Acute Lymphoblastic Leukaemia Detection using Deep Learning ( ViT)

Abstract

Significant advancements in machine learning have been made in disease detection within the medical field; however, challenges remain—particularly in achieving high accuracy and minimizing false positives. Recently, Vision Transformer (ViT) technology, originally developed for visual tasks, has demonstrated promising potential in enhancing detection performance. Motivated by this, our study implemented ViT to detect Acute Lymphoblastic Leukemia (ALL), achieving a remarkable accuracy of 99.35%. This means that out of every 100 disease-related images, our model accurately identified the diseased blood cells approximately 99 times. We utilized a publicly available ALL dataset that includes all four stages of the disease. The importance of this work is underscored by the severe health risks posed by ALL, especially in children. Furthermore, our research highlights the potential of precisely identifying early-stage cancer cases. What distinguishes our approach is the application of machine learning—specifically ViT—to automatically detect and classify cancer, offering a substantial improvement over traditional ALL detection methods, which are often time-consuming and prone to human error. Looking ahead, we aim to develop dedicated hardware to support medical professionals in the rapid and accurate identification of ALL symptoms and affected blood cells. This fusion of data science and medicine holds significant promise for addressing a wide range of medical challenges, including ALL.