Saved in:
Bibliographic Details
Main Authors: Yan, Renao, Sun, Qiehe, Jin, Cheng, Liu, Yiqing, He, Yonghong, Guan, Tian, Chen, Hao
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.05490
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929486880047104
author Yan, Renao
Sun, Qiehe
Jin, Cheng
Liu, Yiqing
He, Yonghong
Guan, Tian
Chen, Hao
author_facet Yan, Renao
Sun, Qiehe
Jin, Cheng
Liu, Yiqing
He, Yonghong
Guan, Tian
Chen, Hao
contents In computational pathology, whole-slide image (WSI) classification presents a formidable challenge due to its gigapixel resolution and limited fine-grained annotations. Multiple-instance learning (MIL) offers a weakly supervised solution, yet refining instance-level information from bag-level labels remains challenging. While most of the conventional MIL methods use attention scores to estimate instance importance scores (IIS) which contribute to the prediction of the slide labels, these often lead to skewed attention distributions and inaccuracies in identifying crucial instances. To address these issues, we propose a new approach inspired by cooperative game theory: employing Shapley values to assess each instance's contribution, thereby improving IIS estimation. The computation of the Shapley value is then accelerated using attention, meanwhile retaining the enhanced instance identification and prioritization. We further introduce a framework for the progressive assignment of pseudo bags based on estimated IIS, encouraging more balanced attention distributions in MIL models. Our extensive experiments on CAMELYON-16, BRACS, TCGA-LUNG, and TCGA-BRCA datasets show our method's superiority over existing state-of-the-art approaches, offering enhanced interpretability and class-wise insights. Our source code is available at https://github.com/RenaoYan/PMIL.
format Preprint
id arxiv_https___arxiv_org_abs_2312_05490
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Shapley Values-enabled Progressive Pseudo Bag Augmentation for Whole Slide Image Classification
Yan, Renao
Sun, Qiehe
Jin, Cheng
Liu, Yiqing
He, Yonghong
Guan, Tian
Chen, Hao
Computer Vision and Pattern Recognition
In computational pathology, whole-slide image (WSI) classification presents a formidable challenge due to its gigapixel resolution and limited fine-grained annotations. Multiple-instance learning (MIL) offers a weakly supervised solution, yet refining instance-level information from bag-level labels remains challenging. While most of the conventional MIL methods use attention scores to estimate instance importance scores (IIS) which contribute to the prediction of the slide labels, these often lead to skewed attention distributions and inaccuracies in identifying crucial instances. To address these issues, we propose a new approach inspired by cooperative game theory: employing Shapley values to assess each instance's contribution, thereby improving IIS estimation. The computation of the Shapley value is then accelerated using attention, meanwhile retaining the enhanced instance identification and prioritization. We further introduce a framework for the progressive assignment of pseudo bags based on estimated IIS, encouraging more balanced attention distributions in MIL models. Our extensive experiments on CAMELYON-16, BRACS, TCGA-LUNG, and TCGA-BRCA datasets show our method's superiority over existing state-of-the-art approaches, offering enhanced interpretability and class-wise insights. Our source code is available at https://github.com/RenaoYan/PMIL.
title Shapley Values-enabled Progressive Pseudo Bag Augmentation for Whole Slide Image Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.05490