An Optimal Detection for Leukaemia Cancer Based On RNS-Metaheuristic Technique in Micro Array Dataset

Abstract

This paper addresses the critical challenge of leukaemia cancer detection through the integration of Residue Number System (RNS) and Convolutional Neural Network (CNN) Deep Learning Framework using a Microarray dataset. Leveraging a dataset obtained from the Kaggle machine learning repository, the study employs a comprehensive image processing pipeline, encompassing grayscale conversion, data augmentation, contrast enhancement, geometry normalization, and OTSU segmentation. The subsequent stages involve feature extraction using Histogram of Gradient (HOG) and comparative feature selection through Ant Colony Optimization (ACO) and an optimized ACO+RNS approaches. Results indicates that incorporating ACO+RNS outperforms the ACO-only in terms of classification accuracy, sensitivity, specificity, precision, and F1-score. Notably, the ACO+RNS model achieves a lower error rate and reduced training time, emphasizing the  efficiency of incorporating Residue Number System encoding in feature selection.