EUVIMEDEUVIMED entdecken
Crossref

Multi-scale parallel perception and adaptive feature fusion for chest x-ray multi-disease detection

Chengkang Liu iD, Yubo Yuan iD, Li Zhang iD, Qingwen Feng iD, Kun Yang, Chuang Zhang, Danhui Wang

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

Radiography, ThoracicImage Processing, Computer-AssistedHumans

Stichwörter der Autor:innen

ChestX-ray8 datasetVinDr-CXR datasetadaptive feature fusionchest x-raymulti-disease detectionmulti-scale parallel perception

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}
}
Kostenlos starten →