PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 10, 2026Applied AI Letters0 citationsOpen Access

Automated Tuberculosis Detection Using Hybrid Deep Learning Framework

Automated Tuberculosis Detection in Chest Radiographs: A Hybrid Deep Learning Framework for Clinical Decision Support

View Full Paper
Ask AI
Bookmark
Share

Authors

MHMd. Tahmid HossainHMHrittik MuralMHMonowar Wadud Hridoy

Discussion

Loading...

Member takes

Overview

Demonstrates automated tuberculosis detection in chest X-ray images, suggesting improved clinical decision support.

Key Points

  • The aim is to enhance tuberculosis diagnosis accuracy using a hybrid deep learning framework for chest X-ray images.
  • Developed a hybrid model combining VGG16, ResNet50, and DenseNet121 CNNs.
  • Trained on three datasets: Montgomery County, Shenzhen, and a third TB-positive dataset.
  • Evaluated model performance using metrics like accuracy, precision, recall, and F1-score.
  • Achieved 97.40% accuracy in tuberculosis detection.
  • Reported precision, recall, and F1-score of 0.96 each.
  • Outperformed individual models: VGG16 (93.00%), ResNet50 (95.90%), and DenseNet121 (96.30%).

Cite This Study

Hossain et al. (2026) studied this question.

synapsesocial.com/papers/69af951a70916d39fea4c444https://doi.org/10.1002/ail2.70022
View Full Paper
Ask AI
Bookmark
Share