An Attentive Dual-Encoder Framework Leveraging Multimodal Visual and Semantic Information for Automatic OSAHS Diagnosis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wei, Yingchen, Qiu, Xihe, Tan, Xiaoyu, Huang, Jingjing, Chu, Wei, Xu, Yinghui, Qi, Yuan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913627148124160
author Wei, Yingchen
Qiu, Xihe
Tan, Xiaoyu
Huang, Jingjing
Chu, Wei
Xu, Yinghui
Qi, Yuan
author_facet Wei, Yingchen
Qiu, Xihe
Tan, Xiaoyu
Huang, Jingjing
Chu, Wei
Xu, Yinghui
Qi, Yuan
contents Obstructive sleep apnea-hypopnea syndrome (OSAHS) is a common sleep disorder caused by upper airway blockage, leading to oxygen deprivation and disrupted sleep. Traditional diagnosis using polysomnography (PSG) is expensive, time-consuming, and uncomfortable. Existing deep learning methods using facial image analysis lack accuracy due to poor facial feature capture and limited sample sizes. To address this, we propose a multimodal dual encoder model that integrates visual and language inputs for automated OSAHS diagnosis. The model balances data using randomOverSampler, extracts key facial features with attention grids, and converts physiological data into meaningful text. Cross-attention combines image and text data for better feature extraction, and ordered regression loss ensures stable learning. Our approach improves diagnostic efficiency and accuracy, achieving 91.3% top-1 accuracy in a four-class severity classification task, demonstrating state-of-the-art performance. Code will be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18919
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Attentive Dual-Encoder Framework Leveraging Multimodal Visual and Semantic Information for Automatic OSAHS Diagnosis
Wei, Yingchen
Qiu, Xihe
Tan, Xiaoyu
Huang, Jingjing
Chu, Wei
Xu, Yinghui
Qi, Yuan
Computer Vision and Pattern Recognition
Machine Learning
Obstructive sleep apnea-hypopnea syndrome (OSAHS) is a common sleep disorder caused by upper airway blockage, leading to oxygen deprivation and disrupted sleep. Traditional diagnosis using polysomnography (PSG) is expensive, time-consuming, and uncomfortable. Existing deep learning methods using facial image analysis lack accuracy due to poor facial feature capture and limited sample sizes. To address this, we propose a multimodal dual encoder model that integrates visual and language inputs for automated OSAHS diagnosis. The model balances data using randomOverSampler, extracts key facial features with attention grids, and converts physiological data into meaningful text. Cross-attention combines image and text data for better feature extraction, and ordered regression loss ensures stable learning. Our approach improves diagnostic efficiency and accuracy, achieving 91.3% top-1 accuracy in a four-class severity classification task, demonstrating state-of-the-art performance. Code will be released upon acceptance.
title An Attentive Dual-Encoder Framework Leveraging Multimodal Visual and Semantic Information for Automatic OSAHS Diagnosis
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2412.18919