Detection of Malaria Parasites in Thin Blood Smears Using CNN-Based Approach

Early and accurate detection of malaria is the main key in controlling and eradicating this deadly disease. An efficient automated tool for examining stained blood slides can be very helpful in this regard. This paper proposes an approach for automatic detection of malarial parasites from thin blood smears. Texture- and intensity-based analyses are performed to detect the blood particles in the pre-processed image. Extracted red blood cell particles are then sent to a convolutional neural network for further probing. The proposed CNN architecture is trained with a publicly available dataset along with some Giemsa-stained blood smear images collected from a hospital. The performance of malaria detection process gives a satisfactory dice score of 0.95.