Saved in:
Bibliographic Details
Main Authors: Li, Xinyang, Zhang, Yi, Xie, Yi, Yang, Jianfei, Wang, Xi, Chen, Hao, Zhang, Haixian
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.11487
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917847156916224
author Li, Xinyang
Zhang, Yi
Xie, Yi
Yang, Jianfei
Wang, Xi
Chen, Hao
Zhang, Haixian
author_facet Li, Xinyang
Zhang, Yi
Xie, Yi
Yang, Jianfei
Wang, Xi
Chen, Hao
Zhang, Haixian
contents Survival prediction is a critical task in pathology. In clinical practice, pathologists often examine multiple cases, leveraging a broader spectrum of cancer phenotypes to enhance pathological assessment. Despite significant advancements in deep learning, current solutions typically model each slide as a sample, struggling to effectively capture comparable and slide-agnostic pathological features. In this paper, we introduce GroupMIL, a novel framework inspired by the clinical practice of collective analysis, which models multiple slides as a single sample and organizes groups of patches and slides sequentially to capture cross-slide prognostic features. We also present GPAMamba, a model designed to facilitate intra- and inter-slide feature interactions, effectively capturing local micro-environmental characteristics within slide-level graphs while uncovering essential prognostic patterns across an extended patch sequence within the group framework. Furthermore, we develop a dual-head predictor that delivers comprehensive survival risk and probability assessments for each patient. Extensive empirical evaluations demonstrate that our model significantly outperforms state-of-the-art approaches across five datasets from The Cancer Genome Atlas.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11487
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Look a Group at Once: Multi-Slide Modeling for Survival Prediction
Li, Xinyang
Zhang, Yi
Xie, Yi
Yang, Jianfei
Wang, Xi
Chen, Hao
Zhang, Haixian
Computer Vision and Pattern Recognition
Survival prediction is a critical task in pathology. In clinical practice, pathologists often examine multiple cases, leveraging a broader spectrum of cancer phenotypes to enhance pathological assessment. Despite significant advancements in deep learning, current solutions typically model each slide as a sample, struggling to effectively capture comparable and slide-agnostic pathological features. In this paper, we introduce GroupMIL, a novel framework inspired by the clinical practice of collective analysis, which models multiple slides as a single sample and organizes groups of patches and slides sequentially to capture cross-slide prognostic features. We also present GPAMamba, a model designed to facilitate intra- and inter-slide feature interactions, effectively capturing local micro-environmental characteristics within slide-level graphs while uncovering essential prognostic patterns across an extended patch sequence within the group framework. Furthermore, we develop a dual-head predictor that delivers comprehensive survival risk and probability assessments for each patient. Extensive empirical evaluations demonstrate that our model significantly outperforms state-of-the-art approaches across five datasets from The Cancer Genome Atlas.
title Look a Group at Once: Multi-Slide Modeling for Survival Prediction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.11487