About this document
Deep Learning for TB Detection in X-rays by 21r21a6649 is a document available to read on EtoBox.
This research article presents the development of deep learning models for the detection of tuberculosis (TB) in chest X-ray images, addressing the challenges of misdiagnosis in low-resource settings. The study utilized a UNet model for segmentation and an Xception model for classification, achieving high accuracy rates of 96.35% for segmentation and 99.29% for classification. Additionally, the use of Grad-CAM heatmaps allowed for effective visualization of TB-infected regions, demonstrating the potential o
- Author
- 21r21a6649
- Language
- EN