Analysis of Acute Lymphoblastic Leukemia Detection Methods Using Deep Learning

This research work puts forward a comparative study of four prominent deep learning models - ResNet, InceptionNet, MobileNet and EfficientNet — for the classification and detection of Acute Lymphoblastic Leukemia (ALL) from microscopic single blood cell images. Leukemia, a critical hematological malignancy, demands accurate and swift diagnosis to facilitate effective treatment. The advent of deep learning has revolutionized medical image analysis, enabling automated and efficient disease detection. In this work, we evaluate the performance of ResNet, InceptionNet, MobileNet, and EfficientNet, all of which have demonstrated exceptional capabilities in various computer vision tasks. The proposed study involves the construction of a dataset containing diverse blood cell images, which then undergoes preprocessing and augmentation to ensure model robustness and generalization. Subsequently, the four deep learning architectures are implemented, pretrained on large-scale image datasets, and fine-tuned on the leukemia dataset. Training, validation, and testing phases are conducted under controlled experimental conditions. The results reveal nuanced differences in the performance of ResNet, InceptionNet, MobileNet, and EfficientNet for leukemia detection and classification. The evaluation metrics provide insights into their strengths and limitations, helping guide selection based on specific application requirements. This study clarifies how various architectures impact model performance in the context of medical image analysis.