Malaria dataset (thin blood smear, updated)
Giemsa-stained thin blood smear slides from 150 P. falciparum-infected and 50 healthy patients were collected and photographed at Chittagong Medical College Hospital, Bangladesh. The smartphone’s built-in camera acquired images of slides for each microscopic field of view. Initially, the images were manually annotated by an expert slide reader at the Mahidol-Oxford Tropical Medicine Research Unit in Bangkok, Thailand (the originals can be found at NLM, ftp://lhcftp.nlm.nih.gov/Open-Access-Datasets/Malaria/).
Due to the fact that a relatively large proportion of images was mislabeled, the dataset has been double-checked and relabeled by Michael Delves. The images have been reorganised into five folders: parasitised, uninfected, weird, bad segmentation, unsure.
Five folders. Parasitized, uninfected, bad segmentation, unsure, weird.
- malaria images (thin blood smear) malaria_thin_smear.zip (336.43 MB)
- 5 groups of parasitized and uninfected images for cross-validation (after cleaning) groups.zip (306.40 MB)
- 5 groups of parasitized and uninfected images for cross-validation (before cleaning) groups_old.zip (323.45 MB)
Open Access dataset files are accessible to all logged in users. Don't have a login? Create a free IEEE account. IEEE Membership is not required.