Medical Image Classification Using RNN in Quadri-Partitioned Neutrosophic Set

Abstract

The classification of brain tumor is essential for both diagnostic and therapeutic planning. Recurrent neural networks (RNNs) have demonstrated promising results in analyzing sequential data in recent years. Quadri-partitioned neutrosophic sets additionally offer a structure for capturing ambiguities and uncertainties in classification problems. This study investigates the categorization of brain tumors using an RNN with a quadri-partitioned neutrosophic set. The study aims to increase classification accuracy and offer information on how certain forecasts can be made. The suggested method QPN-RNN’s accuracy in classifying brain tumors while considering the quadri-partitioned neutrosophic set is shown by experimental data.