Agent Aggregator with Mask Denoise Mechanism for Histopathology Whole Slide Image Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ling, Xitong, Ouyang, Minxi, Wang, Yizhi, Chen, Xinrui, Yan, Renao, Chu, Hongbo, Cheng, Junru, Guan, Tian, Tian, Sufang, Liu, Xiaoping, He, Yonghong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914951728201728
author Ling, Xitong
Ouyang, Minxi
Wang, Yizhi
Chen, Xinrui
Yan, Renao
Chu, Hongbo
Cheng, Junru
Guan, Tian
Tian, Sufang
Liu, Xiaoping
He, Yonghong
author_facet Ling, Xitong
Ouyang, Minxi
Wang, Yizhi
Chen, Xinrui
Yan, Renao
Chu, Hongbo
Cheng, Junru
Guan, Tian
Tian, Sufang
Liu, Xiaoping
He, Yonghong
contents Histopathology analysis is the gold standard for medical diagnosis. Accurate classification of whole slide images (WSIs) and region-of-interests (ROIs) localization can assist pathologists in diagnosis. The gigapixel resolution of WSI and the absence of fine-grained annotations make direct classification and analysis challenging. In weakly supervised learning, multiple instance learning (MIL) presents a promising approach for WSI classification. The prevailing strategy is to use attention mechanisms to measure instance importance for classification. However, attention mechanisms fail to capture inter-instance information, and self-attention causes quadratic computational complexity. To address these challenges, we propose AMD-MIL, an agent aggregator with a mask denoise mechanism. The agent token acts as an intermediate variable between the query and key for computing instance importance. Mask and denoising matrices, mapped from agents-aggregated value, dynamically mask low-contribution representations and eliminate noise. AMD-MIL achieves better attention allocation by adjusting feature representations, capturing micro-metastases in cancer, and improving interpretability. Extensive experiments on CAMELYON-16, CAMELYON-17, TCGA-KIDNEY, and TCGA-LUNG show AMD-MIL's superiority over state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2409_11664
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Agent Aggregator with Mask Denoise Mechanism for Histopathology Whole Slide Image Analysis
Ling, Xitong
Ouyang, Minxi
Wang, Yizhi
Chen, Xinrui
Yan, Renao
Chu, Hongbo
Cheng, Junru
Guan, Tian
Tian, Sufang
Liu, Xiaoping
He, Yonghong
Computer Vision and Pattern Recognition
Artificial Intelligence
Histopathology analysis is the gold standard for medical diagnosis. Accurate classification of whole slide images (WSIs) and region-of-interests (ROIs) localization can assist pathologists in diagnosis. The gigapixel resolution of WSI and the absence of fine-grained annotations make direct classification and analysis challenging. In weakly supervised learning, multiple instance learning (MIL) presents a promising approach for WSI classification. The prevailing strategy is to use attention mechanisms to measure instance importance for classification. However, attention mechanisms fail to capture inter-instance information, and self-attention causes quadratic computational complexity. To address these challenges, we propose AMD-MIL, an agent aggregator with a mask denoise mechanism. The agent token acts as an intermediate variable between the query and key for computing instance importance. Mask and denoising matrices, mapped from agents-aggregated value, dynamically mask low-contribution representations and eliminate noise. AMD-MIL achieves better attention allocation by adjusting feature representations, capturing micro-metastases in cancer, and improving interpretability. Extensive experiments on CAMELYON-16, CAMELYON-17, TCGA-KIDNEY, and TCGA-LUNG show AMD-MIL's superiority over state-of-the-art methods.
title Agent Aggregator with Mask Denoise Mechanism for Histopathology Whole Slide Image Analysis
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2409.11664