A Multiagent System for Automated Detection and Diagnosis of Active Tuberculosis on Chest Radiograph and CT Thorax

Tuberculosis (TB) is a chronic and communicable disease that mostly affects the lungs, but can also affect other organs. TB is a leading cause of morbidity and mortality in adults worldwide, killing almost 2 million people every year. In the USA and Canada, TB is often ignored or misdiagnosed in emergency departments (EDs). This is due to the fact that it is relatively rare in North America. However, it remains prevalent in minority groups, including immigrants from TB endemic countries. The early detection of TB is a key factor to improve its treatment and interrupt its spread. In this paper, we introduce an integrated computer-aided detection (CAD) system for detecting infectious cases of TB on plain chest radiographs by means of an intelligent multiagent system (MAS). This system would be of great value to protect population' health.