Accurate Brain Disease Diagnosis with UE-CNN Uncertainty Discrimination

Detecting uncertainty in brain disease diagnosis is crucial to avoid wrong interpretations and improve patient health. This research work proposes a novel technique, UE-CNN (Uncertainty Estimation Convolutional Neural Network) to measure the uncertainty in the process of brain disease diagnosis. The CNN layers classify uncertainty while processing the input data. Here, various methodologies and domains are employed to detect uncertainty. By removing uncertainty from the input brain images, the system's efficiency can be enhanced. The key performance measures in this study are accuracy and efficiency, wherein the detection of brain diseases is the ultimate goal. Only the significant diseases impacting a large population are considered from the dataset. The proposed UE-CNN technique performs uncertainty detection and achieves the goal of accurate brain disease detection and classification. From the results, it is evident that the proposed UE-CNN outperforms the other existing CNN models in terms of accuracy and overall performance.