eduzhai > Applied Sciences > Engineering >

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

  • Save

... pages left unread,continue reading

Document pages: 12 pages

Abstract: Malaria is considered one of the deadliest diseases in today world whichcauses thousands of deaths per year. The parasites responsible for malaria arescientifically known as Plasmodium which infects the red blood cells in humanbeings. The parasites are transmitted by a female class of mosquitos known asAnopheles. The diagnosis of malaria requires identification and manual countingof parasitized cells by medical practitioners in microscopic blood smears. Dueto the unavailability of resources, its diagnostic accuracy is largely affectedby large scale screening. State of the art Computer-aided diagnostic techniquesbased on deep learning algorithms such as CNNs, with end to end featureextraction and classification, have widely contributed to various imagerecognition tasks. In this paper, we evaluate the performance of custom madeconvnet Mosquito-Net, to classify the infected and uninfected cells for malariadiagnosis which could be deployed on the edge and mobile devices owing to itsfewer parameters and less computation power. Therefore, it can be wildlypreferred for diagnosis in remote and countryside areas where there is a lackof medical facilities.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×