Automatic White Blood Cells Classification using Optimized Convulutional Neural Network

Methods based on deep learning are widely used nowadays for data analysis. These procedures involve low time investment and simple tools. In this research, WBC classification was suggested using module weighted optimized CNN. Two transfer learning modules and deformable convolutional (DC) layers characterize our technique, which we use to improve resilience. For WBC classification on low-resolution and noisy data sets, the suggested Optimized CNN (OCNN) demonstrated the best results because to its precise feature extraction and improved network weights. It has the potential to be employed in clinical settings as an alternate technique. White blood cells (WBCs) are immune system cells that may be found throughout the body in the blood, lymph, and other tissues. There is a current upward trend in the prevalence of WBC-related blood disorders such leukemia and lymphoma. The process of analyzing leukocytes in microscopic blood images is the major concern of this research. In this paper, we work on WBCs segmentation from microscopic blood images.