Automated Detection of Acute Leukemia using K-mean Clustering Algorithm

TL;DR

This paper proposes an automated image analysis method using k-means clustering to detect acute leukemia, achieving high accuracy and reducing reliance on manual microscopic examination.

Contribution

It introduces a novel automated detection algorithm combining image enhancement, segmentation, and clustering for leukemia diagnosis.

Findings

Achieved 92.8% accuracy in leukemia detection

Effective segmentation of blood cell images

Validated with KNN and Naive Bayes classifiers

Abstract

Leukemia is a hematologic cancer which develops in blood tissue and triggers rapid production of immature and abnormal shaped white blood cells. Based on statistics it is found that the leukemia is one of the leading causes of death in men and women alike. Microscopic examination of blood sample or bone marrow smear is the most effective technique for diagnosis of leukemia. Pathologists analyze microscopic samples to make diagnostic assessments on the basis of characteristic cell features. Recently, computerized methods for cancer detection have been explored towards minimizing human intervention and providing accurate clinical information. This paper presents an algorithm for automated image based acute leukemia detection systems. The method implemented uses basic enhancement, morphology, filtering and segmenting technique to extract region of interest using k-means clustering algorithm. The proposed algorithm achieved an accuracy of 92.8% and is tested with Nearest Neighbor (KNN) and Naive Bayes Classifier on the data-set of 60 samples.