Journal of Pioneering Artificial Intelligence Research

Abstract

Acute Lymphoblastic Leukemia (ALL) is the most prevalent form of childhood cancer, accounting for approx imately 25 percent of all pediatric malignancies worldwide. The conventional method of diagnosis, which relies on a trained hematopathologist manually examining Giemsa-stained bone marrow smear slides under a high-powered microscope, is both time-consuming and inherently subjective, with inter-observer variability of up to 20 percent reported in the clinical literature. This paper presents Marrow-Find, a fully integrated AI-powered web application designed to automate the classification, visual explanation, and quantification of leukemia cells from bone marrow microscopic images. The system employs a ResNet50 deep convolution al neural network, pre-trained on ImageNet and fine-tuned on the C-NMC 2019 and ALL-IDB benchmark datasets, to classify bone marrow cells into four clinically significant categories: Benign, Pre-B ALL, Pro-B ALL, and Early Pre-B ALL. The model achieves an overall test accuracy of 94.8 percent with a weighted F1 score of 0.954 and a Cohen's Kappa of 0.931. To address class imbalance in the training data, a Conditional Generative Adversarial Network (cGAN) generates realistic synthetic bone marrow cell images for minority classes. Gradient- weighted Class Activation Mapping (Grad-CAM) produces visual heatmap overlays on each prediction, enabling pathologists to verify the morphological features influencing the model's decision. A Watershed-based segmentation algorithm automatically delineates individual cell boundaries and counts blast cells per image. All five components are integrated into a Flask web application with secure user au thentication, prediction history, human-correction feedback, PDF report generation with QR codes, and an AI chatbot, making specialist-level leukemia diagnostics accessible from any standard web browser.