<![CDATA[Leukemia is a type of cancer that affects the blood-forming system and requires early detection to improve patient outcomes. One of the primary indicators of leukemia is the presence of blast cells in blood smears. Manual detection by hematologists is time-consuming and requires specialized expertise, prompting the need for automated classification methods. This study evaluates and compares the performance of three machine learning algorithms like K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Random Forest for detecting leukemia blast cells from microscopic blood images. The dataset used consists of 15,000 labeled images classified as either normal or blast cells. Feature extraction involved RGB and HSV color histograms, along with texture features derived from the Gray-Level Co-occurrence Matrix (GLCM). Model performance was assessed using confusion matrices and evaluated through accuracy, precision, recall, and F1-score. Among the models tested, Random Forest achieved the highest accuracy at 86.31%, followed by SVM at 83.61% and KNN at 81.40%. These results indicate that Random Forest is the most effective model for automated detection of leukemia blast cells in this context ]]>
Copyrights © 2026
