Leveraging Hybrid Deep Learning for Effective Multiclass Blood Cancer Detection

Acute Lymphoblastic Leukemia (ALL) is an aggressive blood cancer that affects white blood cells; early and accurate diagnosis is essential for the institution of proper treatment. Traditional methods of leukemia diagnosis, through manual investigation of blood smears, are time-consuming and prone to human error, hence there is a need for more robust automated solutions for diagnosis. This study presents a novel hybrid deep learning model by combining the Xception and ResNet50 models in endeavoring to address the challenges of feature extraction and classification accuracy in microscopic blood smear images. Using convolutional neural networks with some optimized preprocessing, such as image cropping, normalization, and augmentation of data, this study presents a model that can achieve very exceptional diagnostic performance in classifying cancer, at an accuracy of 99.99% on the Kaggle ALL dataset, outperforming other models like ResNet34 and GoogLeNet. Exhaustive testing shows strong generalization with minimal loss and low overfitting, which demonstrates the robustness of the model and its efficiency in picking up subtle patterns at a cell-specific level. This research highlights the transformative potential of hybrid deep learning models in clinical diagnostics for more accurate diagnosis, efficiency, and integration into clinical workflows of early Acute Lymphoblastic Leukemia (ALL) detection for the benefit of patient outcomes and the advancement of research on automated leukemia diagnostics.