AI Detects Parasite from Photos of Blood Samples Taken with Smartphone

Chagas disease caused by the parasite Trypanosoma cruzi is a chronic infectious condition whose prevention requires control of its vectors, the triatomines (kissing bugs), and hence a response by public health services. Endemic in 21 countries in the Americas, Chagas disease affects some six million people, with an annual incidence of 30,000 new cases in the region, leading to 14,000 deaths per year on average. Some 70 million people are estimated to risk contracting the disease because they live in areas exposed to triatomines. One of the techniques used to diagnose Chagas is performed by microscopists trained to detect the parasite in blood samples. This requires a professional microscope, which can be coupled to a high-resolution camera, but the method tends to be too expensive and unaffordable for low-income patients. Now, a new study has shown that artificial intelligence (AI) can be used to detect Trypanosoma cruzi in images of blood samples taken with a smartphone camera and analyzed by optical microscope.

The machine learning approach developed by researchers at the University of São Paulo (São Paulo, Brazil) was based on a random forest algorithm trained to detect and count T. cruzi trypomastigotes in mobile phone images. Trypomastigotes are the extracellular form of the protozoan and the only stage that circulates in the bloodstream of patients with acute Chagas. Images of blood smear samples taken with a camera capable of 12 megapixel resolution were analyzed to arrive at a set of features common to 1,314 parasites, including morphometric parameters (shape and size), color and texture.

In the study, parasite specialists trained the algorithm to recognize Trypanosoma cruzi, assisted by machine learning and image processing specialists. The features were divided into training and testing sets and classified using the random forest algorithm. The resulting values for accuracy and sensitivity were considered high (87.6% and 90.5% respectively). The researchers also analyzed the area under the receiver operating characteristic curve (AUC-ROC), a graphical representation widely used to assess diagnostic accuracy and optimal test cut-off. The result was 0.942, considered outstanding (the higher the area under the curve, the more accurate the test). The researchers concluded that automating the analysis of images acquired with a mobile device is a viable alternative for reducing costs and gaining efficiency in the use of the optical microscope. The algorithm is open software so that the scientific community can contribute data and resources.

“We got good results in this machine learning initiative. The algorithm works well for Chagas and can be adapted for other purposes that depend on images, such as analyzing samples of feces, skin and colposcopies,” said Helder Nakaya, a principal investigator at the Center for Research on Inflammatory Diseases. “The point is to generate images and analyze them under a microscope that can be sent to remote parts of Brazil. The app itself must say whether they are images of the parasite that causes Chagas. It’s therefore important to have a robust and affordable microscope that can collect the images automatically.”

Related Links:
University of São Paulo