Multimodal Medical Endoscopic Image Analysis via Progressive Disentangle-aware Contrastive Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Junhao, Li, Yun, Li, Junhao, Bian, Jingliang, Fan, Xiaomao, Lei, Wenbin, Wang, Ruxin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912551275593728
author Wu, Junhao
Li, Yun
Li, Junhao
Bian, Jingliang
Fan, Xiaomao
Lei, Wenbin
Wang, Ruxin
author_facet Wu, Junhao
Li, Yun
Li, Junhao
Bian, Jingliang
Fan, Xiaomao
Lei, Wenbin
Wang, Ruxin
contents Accurate segmentation of laryngo-pharyngeal tumors is crucial for precise diagnosis and effective treatment planning. However, traditional single-modality imaging methods often fall short of capturing the complex anatomical and pathological features of these tumors. In this study, we present an innovative multi-modality representation learning framework based on the `Align-Disentangle-Fusion' mechanism that seamlessly integrates 2D White Light Imaging (WLI) and Narrow Band Imaging (NBI) pairs to enhance segmentation performance. A cornerstone of our approach is multi-scale distribution alignment, which mitigates modality discrepancies by aligning features across multiple transformer layers. Furthermore, a progressive feature disentanglement strategy is developed with the designed preliminary disentanglement and disentangle-aware contrastive learning to effectively separate modality-specific and shared features, enabling robust multimodal contrastive learning and efficient semantic fusion. Comprehensive experiments on multiple datasets demonstrate that our method consistently outperforms state-of-the-art approaches, achieving superior accuracy across diverse real clinical scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16882
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multimodal Medical Endoscopic Image Analysis via Progressive Disentangle-aware Contrastive Learning
Wu, Junhao
Li, Yun
Li, Junhao
Bian, Jingliang
Fan, Xiaomao
Lei, Wenbin
Wang, Ruxin
Image and Video Processing
Computer Vision and Pattern Recognition
Accurate segmentation of laryngo-pharyngeal tumors is crucial for precise diagnosis and effective treatment planning. However, traditional single-modality imaging methods often fall short of capturing the complex anatomical and pathological features of these tumors. In this study, we present an innovative multi-modality representation learning framework based on the `Align-Disentangle-Fusion' mechanism that seamlessly integrates 2D White Light Imaging (WLI) and Narrow Band Imaging (NBI) pairs to enhance segmentation performance. A cornerstone of our approach is multi-scale distribution alignment, which mitigates modality discrepancies by aligning features across multiple transformer layers. Furthermore, a progressive feature disentanglement strategy is developed with the designed preliminary disentanglement and disentangle-aware contrastive learning to effectively separate modality-specific and shared features, enabling robust multimodal contrastive learning and efficient semantic fusion. Comprehensive experiments on multiple datasets demonstrate that our method consistently outperforms state-of-the-art approaches, achieving superior accuracy across diverse real clinical scenarios.
title Multimodal Medical Endoscopic Image Analysis via Progressive Disentangle-aware Contrastive Learning
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.16882