Supporting data for "Multi-Stage Malaria Parasites Recognition by Deep Learning"

Malaria, a mosquito-borne infectious disease affecting humans and other animals, is widespread in the tropical and subtropical regions. Microscopy is the most common method in diagnosing the malaria parasite from stained blood smears. However, this procedure is time-consuming, error-prone, and requires a well-trained professional. Moreover, the recognition of a malaria parasite through a microscope is still a challenging process, especially in distinguishing multiple stages of parasites.

Here is a large-scale dataset of unseen malaria parasites for a Multi-stage Malaria Recognition experiment. This includes test and training images of parasitized cells, test and training images of leukocytes, test and training images of gametocytes, test and training images of uninfected cells, test and training images of red blood cells, test and training images of ring cells, test and training images of schizont cells, test and training images of trophozoite cells.

Related P. vivax (malaria) infected human blood smear data is available in the BBBC repository and can be accessed with accession No. BBBC041 https://bbbc.broadinstitute.org/BBBC041

A related large scale malaria dataset consisting of 13,780 both malaria parasites and RBCs testing images are available in the National Library of Medicine (NLM) respository and can be accessed with accession No. PUB9932. https://lhncbc.nlm.nih.gov/LHC-publications/pubs/MalariaDatasets.html