Acute lymphoblastic leukemia (ALL) constitutes approxi- mately 25% of the pediatric cancers. In general, the task of identifying immature leukemic blasts from normal cells un- der the microscope is challenging because morphologically the images of the two cells appear similar. In this paper, we propose a deep learning framework for classifying immature leukemic blasts and normal cells. The proposed model com- bines the Discrete Cosine Transform (DCT) domain features extracted via CNN with the Optical Density (OD) space fea- tures to build a robust classifier. Elaborate experiments have been conducted to validate the proposed LeukoNet classifier.