Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Adaptive collaborative feature fusion and shape-aware optimization for multi-scale chest lesion detection.

Yubo Yuan1,2, Chengkang Liu1,2, Qingwen Feng3,4

  • 1School of Information Engineering, Zhengzhou University of Science and Technology, Zhengzhou, 450064, China.

Scientific Reports
|June 12, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A bicentric study on the application of dual energy CT for predicting hemorrhagic transformation post endovascular thrombectomy.

Scientific reports·2025
Same author

Cascade-targeting pH/ROS microneedles promote scarless diabetic wound healing by macrophage metaboimmune reprogramming.

Science advances·2025
Same author

Research Progress on Non-Destructive Testing Technology and Equipment for Poultry Eggshell Quality.

Foods (Basel, Switzerland)·2025
Same author

Fucoidan ameliorates rotenone-induced Parkinsonism in mice by regulating the microbiota-gut-brain axis.

International journal of biological macromolecules·2024
Same author

Reactive oxygen species-responsive polydopamine-PtCuTe nanoparticle-loaded microneedle system for promoting the healing of infected skin wounds.

Journal of controlled release : official journal of the Controlled Release Society·2024
Same author

Natural Exponential and Three-Dimensional Chaotic System.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2023
Same journal

MT-MRI for detection of renal interstitial fibrosis in renovascular disease.

Scientific reports·2026
Same journal

Detection of underground objects from GPR data using a lightweight YOLO-based approach.

Scientific reports·2026
Same journal

Early systemic inflammatory-metabolic trajectory phenotypes are associated with survival outcomes in metastatic renal cell carcinoma treated with nivolumab.

Scientific reports·2026
Same journal

Water balance components in a dry-seeded rice-wheat system: Untangling the effects of tillage and mulching practices.

Scientific reports·2026
Same journal

Topological approaches to quantum tensor train compression via ZX-calculus and SVD.

Scientific reports·2026
Same journal

determinants of flood impacts and adaptive capacity among market vendors in Walukuba-Masese, Jinja city, Uganda.

Scientific reports·2026
See all related articles
This summary is machine-generated.

This study introduces a novel multi-scale method for detecting chest lesions in X-rays, improving accuracy for small and irregular findings. The approach enhances early diagnosis and clinical decision-making for chest diseases.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiology

Background:

  • Chest diseases are a leading cause of global mortality.
  • Accurate detection of chest lesions from X-rays is crucial for timely diagnosis.
  • Automated detection faces challenges with lesion variability and precise localization.

Purpose of the Study:

  • To develop an advanced multi-scale method for robust chest lesion detection.
  • To enhance the accuracy and localization of automated systems for complex X-ray images.
  • To improve the identification of small and irregularly shaped lesions.

Main Methods:

  • Proposed a multi-scale chest lesion detection method using adaptive collaborative feature fusion and shape-aware optimization.
  • Developed a Context-Embedded Feature Enhancement Network for global and local feature integration.

Related Experiment Videos

  • Introduced an Adaptive Feature Focusing Network for improved multi-scale feature representation.
  • Implemented a shape-aware optimization strategy with normalized Wasserstein distance and shape-weighted constraints.

    • Main Results:

    • Achieved a 6.3% increase in mean Average Precision (mAP) on the VinDr-CXR dataset.
    • Improved small-lesion detection by 6.4% mAP and mean recall by 8.6% on VinDr-CXR.
    • Demonstrated a 4.2% mAP and 7.8% mean recall improvement on the ChestX-ray8 dataset.

    Conclusions:

    • The proposed method effectively addresses challenges in multi-scale chest lesion detection.
    • The approach shows significant improvements in accuracy and localization robustness.
    • The method exhibits strong generalization capabilities for diverse chest X-ray datasets.