Microscopic Image Segmentation to Quantification of Leishmania Infection in Macrophages

Abstract

The determination of infection rate parameter from in vitro macrophages infected by Leishmania amastigotes is fundamental in the study of vaccine candidates and new drugs for the treatment of leishmaniasis. The conventional method that consists in the amastigotes count inside macrophages, normally is done by a trained microscope technician, which is liable to misinterpretation and sampling. The objective of this work is to develop a method for the segmentation of images to enable the automatic calculation of the infection rate by amastigotes. Segmentation is based on mathematical morphology in the context of a computer vision system. The results obtained by computer vision system presents a 95% accuracy in comparison to the conventional method. Therefore, the proposed method can contribute to the speed and accuracy of analysis of infection rate, minimizing errors from the traditional methods, especially in situations where exhaustive repetitions of the procedure are required from the technician.

Keywords

• amastigote count
• image segmentation
• environmental degradation