Multi-scale parallel perception and adaptive feature fusion for chest x-ray multi-disease detection
Physics in Medicine & Biology · 28.08.2026 · 71 (16) · 165004
DOI: 10.1088/1361-6560/ae970f ↗Kurz gefasst
Fachartikel in der Zeitschrift Physics in Medicine & Biology, online erschienen am 18.08.2026. Verfasst von Chengkang Liu und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Zhengzhou University of Science and Technology, Zhengzhou, Henan, People's Republic of China. Hauptthemen laut MEDLINE: Radiography, Thoracic, Image Processing, Computer-Assisted. Die Arbeit nennt 45 Literaturangaben. Gefördert von: Key Scientific Research Project of the Henan Provincial Department of Science and Technology, Key Scientific Research Project of Higher Education Institutions in Henan Province.
Abstract (Originalsprache)
Objective. Chest x-ray (CXR) imaging is widely used for screening thoracic diseases. However, accurate multi-disease detection remains challenging because lesion sizes vary substantially, multiple abnormalities often coexist, and small or low-contrast lesions can be obscured by anatomical structures. This study aims to improve multi-disease detection in CXR images by enhancing multi-scale lesion representation and cross-level feature consistency. Approach. We propose a CXR multi-disease detection framework based on multi-scale parallel perception and adaptive feature fusion. The Multi-scale Parallel Feature Sensing module captures complementary lesion features under different receptive fields. The Smooth Residual Fusion Block refines lesion-related spatial responses and suppresses irrelevant background interference. The adaptive pyramid feature fusion module dynamically integrates multi-level features to reduce semantic discrepancies and preserve fine-grained lesion details. Main results. On the VinDr-CXR dataset, the proposed method achieved mean Average Precision scores of 0.389 for mAP @ 0.5 and 0.186 for mAP @ [ 0.5 : 0.95 ] , corresponding to absolute improvements of 5.3% and 1.9% points over the baseline, respectively. The gains were particularly evident for small and subtle abnormalities, such as nodules/masses and pneumothorax. Additional validation on the bounding-box annotated subset of ChestX-ray8 further confirmed robustness, with mAP @ 0.5 , mAP @ [ 0.5 : 0.95 ] , and Recall values of 0.186, 0.093, and 0.240, respectively. Significance. The proposed framework provides an effective solution for structurally consistent multi-disease detection in CXR images. Results on two public datasets suggest that multi-scale parallel perception and adaptive feature fusion improve lesion localization robustness, showing potential as a supportive tool for computer-aided screening workflows.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information Engineering, Zhengzhou University of Science and Technology, Zhengzhou, Henan, People's Republic of China.
- Engineering Technology Research Center for Visual Big Data Processing and Control, Zhengzhou University of Science and Technology, Zhengzhou, Henan, People's Republic of China.
- Key Laboratory of Visual Big Data Processing and Application, Zhengzhou University of Science and Technology, Zhengzhou, Henan, People's Republic of China.
ORCID-Profile: Chengkang Liu, Yubo Yuan, Li Zhang, Qingwen Feng
Förderung
- Key Scientific Research Project of the Henan Provincial Department of Science and Technology
- Key Scientific Research Project of Higher Education Institutions in Henan Province
Zitieren
APA
Liu, C., Yuan, Y., Zhang, L., Feng, Q., Yang, K., Zhang, C., & Wang, D. (2026). Multi-scale parallel perception and adaptive feature fusion for chest x-ray multi-disease detection. Physics in Medicine & Biology, 71(16), 165004. https://doi.org/10.1088/1361-6560/ae970f
Vancouver
Liu C, Yuan Y, Zhang L, Feng Q, Yang K, Zhang C, et al. Multi-scale parallel perception and adaptive feature fusion for chest x-ray multi-disease detection. Physics in Medicine & Biology. 2026;71(16):165004. doi:10.1088/1361-6560/ae970f
BibTeX
@article{Liu2026,
author = {Liu, Chengkang and Yuan, Yubo and Zhang, Li and Feng, Qingwen and Yang, Kun and Zhang, Chuang and Wang, Danhui},
title = {Multi-scale parallel perception and adaptive feature fusion for chest x-ray multi-disease detection},
journal = {Physics in Medicine & Biology},
year = {2026},
volume = {71},
number = {16},
pages = {165004},
doi = {10.1088/1361-6560/ae970f}
}
EUVIMED