Morphological Analysis and Subtype Detection of Acute Myeloid Leukemia in High-Resolution Blood Smears Using ConvNeXT

Abstract

Key Objective: Develop a ConvNeXt-based deep learning model for AML subtype classification using high-resolution blood smear images. Compare ConvNeXt’s performance with traditional CNNs (ResNet50) and Vision Transformers to assess classification accuracy and feature extraction. Enhance model generalization and stability using Stochastic Weight Averaging (SWA), Mixup augmentation, and bias mitigation techniques. Explore multi-modal AI by integrating genomic and molecular data to improve leukemia classification and personalized treatment strategies. (1) Background: Acute Myeloid Leukemia (AML) is a complex hematologic malignancy where accurate subtype classification is crucial for targeted treatment and improved patient outcomes. Automated AML subtype detection is especially important for underrepresented subtypes to ensure equitable diagnostics; (2) Methods: This study explores the potential of ConvNeXt, an advanced convolutional neural network architecture, for classifying high-resolution peripheral blood smear images into AML subtypes. A deep learning pipeline was developed, integrating Stochastic Weight Averaging (SWA) for model stability, Mixup data augmentation to enhance generalization, and Grad-CAM for model interpretability, ensuring biologically meaningful feature visualization. Various models, including ResNet50 and Vision Transformers, were benchmarked for comparative performance analysis; (3) Results: ConvNeXt outperformed ResNet50, achieving a classification accuracy of 95% compared to 91% for ResNet50 and 81% for transformer-based models (Vision Transformers). Grad-CAM visualizations provided biologically interpretable heatmaps, enhancing trust in computational predictions and bridging the gap between AI-driven diagnostics and clinical decision-making. Ablation studies highlighted the contributions of data augmentation, optimizer selection, and hyperparameter tuning, demonstrating the robustness and adaptability of the model; (4) Conclusions: This study advances AI’s role in hematopathology by combining high classification performance, explainability, and scalability. ConvNeXt offers a robust, interpretable, and scalable solution for AML subtype classification, improving diagnostic precision and supporting clinical decision-making. These results underscore the potential for AI-driven advancements in equitable and efficient AML diagnostics.