A Clinical-oriented Multi-level Contrastive Learning Method for Disease Diagnosis in Low-quality Medical Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hou, Qingshan, Cheng, Shuai, Cao, Peng, Yang, Jinzhu, Liu, Xiaoli, Zaiane, Osmar R., Tham, Yih Chung
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929305053822976
author Hou, Qingshan
Cheng, Shuai
Cao, Peng
Yang, Jinzhu
Liu, Xiaoli
Zaiane, Osmar R.
Tham, Yih Chung
author_facet Hou, Qingshan
Cheng, Shuai
Cao, Peng
Yang, Jinzhu
Liu, Xiaoli
Zaiane, Osmar R.
Tham, Yih Chung
contents Representation learning offers a conduit to elucidate distinctive features within the latent space and interpret the deep models. However, the randomness of lesion distribution and the complexity of low-quality factors in medical images pose great challenges for models to extract key lesion features. Disease diagnosis methods guided by contrastive learning (CL) have shown significant advantages in lesion feature representation. Nevertheless, the effectiveness of CL is highly dependent on the quality of the positive and negative sample pairs. In this work, we propose a clinical-oriented multi-level CL framework that aims to enhance the model's capacity to extract lesion features and discriminate between lesion and low-quality factors, thereby enabling more accurate disease diagnosis from low-quality medical images. Specifically, we first construct multi-level positive and negative pairs to enhance the model's comprehensive recognition capability of lesion features by integrating information from different levels and qualities of medical images. Moreover, to improve the quality of the learned lesion embeddings, we introduce a dynamic hard sample mining method based on self-paced learning. The proposed CL framework is validated on two public medical image datasets, EyeQ and Chest X-ray, demonstrating superior performance compared to other state-of-the-art disease diagnostic methods.
format Preprint
id arxiv_https___arxiv_org_abs_2404_04887
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Clinical-oriented Multi-level Contrastive Learning Method for Disease Diagnosis in Low-quality Medical Images
Hou, Qingshan
Cheng, Shuai
Cao, Peng
Yang, Jinzhu
Liu, Xiaoli
Zaiane, Osmar R.
Tham, Yih Chung
Computer Vision and Pattern Recognition
Representation learning offers a conduit to elucidate distinctive features within the latent space and interpret the deep models. However, the randomness of lesion distribution and the complexity of low-quality factors in medical images pose great challenges for models to extract key lesion features. Disease diagnosis methods guided by contrastive learning (CL) have shown significant advantages in lesion feature representation. Nevertheless, the effectiveness of CL is highly dependent on the quality of the positive and negative sample pairs. In this work, we propose a clinical-oriented multi-level CL framework that aims to enhance the model's capacity to extract lesion features and discriminate between lesion and low-quality factors, thereby enabling more accurate disease diagnosis from low-quality medical images. Specifically, we first construct multi-level positive and negative pairs to enhance the model's comprehensive recognition capability of lesion features by integrating information from different levels and qualities of medical images. Moreover, to improve the quality of the learned lesion embeddings, we introduce a dynamic hard sample mining method based on self-paced learning. The proposed CL framework is validated on two public medical image datasets, EyeQ and Chest X-ray, demonstrating superior performance compared to other state-of-the-art disease diagnostic methods.
title A Clinical-oriented Multi-level Contrastive Learning Method for Disease Diagnosis in Low-quality Medical Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.04887