MOSQUITO‐NET : A deep learning based CADx system for malaria diagnosis along with model interpretation using GradCam and class activation maps

Malaria is considered one of the deadliest diseases in today world which causes thousands deaths per year. The parasites responsible for malaria are scientifically known as Plasmodium infects red blood cells human beings. transmitted by a female class mosquitos Anopheles. diagnosis requires identification and manual counting parasitized medical practitioners microscopic smears. Due to unavailability resources, its diagnostic accuracy largely affected large scale screening. State art Computer-aided techniques based on deep learning algorithms such CNNs, with end feature extraction classification, have widely contributed various image recognition tasks. In this paper, we evaluate performance custom made convnet Mosquito-Net, classify infected uninfected could be deployed edge mobile devices owing fewer parameters less computation power. Therefore, it can wildly preferred remote countryside areas where there lack facilities.