Leukemia is a leukemia cell image dataset designed to be used to train computer vision models to automatically detect and classify leukemia cells. The dataset contains 6,778 images of cells, including normal cells (3,389) and leukemia cells (3,389). Acute lymphoblastic leukemia (ALL) is the most common type of childhood cancer, accounting for about 25% of childhood cancers. The cells were segmented from microscopic images, and the ground truth labels were annotated by oncologists.