Cat-Inspired Deep Convolutional Neural Network for Bone Marrow Cancer Cells Detection

Bone marrow cancer is considered to be the most complex and dangerous disease which results due an uncontrolled growth of white blood cells called leukocytes. Acute Lymphoblastic Leukemia (ALL) Multiple Myeloma (MM) are important categories bone cancers, induces a larger number in marrow, preventing production healthy cells. The advent Artificial Intelligence, especially machine deep learning, has expanded humanity’s capacity analyze detect these increasingly diseases. But, accurate detection reducing probability false alarm rates remain on darker side research. This paper proposes novel convolutional neural networks hyper parameters optimized by adaptive Multi-objective CAT algorithms. proposed model trained preprocessed cell images followed training with Optimized Convolutional Neural Network (OCNN) finally detecting category present marrow. extensive experimentations have been carried out using SN-AM datasets various performance metrics such as accuracy, precision, recall, specificity, F1-score calculated analyzed. overall accuracy was found 99.45% predicting different it outperforms pre-trained learning models Alexnets, VGG-16 nets, U-nets. To establish superiority model, we compared other Support Vector Machines, Random Forest, Naïve Bayes, Networks. From above intensive studies, clear that able produce brighter performances than