Malaria Parasite Detection on Microscopic Blood Smear Images with Integrated Deep Learning

[摘要] Malaria is a deadly syndrome formed by the Plasmodium parasite that spreads through the bite of infectedAnopheles mosquitoes. There are several drugs to cure malaria but it is difficult to detect due to inadequate equipment andtechnology. Microscopic check-ups of blood smear images by experts help to detect malaria-infected parasites accurately.However, manual analysis is tedious and time-consuming as the experts have to deal with many cases. This paper presentscomputer assisted malaria parasite detection model by classifying the blood smear image with hybrid deep learning methodsthat have high accuracy for classification. In the proposed approach the blood smear images are pre-processed using bilateralfiltering technique in which features are extracted with the convolutional neural network. These features are selected by theimproved grey-wolf optimization, and image classification is performed with the support vector machine. To evaluate theefficiency of the proposed technique, the NIH malaria dataset is utilized and the results are compared with existing approachesin terms of accuracy, F-Measure, recall, precision, and specificity. The outcome reveals that the proposed scheme is accurateand can be more helpful to pathologists for reliable parasite detection.

[学科分类] 计算机科学（综合）

[关键词] Blood smear images;image classification;image processing;malaria;plasmodium parasite