WIP: Intepretable Classification: Chest X-Rays
Posted on Wed 14 April 2021 in research
Radiological signs on healthy (left) and Activte Pulmonary TB-affected lungs (right).
Reproducibility Checklist
- All datasets used in this study are public
- Software will be open-sourced soon. It is extensible and tested on a regular basis
- Complete documentation will be availabe available
Partnership
This study was conducted in partnership with TB specialists from the Federal University of Rio de Janeiro and Rede TB in Brazil.
Tuberculosis (TB) is one of the leading causes of death from a single infectious agent. In many high-burden regions around the world, which often lack specialized healthcare professionals, Chest X-Ray (CXR) exams continue to be of vital importance in the diagnosis and follow-up of the various presentations of the disease. In this context, we investigate the benefits of automatic Pulmonary Tuberculosis (PTB) detection methods based on Deep Learning. Our work will be made open-source and fully reproducible in the hopes it becomes useful to further explore the application of Deep Learning to PTB screening.