You are here

Malaria Screening: Research into Image Analysis and Deep Learning.

Printer-friendly versionPrinter-friendly version
Report to the Board of Scientific Counselors September 2018.
Abstract: 

With more than 200 million cases worldwide, and more than 400,000 deaths per year, malaria is a major burden on global health [1, 16]. Malaria is caused by parasites that are transmitted through the bites of infected mosquitoes. When malaria parasites enter the blood stream, they infect and destroy the red blood cells. Typical symptoms of malaria include fever, fatigue, headaches, and in severe cases seizures, coma, and death. Most deaths occur among children in Africa, where a child dies from malaria every other minute of every day, and where malaria is a leading cause of childhood neuro-disability.

While existing drugs make malaria a curable disease, inadequate diagnostics and emerging drug resistance are major barriers to successful mortality reduction. The current standard method for malaria diagnosis in the field is light microscopy of blood films [17, 18, 19]. Microscopists examine millions of blood films every year for malaria. This involves manual counting of parasites or infected red blood cells, which is a labor-intensive and error-prone process, especially if patients have to be tested several times a day. However, accurate counts are essential to diagnosing malaria accurately, and are an important part of testing for drug-effectiveness, drug-resistance, and estimating disease severity [20].

Unfortunately, microscopic diagnostics depends heavily on the experience and skill of the microscopist. It is common for microscopists in low-resource settings to work in isolation, with no rigorous system in place that can ensure the maintenance of their skills and thus diagnostic quality. This leads to incorrect diagnostic decisions in the field. For false negative cases, this leads to unnecessary use of antibiotics, a second consultation, lost days of work, and in some cases progression into severe malaria. For false positive cases, this means unnecessary use of anti-malaria drugs and suffering from their potential side effects, such as nausea, abdominal pain, diarrhea, and even more severe complications.

Jaeger S, Antani SK, Rajaraman S, Yang F, Yu H. Malaria Screening: Research into Image Analysis and Deep Learning. Report to the Board of Scientific Counselors September 2018.