EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LMeRAN: Label Masking-Enhanced Residual Attention Network for Multi-Label Chest X-Ray Disease Aided Diagnosis

Hongping Fu, Chao Song iD, Xiaolong Qu iD, Dongmei Li iD, Lei Zhang iD

Sensors · 2025

DOI: 10.3390/s25185676 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Hongping Fu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China. Hauptthemen laut MEDLINE: Radiography, Thoracic, Diagnosis, Computer-Assisted, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities, Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Chest X-ray (CXR) imaging is essential for diagnosing thoracic diseases, and computer-aided diagnosis (CAD) systems have made substantial progress in automating the interpretation of CXR images. However, some existing methods often overemphasize local features while neglecting global context, limiting their ability to capture the broader pathological landscape. Moreover, most methods fail to model label correlations, leading to insufficient utilization of prior knowledge. To address these limitations, we propose a novel multi-label CXR image classification framework, termed the Label Masking-enhanced Residual Attention Network (LMeRAN). Specifically, LMeRAN introduces an original label-specific residual attention to capture disease-relevant information effectively. By integrating multi-head self-attention with average pooling, the model dynamically assigns higher weights to critical lesion areas while retaining global contextual features. In addition, LMeRAN employs a label mask training strategy, enabling the model to learn complex label dependencies from partially available label information. Experiments conducted on the large-scale public dataset ChestX-ray14 demonstrate that LMeRAN achieves the highest mean AUC value of 0.825, resulting in an increase of 3.1% to 8.0% over several advanced baselines. To enhance interpretability, we also visualize the lesion regions relied upon by the model for classification, providing clearer insights into the model’s decision-making process.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Radiography, ThoracicDiagnosis, Computer-AssistedRadiographic Image Interpretation, Computer-AssistedHumansAlgorithmsNeural Networks, ComputerX-Rays

Stichwörter der Autor:innen

attention mechanismchest X-raycomputer-aided diagnosislabel mask trainingmulti-label classification

Autor:innen und Institutionen

  • School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China.
  • Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration, Beijing 100083, China.
  • National Data Center of Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100083, China.

ORCID-Profile: Chao Song, Xiaolong Qu, Dongmei Li, Lei Zhang

Förderung

  • Fundamental Research Funds for the Central Universities
  • Natural Science Foundation of China

Zitieren

APA

Fu, H., Song, C., Qu, X., Li, D., & Zhang, L. (2025). LMeRAN: Label Masking-Enhanced Residual Attention Network for Multi-Label Chest X-Ray Disease Aided Diagnosis. Sensors. https://doi.org/10.3390/s25185676

Vancouver

Fu H, Song C, Qu X, Li D, Zhang L. LMeRAN: Label Masking-Enhanced Residual Attention Network for Multi-Label Chest X-Ray Disease Aided Diagnosis. Sensors. 2025. doi:10.3390/s25185676

BibTeX
@article{Fu2025,
  author = {Fu, Hongping and Song, Chao and Qu, Xiaolong and Li, Dongmei and Zhang, Lei},
  title = {LMeRAN: Label Masking-Enhanced Residual Attention Network for Multi-Label Chest X-Ray Disease Aided Diagnosis},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25185676}
}
Kostenlos starten →