A ResNet18 model was trained to detect trypanosoma parasites from microscope images using pre-processed dataset derived from microscope videos of unstained thick blood smears, with the blood smears originating from a mouse infected with Trypanosoma brucei. Our pre-processing strategy mainly involved image cropping and the application of a thresholding algorithm for facilitating effective model training. Moreover, our thresholding approach made it possible to observe a positive correlation between the percentage of parasite-related pixels in an image and the classification effectiveness.
Result was presented at IHCI 2020 and published as a conference paper, "Automatic Detection of Trypanosomosis in Thick Blood Smears Using Image Pre-processing and Deep Learning".
You can found out more from the below url.
https://link.springer.com/chapter/10.1007%2F978-3-030-68452-5_27