Slice interpolation of medical images using enhanced fuzzy radial basis function neural networks

• Published in: Computers in biology and medicine Vol. 110; pp. 66 - 78
• Main Authors: Chao, Zhen, Kim, Hee-Joung
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.07.2019; Elsevier Limited
• Subjects: Algorithms; Artificial neural networks; Big Data; Brain; Brain research; Conflicts of interest; Deep learning; Enhanced radial basis function neural network; Fuzzy logic; Human factors; Hybrid of gravity search algorithm and error backpropagation algorithm; Image enhancement; Interpolation; Magnetic resonance imaging; Medical imaging; Methods; Missing slice images; Neural networks; Neurons; NMR; Nuclear magnetic resonance; Performance enhancement; Radial basis function; Registration; Slice interpolation method; Enhanced radial basis function neural network; Slice interpolation method; Missing slice images; Hybrid of gravity search algorithm and error backpropagation algorithm
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2019.05.013

Volume data composed of complete slice images play an indispensable role in medical diagnoses. However, system or human factors often lead to the loss of slice images. In recent years, various interpolation algorithms have been proposed to solve these problems. Although these algorithms are effective, the interpolated images have some shortcomings, such as less accurate recovery and missing details. In this study, we propose a new method based on an enhanced fuzzy radial basis function neural network to improve the performance of the interpolation method. The neural network includes an input layer (six input neurons), three hidden layers of neurons, and the output layer (one output neuron), and we propose a patch matching method to select the input variables of the neural network. Accordingly, we use two normal pending images to be interpolated as the input. Final output data is obtained by applying the trained neural network. In examining four groups of medical images, the proposed method outperforms five other methods, achieving the highest similarity image metric (ESSIM) values of 0.96, 0.95, 0.94, and 0.92 and the lowest mean squared difference (MSD) values of 35.5, 41.2, 50.9, and 47.1. In addition, for a whole MRI brain volume data experiment, the average MSD and ESSIM values of the proposed method and other methods are (41.62, 0.95) and (57.13, 0.90), respectively. The results indicate that the proposed method is superior to the other methods. •Proposing fuzzy radial basis function neural network to slice interpolation.•Applying the composite pattern to train and update the neural network.•Improving the accuracy of interpolation by comparing with other current methods.