Deep Learning CNN Model-Based Anomaly Detection in 3D Brain MRI Images using Feature Distribution Similarity

Towards detecting an anomaly in brain images, different approaches are discussed the literature. Features like white mass values and shape features have identified presence of tumors. Various deep learning models neural network has been adapted to problem tumor detection suffers meet maximum accuracy tumor. An Adaptive Feature Centric Distribution Similarity Based Anomaly Detection Model with Convolution Neural Network (AFCD-CNN) is sketched towards disease prediction handle problem. The model considers black-and-white distribution features. First, method applies Multi-Hop Neighbor Analysis (MHNA) algorithm normalizing image. Further, process uses Mass Determined Segmentation (AMDS) algorithm, which groups pixels MRI according black values. extracts ROI segmented image convolves CNN at training phase. designed convolve into one dimension. output layer neurons estimate (FDS) against various compute Class Weight (ACW). According ACW value, performed higher up 97% where time complexity reduced 32 seconds.