PulseAugur
中
实时 11:20:04
English(EN) MergeSurv: Merging-Based Continual Learning for Survival Analysis on Whole-Slide Images

新方法推进病理图像分析的持续学习 · 跟踪5个来源

作者 PulseAugur 编辑部 · [5 个来源] ·

研究人员开发了计算病理学中持续学习的两种新方法，重点关注全切片图像（WSI）的生存分析。第一种方法MergeSurv采用基于合并的框架，其中病理视觉语言基础模型在各个癌症队列上进行微调，并按顺序合并其参数。该方法及其推理策略One-for-All (OFA) 和 Voting-Expert Aggregation (VEA) 在TCGA队列的实验中，表现优于朴素微调和其他持续学习技术，有效缓解了灾难性遗忘。第二种方法将模型合并与测试时自适应（TTA）进行基准测试，用于无重放的持续WSI分类。该方法在不存储历史数据的情况下，在保持任务特定性能和保留知识方面显示出潜力，尽管其有效性对任务顺序以及自适应与知识保留之间的平衡敏感。 AI

影响 计算病理学中持续学习的这些进展可能带来更高效、可扩展的诊断工具，从而改善预后估计和治疗计划。

排序理由 两篇发表在arXiv上的研究论文，详细介绍了计算病理学中持续学习的新方法。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →

新方法推进病理图像分析的持续学习 · 跟踪5个来源

报道来源 [5]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    MergeSurv: Merging-Based Continual Learning for Survival Analysis on Whole-Slide Images

    Survival analysis on Whole Slide Images (WSIs) is important in computational pathology for prognosis estimation and treatment planning. However, existing survival models are typically trained independently for each cancer cohort, making continual adaptation computationally expens…

  2. arXiv cs.CV TIER_1 English(EN) · Vu Minh Tran, Doanh C. Bui, Ma\"i K. Nguyen, Khang Nguyen ·

    MergeSurv: Merging-Based Continual Learning for Survival Analysis on Whole-Slide Images

    arXiv:2607.04747v1 Announce Type: new Abstract: Survival analysis on Whole Slide Images (WSIs) is important in computational pathology for prognosis estimation and treatment planning. However, existing survival models are typically trained independently for each cancer cohort, ma…

  3. arXiv cs.CV TIER_1 English(EN) · Duc-Thanh Le, Doanh C. Bui, Ma\"i K. Nguyen, Khang Nguyen ·

    Continual Model Merging with Test-Time Adaptation for Whole-Slide Image Analysis

    arXiv:2607.04755v1 Announce Type: new Abstract: Model merging offers a practical alternative to conventional continual learning by integrating independently fine-tuned models without retaining previous training data. Recent state-of-the-art model merging methods employ test-time …

  4. arXiv cs.CV TIER_1 English(EN) · Khang Nguyen ·

    面向全切片图像分析的带测试时自适应的持续模型合并

    Model merging offers a practical alternative to conventional continual learning by integrating independently fine-tuned models without retaining previous training data. Recent state-of-the-art model merging methods employ test-time adaptation (TTA-guided merging) to address distr…

  5. arXiv cs.CV TIER_1 English(EN) · Khang Nguyen ·

    MergeSurv：基于合并的持续学习在全切片图像上的生存分析

    Survival analysis on Whole Slide Images (WSIs) is important in computational pathology for prognosis estimation and treatment planning. However, existing survival models are typically trained independently for each cancer cohort, making continual adaptation computationally expens…

相关实体

相关话题