A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model

基础(证据) 计算机科学 病理 医学 地理 考古
作者
Yingxue Xu,Yihui Wang,Fengtao Zhou,Jiabo Ma,Shu Yang,Huangjing Lin,Xuejun Wang,Ji‐Guang Wang,Li Liang,Anjia Han,Ronald Chan,Hao Chen
出处
期刊:Cornell University - arXiv
标识
DOI:10.48550/arxiv.2407.15362
摘要

Remarkable strides in computational pathology have been made in the task-agnostic foundation model that advances the performance of a wide array of downstream clinical tasks. Despite the promising performance, there are still several challenges. First, prior works have resorted to either vision-only or vision-captions data, disregarding invaluable pathology reports and gene expression profiles which respectively offer distinct knowledge for versatile clinical applications. Second, the current progress in pathology FMs predominantly concentrates on the patch level, where the restricted context of patch-level pretraining fails to capture whole-slide patterns. Here we curated the largest multimodal dataset consisting of H\&E diagnostic whole slide images and their associated pathology reports and RNA-Seq data, resulting in 26,169 slide-level modality pairs from 10,275 patients across 32 cancer types. To leverage these data for CPath, we propose a novel whole-slide pretraining paradigm which injects multimodal knowledge at the whole-slide context into the pathology FM, called Multimodal Self-TAught PRetraining (mSTAR). The proposed paradigm revolutionizes the workflow of pretraining for CPath, which enables the pathology FM to acquire the whole-slide context. To our knowledge, this is the first attempt to incorporate multimodal knowledge at the slide level for enhancing pathology FMs, expanding the modelling context from unimodal to multimodal knowledge and from patch-level to slide-level. To systematically evaluate the capabilities of mSTAR, extensive experiments including slide-level unimodal and multimodal applications, are conducted across 7 diverse types of tasks on 43 subtasks, resulting in the largest spectrum of downstream tasks. The average performance in various slide-level applications consistently demonstrates significant performance enhancements for mSTAR compared to SOTA FMs.

科研通智能强力驱动
Strongly Powered by AbleSci AI

祝大家在新的一年里科研腾飞
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
heavenhorse应助拾一采纳,获得10
刚刚
why完成签到,获得积分10
1秒前
忧伤的元菱完成签到,获得积分20
1秒前
晚晚发布了新的文献求助10
1秒前
Akim应助猛犸象冲冲冲采纳,获得10
3秒前
lan发布了新的文献求助10
3秒前
mr_beard完成签到 ,获得积分10
3秒前
薇薇一笑发布了新的文献求助10
4秒前
Ytwo完成签到,获得积分10
4秒前
王小头要查文献完成签到,获得积分10
5秒前
5秒前
5秒前
苏素完成签到,获得积分10
5秒前
5秒前
hongt05完成签到 ,获得积分10
6秒前
Cathy完成签到,获得积分10
6秒前
Tarahu完成签到,获得积分10
6秒前
brianzk1989完成签到,获得积分10
7秒前
我我完成签到 ,获得积分10
7秒前
mojibunny完成签到,获得积分10
7秒前
梅思双完成签到,获得积分10
7秒前
8秒前
成金陈发布了新的文献求助10
8秒前
xiaoying发布了新的文献求助10
8秒前
花花发布了新的文献求助10
8秒前
8秒前
9秒前
zyq完成签到,获得积分10
9秒前
研友_ZzMMRn完成签到,获得积分10
9秒前
如是之人发布了新的文献求助10
10秒前
蓝天白云发布了新的文献求助10
11秒前
俏皮芹完成签到,获得积分10
11秒前
投石问路完成签到,获得积分10
11秒前
筑梦完成签到,获得积分10
11秒前
liuguimin完成签到,获得积分10
11秒前
9sy完成签到,获得积分10
11秒前
晚晚完成签到,获得积分10
12秒前
852应助拉斯特迪亚采纳,获得10
12秒前
小兵发布了新的文献求助30
13秒前
13秒前
高分求助中
Востребованный временем 2500
The Three Stars Each: The Astrolabes and Related Texts 1500
Les Mantodea de Guyane 800
Mantids of the euro-mediterranean area 700
Plate Tectonics 500
Igneous rocks and processes: a practical guide(第二版) 500
Mantodea of the World: Species Catalog 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 物理化学 催化作用 细胞生物学 免疫学 冶金
热门帖子
关注 科研通微信公众号,转发送积分 3408846
求助须知:如何正确求助?哪些是违规求助? 3012784
关于积分的说明 8855969
捐赠科研通 2700132
什么是DOI,文献DOI怎么找? 1480218
科研通“疑难数据库(出版商)”最低求助积分说明 684251
邀请新用户注册赠送积分活动 678578