ALL Detection

Acute Lymphoblastic Leukemia (ALL) is the most common childhood cancer and affects both children and adults, requiring accurate risk assessment to guide effective treatment while addressing challenges such as relapse, resistance, and long-term toxicity. To support early diagnosis, this study proposes a deep optimized convolutional neural network (CNN) that integrates five convolutional blocks with thirteen convolutional layers and five max-pooling layers. Tuned with 30 training epochs and a batch size of 32, the model achieved strong performance using the Adam optimizer, reaching 96% accuracy and 95% precision.