A stacked custom convolution neural network for voxel-based human brain morphometry classification.

The precise identification of brain tumors in people using automatic methods is still a problem. While several studies have been offered to identify brain tumors, very few of them take into account the method of voxel-based morphometry (VBM) during the classification phase. This research aims to address these limitations by improving edge detection and classification accuracy. The proposed work combines a stacked custom Convolutional Neural Network (CNN) and VBM. The classification of brain tumors is completed by this employment. Initially, the input brain images are normalized and segmented using VBM. A ten-fold cross validation was utilized to train as well as test the proposed model. Additionally, the dataset's size is increased through data augmentation for more robust training. The proposed model performance is estimated by comparing with diverse existing methods. The receiver operating characteristics (ROC) curve with other parameters, including the F1 score as well as negative prediction value, are used to determine the proposed model effectiveness. The proposed VBM and stacked custom CNN model achieves significant improvements. The proposed model performed with a higher accuracy level of 98%. The results confirm that the proposed VBM and stacked custom CNN model outperforms other existing approaches in brain tumor classification.