Classifying Parasitized and Uninfected Malaria Red Blood Cells Using Convolutional-Recurrent Neural Networks

This work aims to classify malaria infected cells from those uninfected using two deep learning approaches. Plasmodium parasite transmitted by a female anopheles’s mosquitoes bite is the main cause of malaria. Commonly, Microbiological analyses microscope allows detecting blood sample, followed an specialist interpretation results conclude diagnosis process. Taking advantage efficient approaches applied in computer vision field, present framework propose architecture based on Recurrent neural Networks detect accurately cells. The first one implements Convolutional Long Short-Term Memory while second uses Bidirectional architecture. A malaria’s public dataset consisting parasitized and cell images was used for training testing proposed model. methods developed this achieved accuracy 99.89 % detection infected, without preprocessing data.