KEXNet: A Knowledge-Enhanced Model for Improved Chest X-Ray Lesion Detection

Automated diagnosis of chest X-rays is pivotal in radiology, aiming to alleviate the workload of radiologists. Traditional methods primarily rely on visual features or label dependence, which is a limitation in detecting nuanced or rare lesions. To address this, we present KEXNet, a pioneering knowl...

Full description

Saved in:
Bibliographic Details
Main Authors: Quan Yan, Junwen Duan, Jianxin Wang
Format: Article
Language:English
Published: Tsinghua University Press 2024-12-01
Series:Big Data Mining and Analytics
Subjects:
Online Access:https://www.sciopen.com/article/10.26599/BDMA.2024.9020045
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850249584036544512
author Quan Yan
Junwen Duan
Jianxin Wang
author_facet Quan Yan
Junwen Duan
Jianxin Wang
author_sort Quan Yan
collection DOAJ
description Automated diagnosis of chest X-rays is pivotal in radiology, aiming to alleviate the workload of radiologists. Traditional methods primarily rely on visual features or label dependence, which is a limitation in detecting nuanced or rare lesions. To address this, we present KEXNet, a pioneering knowledge-enhanced X-ray lesion detection model. KEXNet employs a unique strategy akin to expert radiologists, integrating a knowledge graph based on expert annotations with an interpretable graph learning approach. This novel method combines object detection with a graph neural network, facilitating precise local lesion detection. For global lesion detection, KEXNet synergizes knowledge-enhanced local features with global image features, enhancing diagnostic accuracy. Our evaluations on three benchmark datasets demonstrate that KEXNet outshines existing models, particularly in identifying small or infrequent lesions. Notably, on the Chest ImaGenome dataset, KEXNet’s AUC for local lesion detection surpasses 8.9% compared to the state-of-the-art method AnaXNet, showcasing its potential in revolutionizing automated chest X-ray diagnostics.
format Article
id doaj-art-95c49182c7304bcdac3282f5fccf9e44
institution OA Journals
issn 2096-0654
language English
publishDate 2024-12-01
publisher Tsinghua University Press
record_format Article
series Big Data Mining and Analytics
spelling doaj-art-95c49182c7304bcdac3282f5fccf9e442025-08-20T01:58:28ZengTsinghua University PressBig Data Mining and Analytics2096-06542024-12-01741187119810.26599/BDMA.2024.9020045KEXNet: A Knowledge-Enhanced Model for Improved Chest X-Ray Lesion DetectionQuan Yan0Junwen Duan1Jianxin Wang2School of Computer Science and Engineering and Hunan Provincial Key Lab on Bioinformatics, Central South University, Changsha 410083, ChinaSchool of Computer Science and Engineering and Hunan Provincial Key Lab on Bioinformatics, Central South University, Changsha 410083, ChinaSchool of Computer Science and Engineering and Hunan Provincial Key Lab on Bioinformatics, Central South University, Changsha 410083, ChinaAutomated diagnosis of chest X-rays is pivotal in radiology, aiming to alleviate the workload of radiologists. Traditional methods primarily rely on visual features or label dependence, which is a limitation in detecting nuanced or rare lesions. To address this, we present KEXNet, a pioneering knowledge-enhanced X-ray lesion detection model. KEXNet employs a unique strategy akin to expert radiologists, integrating a knowledge graph based on expert annotations with an interpretable graph learning approach. This novel method combines object detection with a graph neural network, facilitating precise local lesion detection. For global lesion detection, KEXNet synergizes knowledge-enhanced local features with global image features, enhancing diagnostic accuracy. Our evaluations on three benchmark datasets demonstrate that KEXNet outshines existing models, particularly in identifying small or infrequent lesions. Notably, on the Chest ImaGenome dataset, KEXNet’s AUC for local lesion detection surpasses 8.9% compared to the state-of-the-art method AnaXNet, showcasing its potential in revolutionizing automated chest X-ray diagnostics.https://www.sciopen.com/article/10.26599/BDMA.2024.9020045multi-label chest x-ray classificationobject detectionknowledge graph learning
spellingShingle Quan Yan
Junwen Duan
Jianxin Wang
KEXNet: A Knowledge-Enhanced Model for Improved Chest X-Ray Lesion Detection
Big Data Mining and Analytics
multi-label chest x-ray classification
object detection
knowledge graph learning
title KEXNet: A Knowledge-Enhanced Model for Improved Chest X-Ray Lesion Detection
title_full KEXNet: A Knowledge-Enhanced Model for Improved Chest X-Ray Lesion Detection
title_fullStr KEXNet: A Knowledge-Enhanced Model for Improved Chest X-Ray Lesion Detection
title_full_unstemmed KEXNet: A Knowledge-Enhanced Model for Improved Chest X-Ray Lesion Detection
title_short KEXNet: A Knowledge-Enhanced Model for Improved Chest X-Ray Lesion Detection
title_sort kexnet a knowledge enhanced model for improved chest x ray lesion detection
topic multi-label chest x-ray classification
object detection
knowledge graph learning
url https://www.sciopen.com/article/10.26599/BDMA.2024.9020045
work_keys_str_mv AT quanyan kexnetaknowledgeenhancedmodelforimprovedchestxraylesiondetection
AT junwenduan kexnetaknowledgeenhancedmodelforimprovedchestxraylesiondetection
AT jianxinwang kexnetaknowledgeenhancedmodelforimprovedchestxraylesiondetection