摘要
自监督学习已成为从大规模未标记全切片图像（WSIs）中学习可转移表示的有效范式。然而，现有方法主要学习通用视觉特征，无法明确捕捉对疾病特征至关重要的病理特定形态模式。为解决此局限，我们提出了带病理感知原型蒸馏的微小视觉Transformer（TVT-PAPD）。该自监督病理表示学习框架将微小视觉Transformer（TVT）与新型病理感知原型蒸馏（PAPD）模块集成。PAPD利用可学习的病理原型库发现并保留代表性组织形态模式，促使语义相似的病理区域学习一致且有判别力的表示。所提框架在保持计算效率（90M参数）的同时增强了病理感知特征学习。在癌症基因组图谱（TCGA）低级别胶质瘤（LGG）/胶质母细胞瘤（GBM）数据集和印度病理脑（IPD-Brain）数据集上的实验表明，TVT-PAPD在LGG-GBM分类中分别实现了93.02%和90.23%的加权F1分数，同时在独立胶质瘤数据集上展现出强大的跨队列泛化能力。
英文摘要
Self-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) low-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.
Comments13 pages, 4 figures, 10 tables
