|Team name||Country||Total Votes|
Our solution is an AI-powered Tuberculosis Chest X-ray Classifier using Computer Vision (Convolutional Neural Network), an algorithm that identifies and classifies images of patients suffering from TB. The algorithm is integrated on a Digital Radiography/Magnetic Resonance Imaging (MRI) machine to facilitate real-time predictive results.
In Africa, a patient’s wait time to receive analyzed lab results can be as long as 72 hours resulting in late treatment reducing the chances of survival especially with fast killing diseases such as Tuberculosis. This is because of the limited number of Radiologists in African hospitals experienced enough to interpret lab results, making one Radiologist work for up to three hospitals. Our solution comes in handy to provide real-time interpolated results immediately chest X-ray images are captured by a Digital Radiography or MRI.
Tuberculosis (TB) is a global disease, found in every country in the world. It is the leading infectious cause of death worldwide according to WHO. The World Health Organization estimates that 1.8 billion people—close to one-quarter of the world's population—are infected with Mycobacterium tuberculosis (M.tb), the bacteria that causes TB.
• Our model provides predicted results to augment the workload of the medical officer interpreting a patient's x-ray result.
• Resulting in faster diagnostics time,
• Reduction of workload on the medical officer and
• Less congestion in the hospital premises.
With Tuberculosis infections still active as the COVID-19 pandemic continues, an automated tool to help identify TB has the potential to reduce hospital workload and optimize patient care during a time when hospitals are being overwhelmed by COVID-19 cases.