Early Detection of Acute Myeloid Leukemia (AML) Using YOLOv12 Deep Learning Model

TL;DR

This paper presents a deep learning approach using YOLOv12 combined with image segmentation techniques to accurately classify multiclass AML cells, achieving over 99% accuracy.

Contribution

The study introduces a novel combination of YOLOv12 with segmentation preprocessing for AML classification, enhancing accuracy over existing methods.

Findings

YOLOv12 with Otsu thresholding achieved 99.3% accuracy.

Cell-based segmentation outperformed nucleus-based segmentation.

The approach effectively distinguishes visually similar AML cell types.

Abstract

Acute Myeloid Leukemia (AML) is one of the most life-threatening type of blood cancers, and its accurate classification is considered and remains a challenging task due to the visual similarity between various cell types. This study addresses the classification of the multiclasses of AML cells Utilizing YOLOv12 deep learning model. We applied two segmentation approaches based on cell and nucleus features, using Hue channel and Otsu thresholding techniques to preprocess the images prior to classification. Our experiments demonstrate that YOLOv12 with Otsu thresholding on cell-based segmentation achieved the highest level of validation and test accuracy, both reaching 99.3%.