A Cell Augmentation Tool for Blood Smear Analysis

We propose a tool to add parasite-infected red blood cells to blood smear images for malaria screening based on a Mask R-CNN network. The number of infected and uninfected red blood cells in blood smears of malaria patients is typically unbalanced. Our proposed tool extracts cells, augments them by rotation, and then pastes the augmented cells back into empty spaces between existing cells. To paste augmented cells back into an image, the underlying algorithm computes a set of candidate locations that are far away from existing cells by applying a distance transform to a cell mask. Among these candidate locations, the final locations are selected by choosing the locations that are far from each other and distributed across the image to avoid cell clusters and touching cells.For evaluation, we augment 165 blood smear images from 33 patients and run tests on 800 blood smear images from 160 patients. In the training set, the number of infected red blood cells is much smaller than the number of uninfected cells, 1,142 vs. 33,071. The tool adds 8,208 rotated copies of infected cells across all images, increasing the total number of infected cells to 9,350. We then use Mask R-CNN to detect infected cells, before and after augmentation, and find that our tool improves the recall, precision, and F1 measure for the detection of infected cells by about 6%.