Detection of malaria parasite in thick blood smears using deep learning

We're working on a deep learning algorithm which can distinguish between malaria parasites in blood smears in a video format which consists of several images. There are two processing steps in our method. Initially, we locate parasites by quickly inspecting a thick smear image and remove noise from that parasite. Then, using a customized Convolutional Neural Network (CNN), each image in a video is classified as one of two ways, whether it consists of parasite or not. We took a datafile of 1817 smear photographs from 148 victims from an openly accessible institute. This datafile was used to assess and trial our algorithm. Copyright (c) 2022 Elsevier Ltd. All rights reserved. Selection and peer-review under responsibility of the scientific committee of the International Conference on Advanced Materials for Innovation and Sustainability.