A machine learning-based system for detecting leishmaniasis in microscopic images

Background Leishmaniasis, a disease caused by a protozoan, causes numerous deaths in humans each year. After malaria, leishmaniasis is known to be the deadliest parasitic disease globally. Direct visual detection of leishmania parasite through microscopy is the frequent method for diagnosis of this disease. However, this method is time-consuming and subject to errors. This study was aimed to develop an artificial intelligence-based algorithm for automatic diagnosis of leishmaniasis. Methods We used the Viola-Jones algorithm to develop a leishmania parasite detection system. The algorithm includes three procedures: feature extraction, integral image creation, and classification. Haar-like features are used as features. An integral image was used to represent an abstract of the image that significantly speeds up the algorithm. The adaBoost technique was used to select the discriminate features and to train the classifier. Results A 65% recall and 50% precision was concluded in the detection of macrophages infected with the leishmania parasite. Also, these numbers were 52% and 71%, respectively, related to amastigotes outside of macrophages. Conclusion The developed system is accurate, fast, easy to use, and cost-effective. Therefore, artificial intelligence might be used as an alternative for the current leishmanial diagnosis methods.

Effects of Food and Temperature on Drosophila melanogaster Reproductive Dormancy as Revealed by Quantification of a GFP-Tagged Yolk Protein in the Ovary

When exposed to harsh environmental conditions, such as food scarcity and/or low temperature, Drosophila melanogaster females enter reproductive dormancy, a metabolic state that enhances stress resistance for survival at the expense of reproduction. Although the absence of egg chambers carrying yolk from the ovary has been used to define reproductive dormancy in this species, this definition is susceptible to false judgements of dormancy events: e.g. a trace amount of yolk could escape visual detection; a fly is judged to be in the non-dormancy state if it has a single yolk-containing egg chamber even when other egg chambers are devoid of yolk. In this study, we propose an alternative method for describing the maturation state of oocytes, in which the amount of yolk in the entire ovary is quantified by the fluorescence intensity derived from GFP, which is expressed as a fusion with the major yolk protein Yp1. We show that yolk deposition increases with temperature with a sigmoidal function, and the quality of food substantially alters the maximum accumulation of yolk attainable at a given temperature. The Yp1::GFP reporter will serve as a reliable tool for quantifying the amount of yolk and provides a new means for defining the dormancy state in D. melanogaster.