SBCDNet: An Efficient Sparse-Based Deep Cascade Blood Cancer Detection Network

Automated and early diagnosis of blood cancer is an essential task. Currently, deep learning-based systems are widely used for medical diagnosis. However, the major drawbacks of such systems are the requirement of huge labeled databases and slow training. Thus, an efficient sparse-based deep cascade model is proposed to make the diagnosis of acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML) more accurate. The major contributions are as follows. 1) A novel sparse-based deep cascade blood cancer detection network (SBCDNet) is proposed to yield outstanding performance in small databases. 2) An efficient single-level deep cascade model is suggested for selecting more important features and making the system faster and more accurate. 3) Softmax vector coding of errors is used to achieve nonlinear transformation in layer-wise learning. 4) Modified Fast Iterative Shrinkage, and Thresholding Algorithm is employed to solve inverse linear problems. Experimental results demonstrate that the proposed SBCDNet outperforms its competitors with the best performances, including 98.15% and 97.50% accuracies for ALL and AML detection, respectively.