Computer-Aided Diagnosis (CAD) of Stroke in The Brain CT-Scan Images Using Integration of Grey Level Co-Occurrence Matrix (GLCM) Texture Feature Extraction And K-Nearest-Neighbour (KNN) Classification

This study presents an advanced and efficient computer-aided diagnosis (CAD) system for stroke detection using brain CT images, integrating Grey Level Co-Occurrence Matrix (GLCM) feature extraction and K-Nearest Neighbour (KNN) classification. The objective is to enhance stroke detection accuracy and efficiency in clinical settings. A dataset of 400 brain CT images, divided into 300 for training and 100 for testing with equal normal and stroke classes, was used to evaluate performance. The GLCM texture features significantly differentiated between normal and stroke images. The optimized KNN model demonstrated high performance, achieving 99% classification accuracy, 100% sensitivity, 98% specificity, 97% precision, a 99% F1 score, 100% positive predictive value, and 98% negative predictive value. The average computation time per image was 3.2 seconds, indicating feasibility for real-time application. In conclusion, the GLCM-KNN integrated CAD system proves to be an accurate and efficient method for stroke diagnosis on brain CT scans, offering a potential solution for early stroke detection in resource-limited healthcare facilities.