Healthcare
Case StudyLondon Hospital for Tropical Diseases

London Hospital for Tropical Diseases is testing an AI powered microscope which detects the presence of malaria parasites in blood with the same accuracy as microscopists

Deep learning powered microscopes can be used to identify and count of malarial parasites in blood smear in 20 minutes. This facilitates faster detection of the disease and address shortages of trained staff.

Context

It can be very difficult and time consuming to detect cases of malarial parasites. "In cases of very low infection levels, just a single malaria parasite might appear among 100,000 red blood cells." This has been compared to finding a needle in a haystack. Automated microscopes can be used to provide standardised detection of diseases resulting in efficiency and quality gains.

The Project

"The optical microscope remains a widely-used tool for diagnosis and quantitation of malaria. An automated system that can match the performance of well-trained technicians is motivated by a shortage of trained microscopists. We have developed a computer vision system that leverages deep learning to identify malaria parasites in micrographs of standard, field-prepared thick blood films. The prototype application diagnoses P. falciparum with sufficient accuracy to achieve competency level 1 in the World Health Organization external competency assessment, and quantitates with sufficient accuracy for use in drug resistance studies. A suite of new computer vision techniques—global white balance, adaptive nonlinear grayscale, and a novel augmentation scheme—underpin the system’s state-of-the-art performance."

AI Usage

"The solution required a combination of both deep learning and traditional computer algorithms used for segmenting things of interest within images."

Results

Achieved same accuracy as trained microscopists

Back to Case Studies
AI Daily Brief — leaders actually read it.

Free email — not hiring or booking. Optional BPAI updates for company news. Unsubscribe anytime.

Include

No spam. Unsubscribe anytime. Privacy policy.