Motion prediction model using adaptive neuro fuzzy network (ANFN) and probabilistic neural network (PNN) algorithm in 4-dimensional computed tomography (4DCT) images

Abstract

Introduction: Across the world, the major cause of death is due to lung cancer. Due to overlapping structure of cancer cell, earlier lung cancer detection is challenging. Image processing techniques are widely employed to detect lung cancer earlier. Objective: Novel method to prevent and predict lung cancer as well as to identify the most significant genetic and environmental factors has to be developed. Methods: The proposed system illustrates a novel predicting model using Adaptive Neuro-Fuzzy Network combined with probabilistic neural networks. Filtered image using Gaussian 3D operator has to predict the tumour growth direction. This model uses an adaptive neuro-fuzzy network and probabilistic neural network for better identification. Results: Simulation result gives a prediction of Tumour growth direction with its accuracy value, precision value, RMSE (root-mean-square error), specificity, positive predictive value, negative predictive value. Hence the simulation results show the prediction of Tumour growth. Conclusion: The proposed system illustrates a novel predicting model using Adaptive Neuro-Fuzzy Network combined with probabilistic neural networks. By predicting the movement of Tumour cells, it will be easier to control the tumour spreading. This can be done by the motion prediction model to reduce the growth of the tumour cells which is the contribution of this paper.