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 Video

Updated: Jul 19, 2026

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

CPM-XNet: Annotation-Efficient Deep-Learning Framework for Detecting Tuberculosis in Chest X-Ray Images.

Tzu-Chin Yang1,2, Bing-Yen Wang3,4, Jin-Yu Li5

  • 1Department of Medical Imaging, Tungs' Taichung MetroHarbor Hospital, Taichung 435403, Taiwan.

Diagnostics (Basel, Switzerland)
|July 15, 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

Saebias A-G, eudesmane sesquiterpenes from Salvia plebeia with potential for Alzheimer's disease prevention via anti-neuroinflammatory and neuroprotective effects.

Phytochemistry·2026
Same author

[Research progress on role of PINK1/Parkin-mediated mitophagy in Alzheimer's disease and TCM interventions].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2026
Same author

Modulated electro-hyperthermia enhances tumor cell susceptibility to γδ T cell-mediated cytotoxicity and tumor infiltration in NOD/SCID xenograft models.

International journal of hyperthermia : the official journal of European Society for Hyperthermic Oncology, North American Hyperthermia Group·2026
Same author

Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs.

Diagnostics (Basel, Switzerland)·2026
Same author

Metabolic PANoptosis orchestrated by porous silkworm-like PtFeCoTeMn high-entropy nanozyme for synergistic cancer therapy.

Journal of colloid and interface science·2026
Same author

A Highly Rearranged Nor-Abietane Diterpenoid with an Unusual 6/6/6/5/4 Pentacyclic System and Three Other Diterpenoids from <i>Lycopus lucidus</i> var. <i>hirtus</i> and Antineuroinflammatory Activities.

The Journal of organic chemistry·2026

We developed CPM-XNet, an annotation-efficient deep learning framework for tuberculosis (TB) classification in chest X-rays (CXRs). This method improves diagnostic accuracy without requiring costly lesion-level annotations.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiology

Background:

  • Chest X-rays (CXRs) are crucial for tuberculosis (TB) screening but interpretation challenges necessitate automated tools.
  • Current deep learning models require extensive, costly annotations (lesion/pixel-level), hindering clinical application.
  • CPM-XNet addresses this by enabling annotation-efficient TB classification.

Purpose of the Study:

  • To develop an annotation-efficient deep learning framework (CPM-XNet) for tuberculosis classification in chest X-ray images.
  • To evaluate the performance of CPM-XNet compared to baseline models without dense annotations.
  • To assess the contribution of the compressing-projecting mask (CPM) module to classification accuracy.

Main Methods:

  • Developed CPM-XNet, incorporating a compressing-projecting mask (CPM) for lung-aware modulation while retaining global context.
Keywords:
chest X-rayconvolutional neural networkdeep learningexplainable AIlung-aware feature modulationtuberculosisweakly supervised learning

More Related Videos

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

Related Experiment Videos

Last Updated: Jul 19, 2026

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

  • Utilized CPM-modulated CXR images for downstream classification using CNN backbones and a vision transformer.
  • Validated the framework on internal and public TB datasets.

    • Main Results:

    • CPM-XNet demonstrated superior performance over baseline models trained on unmodulated images.
    • CPM-ResNet101 exhibited higher and more stable performance on the Tung cohort compared to its non-CPM counterpart.
    • Ablation studies confirmed CPM modulation as the primary driver of performance gains.

    Conclusions:

    • CPM-XNet offers an effective annotation-efficient strategy for lesion-annotation-free TB classification in CXRs.
    • The framework shows preliminary technical feasibility for automated TB screening.
    • Further validation on larger, diverse datasets is recommended prior to clinical deployment.