arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2506.18668cs.CVcs.AI

在多中心皮肤癌亚型数据集中基准测试组织病理学基础模型

Benchmarking histopathology foundation models in a multi-center dataset for skin cancer subtyping

Universitat Politècnica de València (UPV)(瓦伦西亚理工大学);Artikode Intelligence S.L.(Artikode Intelligence公司)

Pablo Meseguer, Rocío del Amor, Valery Naranjo

AI总结:

本文提出一个基于AI4SkIN多中心数据集的基准,用于评估组织病理学基础模型在MIL分类框架中作为补丁级特征提取器的表现,并引入FM-SI指标衡量模型在分布偏移下的一致性,发现低偏差特征可提升分类性能。

摘要:

在大规模领域内数据集上进行预训练,使组织病理学基础模型(FM)具备学习任务无关数据表示的能力,从而增强下游任务的迁移学习。在计算病理学中,由于全切片图像的千兆像素规模,自动化全切片图像分析需要多实例学习(MIL)框架。组织病理学基础模型之间的多样性凸显了设计真实世界挑战以评估其有效性的必要性。为弥合这一差距,我们的工作提出了一个新颖的基准,用于在MIL分类框架内将组织病理学基础模型作为补丁级特征提取器进行评估。为此,我们利用AI4SkIN数据集,这是一个多中心队列,包含具有挑战性的皮肤梭形细胞肿瘤亚型的切片。我们还定义了基础模型-轮廓指数(FM-SI),这是一种衡量模型在分布偏移下一致性的新颖指标。我们的实验表明,提取偏差较小的特征能够提升分类性能,尤其是在基于相似性的MIL分类器中。

英文摘要:

Pretraining on large-scale, in-domain datasets grants histopathology foundation models (FM) the ability to learn task-agnostic data representations, enhancing transfer learning on downstream tasks. In computational pathology, automated whole slide image analysis requires multiple instance learning (MIL) frameworks due to the gigapixel scale of the slides. The diversity among histopathology FMs has highlighted the need to design real-world challenges for evaluating their effectiveness. To bridge this gap, our work presents a novel benchmark for evaluating histopathology FMs as patch-level feature extractors within a MIL classification framework. For that purpose, we leverage the AI4SkIN dataset, a multi-center cohort encompassing slides with challenging cutaneous spindle cell neoplasm subtypes. We also define the Foundation Model - Silhouette Index (FM-SI), a novel metric to measure model consistency against distribution shifts. Our experimentation shows that extracting less biased features enhances classification performance, especially in similarity-based MIL classifiers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑