# Demystifying Deep Learning Decisions in Leukemia Diagnostics Using Explainable AI

## TL;DR

This paper introduces an AI system with explainable AI tools to improve leukemia diagnostics by accurately analyzing blood smear images and providing transparent reasoning.

## Contribution

The novel contribution is an AI pipeline combining CNNs and XAI methods (LIME and Grad-CAM) for leukemia diagnostics with high accuracy and interpretability.

## Key findings

- MobileNetV2 achieved 97.9% accuracy and F1-score on a five-class leukemia diagnostic task.
- DenseNet-121 and MobileNetV2 provided the strongest nucleus-centric explanations aligned with clinical cues.
- The proposed AI pipeline outperformed baselines in accuracy and interpretability on a large, diverse dataset.

## Abstract

Background/Objectives: Conventional workflows, peripheral blood smears, and bone marrow assessment supplemented by LDI-PCR, molecular cytogenetics, and array-CGH, are expert-driven in the face of biological and imaging variability. Methods: We propose an AI pipeline that integrates convolutional neural networks (CNNs) and transfer learning-based models with two explainable AI (XAI) approaches, LIME and Grad-Cam, to deliver both high diagnostic accuracy and transparent rationale. Seven public sources were curated into a unified benchmark (66,550 images) covering ALL, AML, CLL, CML, and healthy controls; images were standardized, ROI-cropped, and split with stratification (80/10/10). We fine-tuned multiple backbones (DenseNet-121, MobileNetV2, VGG16, InceptionV3, ResNet50, Xception, and a custom CNN) and evaluated the accuracy and F1-score, benchmarking against the recent literature. Results: On the five-class task (ALL/AML/CLL/CML/Healthy), MobileNetV2 achieved 97.9% accuracy/F1, with DenseNet-121 reaching 97.66% F1. On ALL subtypes (Benign, Early, Pre, Pro) and across tasks, DenseNet121 and MobileNetV2 were the most reliable, achieving state-of-the-art accuracy with the strongest, nucleus-centric explanations. Conclusions: XAI analyses (LIME, Grad-CAM) consistently localized leukemic nuclei and other cell-intrinsic morphology, aligning saliency with clinical cues and model performance. Compared with baselines, our approach matched or exceeded accuracy while providing stronger, corroborated interpretability on a substantially larger and more diverse dataset.