MiTHras：用于有丝分裂图像分析的任务特定分层半监督对比掩码自编码器
MiTHras: Task-specific Hierarchical Semi-supervised Contrastive Masked Autoencoder for Mitotic Figure Analysis
浏览论文内容
中文总结 AI 辅助
MiTHras通过结合伪标签引导的对比学习和掩码重建，在多个基准上取得最优F1分数，为有丝分裂图像分析提供了稳健且可迁移的表征。
中文摘要 AI 辅助
有丝分裂图像（MF）分析支持肿瘤分级和预后评估，但自动化模型对组织类型和图像采集方式的差异仍然敏感。我们提出了MiTHras，一个任务特定的预训练框架，该框架将伪标签引导的图像级和令牌级对比学习与掩码重建相结合。我们构建了TCGA-MF-Pseudo，一个包含来自14个TCGA队列、涵盖11个器官部位的180万张细胞中心图像的数据集。在MF分类、检测、基于计数的生存预测和亚型分类上的全面评估证明了MiTHras的有效性。它在所有三个MF分类基准和两个亚型基准上取得了最高的平均F1分数。在冻结编码器线性探针设置下，MiTHras相比通用和病理学基础编码器的优势大于完全微调设置。尽管由于共享候选检测阶段，检测性能提升有限，但消融实验证实，令牌级监督改善了典型与非典型分类以及线性探针性能。这些发现表明，MiTHras为自动化有丝分裂活性评估产生了稳健且可迁移的表征。
英文摘要
Mitotic figure (MF) analysis supports tumor grading and prognostic assessment, but automated models remain sensitive to differences in tissue type and image acquisition. We present MiTHras, a task-specific pretraining framework that combines pseudo-label-guided image- and token-level contrastive learning with masked reconstruction. We construct TCGA-MF-Pseudo, a corpus of 1.8 million cell-centered images from 14 TCGA cohorts spanning 11 organ sites. Comprehensive evaluation on MF classification, detection, count-based survival prediction, and subtype classification demonstrates the efficacy of MiTHras. It achieves the highest mean F1 on all three MF classification benchmarks and both subtype benchmarks. MiTHras also outperforms general-purpose and pathology foundation encoders by a larger margin under frozen-encoder linear probing than under full fine-tuning. Although detection gains are modest due to a shared candidate-detection stage, ablations confirm that token-level supervision improves typical-versus-atypical classification and linear probing. These findings establish that MiTHras yields robust, transferable representations for automated mitotic activity assessment.
发表机构
- Korea University（高丽大学）
- University Medical Center Ho Chi Minh City（胡志明市大学医学中心）
- Histofy Ltd（Histofy 有限公司）
机构由 AI 辅助整理，请以论文原文为准。
