Distilling High Diagnostic Value Patches for Whole Slide Image Classification Using Attention Mechanism

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nan, Tianhang, Quan, Hao, Ding, Yong, Li, Xingyu, Yang, Kai, Cui, Xiaoyu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911040066813952
author Nan, Tianhang
Quan, Hao
Ding, Yong
Li, Xingyu
Yang, Kai
Cui, Xiaoyu
author_facet Nan, Tianhang
Quan, Hao
Ding, Yong
Li, Xingyu
Yang, Kai
Cui, Xiaoyu
contents Multiple Instance Learning (MIL) has garnered widespread attention in the field of Whole Slide Image (WSI) classification as it replaces pixel-level manual annotation with diagnostic reports as labels, significantly reducing labor costs. Recent research has shown that bag-level MIL methods often yield better results because they can consider all patches of the WSI as a whole. However, a drawback of such methods is the incorporation of more redundant patches, leading to interference. To extract patches with high diagnostic value while excluding interfering patches to address this issue, we developed an attention-based feature distillation multi-instance learning (AFD-MIL) approach. This approach proposed the exclusion of redundant patches as a preprocessing operation in weakly supervised learning, directly mitigating interference from extensive noise. It also pioneers the use of attention mechanisms to distill features with high diagnostic value, as opposed to the traditional practice of indiscriminately and forcibly integrating all patches. Additionally, we introduced global loss optimization to finely control the feature distillation module. AFD-MIL is orthogonal to many existing MIL methods, leading to consistent performance improvements. This approach has surpassed the current state-of-the-art method, achieving 91.47% ACC (accuracy) and 94.29% AUC (area under the curve) on the Camelyon16 (Camelyon Challenge 2016, breast cancer), while 93.33% ACC and 98.17% AUC on the TCGA-NSCLC (The Cancer Genome Atlas Program: non-small cell lung cancer). Different feature distillation methods were used for the two datasets, tailored to the specific diseases, thereby improving performance and interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2407_19821
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Distilling High Diagnostic Value Patches for Whole Slide Image Classification Using Attention Mechanism
Nan, Tianhang
Quan, Hao
Ding, Yong
Li, Xingyu
Yang, Kai
Cui, Xiaoyu
Image and Video Processing
Computer Vision and Pattern Recognition
Tissues and Organs
Multiple Instance Learning (MIL) has garnered widespread attention in the field of Whole Slide Image (WSI) classification as it replaces pixel-level manual annotation with diagnostic reports as labels, significantly reducing labor costs. Recent research has shown that bag-level MIL methods often yield better results because they can consider all patches of the WSI as a whole. However, a drawback of such methods is the incorporation of more redundant patches, leading to interference. To extract patches with high diagnostic value while excluding interfering patches to address this issue, we developed an attention-based feature distillation multi-instance learning (AFD-MIL) approach. This approach proposed the exclusion of redundant patches as a preprocessing operation in weakly supervised learning, directly mitigating interference from extensive noise. It also pioneers the use of attention mechanisms to distill features with high diagnostic value, as opposed to the traditional practice of indiscriminately and forcibly integrating all patches. Additionally, we introduced global loss optimization to finely control the feature distillation module. AFD-MIL is orthogonal to many existing MIL methods, leading to consistent performance improvements. This approach has surpassed the current state-of-the-art method, achieving 91.47% ACC (accuracy) and 94.29% AUC (area under the curve) on the Camelyon16 (Camelyon Challenge 2016, breast cancer), while 93.33% ACC and 98.17% AUC on the TCGA-NSCLC (The Cancer Genome Atlas Program: non-small cell lung cancer). Different feature distillation methods were used for the two datasets, tailored to the specific diseases, thereby improving performance and interpretability.
title Distilling High Diagnostic Value Patches for Whole Slide Image Classification Using Attention Mechanism
topic Image and Video Processing
Computer Vision and Pattern Recognition
Tissues and Organs
url https://arxiv.org/abs/2407.19821