Estimation of Brain Age from MRI Images Using Convolutional Neural Network and Compared with K-Nearest Neighbor to Improve the Accuracy

The research aims in enhancing the precision of brain age estimation from MRI scans through the application of Convolutional Neural Networks (CNN) and to conduct a comparative analysis with the K-Nearest Neighbor (KNN) method. Kagle data is used in the Convolutional neural network (CNN). The study involves a comparison between the CNN algorithm and the K-Nearest Neighbor (KNN) method. Two groups, labeled as group 1 and group 2, each comprised 20 samples. Poor estimation of data collection is improved by using CNN with KNN at the accuracy rate of 94.31% to accuracy of 93.08%. The obtained value for the independent sample t-test is 0.029 (p<0.05). This shows that the two techniques have different statistical results. The estimation of brain age using the Convolutional Neural Network (CNN) involves assessing dataset efficiency and accuracy. In this regard, the CNN outperforms the K-Nearest Neighbor (KNN) method, achieving an accuracy rate of 94.31% compared to KNN's 93.08%.