Automatic identification of malaria-infected cells using deep convolutional neural network

Malaria has been a severe ailment spread by the plasmodium parasite, which is conveyed by the bite of an infected Anopheles mosquito. The conventional method of diagnosing malaria is to look for parasite-infected erythrocytes in human blood smears under a microscope by trained personnel. The outcome of this approach depends on the expertise of the persons performing the tests and sometimes they cannot maintain optimal proficiency. Deep learning can be a highly advantageous option as a means of clinical diagnostics. This paper presents two unique deep learning models for identifying malaria from blood cell images based on convolutional neural networks. Accuracy, recall and Matthews correlation coefficient were used to evaluate these models. Proposed method is more effective than the conventional approach of malaria detection which is time-consuming and will help physicians detect the disease more quickly and effortlessly.