Abstract

Leukemia, another name for bloodstream cancerous cells illness, is a potentially fatal illness which needs prompt and accurate assessment to be able to effectively cured. Throughout the study, it offers a novel strategy that can identify and categorize bloodstream cancerous cells illness utilizing deep learning approach. By employing the Python adaptation of the MobileNetV2 Architecture, we were able to attain impressively precise outcomes. The dataset utilized is "Blood Cells Cancer (ALL) dataset," categorized into four classes: benign, (malignant) early Pre-B, (malignant) Pre-B, and (malignant) Pro-B. Comprising 3242 images of Peripheral Blood Smears (PBS), the collection plays a crucial role in properly determining Acute Lymphoblastic Leukemia (ALL) in prevention of cancer. Using the MobileNetV2 Architecture as its foundation, the deep learning model exhibits good performance. It obtained an excellent precision of 98.00% during training, demonstrating its capacity to accurately discriminate among various kinds of bloodstream cancerous cells. Additionally, the Validation precision of 96.00% underscores the model's robustness and generalization capabilities. This endeavor exclusively showcases the efficacy of neural networks within the domain of healthcare picture processing, it likewise leads towards the prompt identification and categorization of bloodstream cancerous cells, thereby enhancing the clinical experience. Leveraging MobileNetV2 and Python enables us to develop a productive and easily available method for medical practitioners, paving the way for improved bloodstream cancerous cells illness assessment and prevention.