Incremental learning for acute lymphoblastic leukemia classification based on hybrid deep learning using blood smear image

Abstract

The prevalent type of blood cancer is called leukemia, which is caused by the irregular production of immature malignant cells in the bone marrow. This dangerous condition weakens the immune system, making the body susceptible to infections, and can lead to death if not treated quickly. Thus, immediate treatments are necessary to detect leukemia at the initial stage to control abnormal cell growth. Leukemia detection from microscopic images of blood smears of malignant leukemia cells is a time-consuming and tedious task. Thus, a Tangent Sand Cat Swarm Optimization-Long Short-Term Memory-LeNet (TSCO-L-LeNet) with incremental learning is designed for the precise classification of acute lymphoblastic leukemia. The proposed model offers cheaper, faster and safer diagnosis service as the use of blood smear images reduces the diagnosis time and improves accuracy. Here, the input image is pre-processed using the adaptive median filter and the Scribble2label is used to segment the image. Later, the augmentation of segmented image is performed and the feature extraction process is employed to extract the necessary features from the augmented image. Finally, the L-LeNet with incremental learning is executed for acute lymphoblastic leukemia classification from the extracted features, where the TSCO approach is used to train the weights of L-LeNet. The experimental results show that TSCO-L-LeNet achieved maximum performance of 0.987 for accuracy, 0.977 for True Negative Rate (TNR), 0.967 for recall, 0.033 for False Negative rate, 0.023 for False Positive rate, and 0.979 for precision.