You are here

Automated Detection of Lung Diseases in Chest X-Rays

Printer-friendly versionPrinter-friendly version
April 2015 Technical Report to the LHNCBC Board of Scientific Counselors

Tuberculosis (TB) is an infectious disease caused by the bacillus M. Tuberculosis. According to the World Health Organization (WHO) Global Tuberculosis Report 2014 [1], TB remains one of the world’s deadliest communicable diseases. In 2013, an estimated 9.0 million people developed TB, of these 1.1 million (13%) were HIV-positive. According to the report, 1.5 million died from the disease, 360 000 of whom were HIV-positive. The rates of TB mortality are slowly declining each year and it is estimated that 37 million lives were saved between 2000 and 2013 through effective diagnosis and treatment. However, TB is now present in all regions of the world, increasingly as drug resistant variants.

In this report, we present a reliable automated CXR image-based screening system for detecting pulmonary diseases, with a special initial focus on TB [6, 7]. The system is being tested through our collaboration with AMPATH (Academic Model for Prevention and Treatment of HIV/AIDS) [7]. AMPATH is a partnership between Moi University School of Medicine and Moi Teaching and Referral Hospital, Eldoret, Kenya, and a consortium of U.S. medical schools under the leadership of Indiana University. AMPATH provides drug treatment and health education for HIV/AIDS control in Kenya. AMPATH currently treats nearly 200,000 patients for HIV. Large numbers of HIV patients need to be X-rayed and screened for active TB to ensure proper treatment of their infection(s) and avoid drug incompatibilities. However, the shortage of radiological services in Kenya necessitates an automated and inexpensive screening system. The system should be automatic and provide adequate clinical decision support to regional medical officers with little radiology background. The target imaging source for our automated system are portable X-ray scanners mounted on trucks designed for radiological imaging to access population in rural areas with poor road access. At-risk individuals identified by our system would be referred for treatment to regional clinics, or the hospital in Eldoret.

Antani SK. Automated Detection of Lung Diseases in Chest X-Rays April 2015 Technical Report to the LHNCBC Board of Scientific Counselors