About the Dataset

Malaria images were taken from thick blood smears and stained using Field stain at x1000 microscope magnification.
The TB images were made from fresh sputum and stained using ZN (Ziehl Neelsen) stain. These were examined under x1000 magnification.
Finally the intestinal parasites images were captured from slides of a wet preparation, i.e. a portion of stool sample mixed in a drop of normal saline and examined under x400 magnification. The experts identified bounding boxes around each object of interest in every image. In thick blood smear images, plasmodium were annotated (7245 objects in 1182 images); in sputum samples, tuberculosis bacilli were annotated (3734 objects in 928 images), and in stool samples, the eggs of hookworm, Taenia and Hymenolepsis nana were annotated (162 objects in 1217 images).

Publication

J.A. Quinn, R. Nakasi, P.K. Mugagga, P. Byanyima, W. Lubega, A. Andama. Deep Convolutional Neural Networks for Microscopy-Based Point of Care Diagnostics. Proceedings of the International Conference on Machine Learning for Health Care, Journal of Machine Learning Research W&C track, Volume 56, 2016. link