LeukoNet: DCT-based CNN architecture for the classification of normal versus Leukemic blasts in B-ALL Cancer

Acute lymphoblastic leukemia (ALL) constitutes approximately 25% of the cancers. In general, the task of identifying immature leukemic blasts normal cells under the microscope is challenging because morphologically images of the two cells appear similar. In this paper, we propose a deep framework for classifying immature leukemic blasts and normal cells. proposed model combines the Discrete Cosine Transform (DCT) domain features via CNN with the Optical Density (OD) space features to build a classifier. Elaborate experiments have been conducted to validate the LeukoNet classifier.