Implementation of FFT-Based Convolutional Neural Networks on Medical Imagery for Studying Performance Boost

Abstract

This study focuses on the implementation of CNNs based on the Fast Fourier Transform (FFT) in medical images to study the performance boost compared to traditional neural networks. Using a Kaggle dataset of brain tumour imagery, we examine the effectiveness of FFT-based CNNs for the detection and classification of brain tumours. By leveraging the advantages of FFT, we aim to improve the efficiency and accuracy of CNNs in analyzing medical images. Our results demonstrate that FFT-based CNNs outperform traditional CNNs in terms of accuracy and computational efficiency. This performance boost is attributed to the inherent properties of FFT, which enable faster convolution operations and reduced complexity. In order to ensure a fair comparison between traditional CNNs and Fourier Transform-based convolutions, the forward pass for both methods was implemented from scratch using NumPy and SciPy libraries. By doing so, any optimization benefits gained by either technique through specific libraries or computation platforms are eliminated. This approach allows for a more accurate evaluation of the relative performance of each method in terms of inference time and accuracy, while also providing insights into potential areas for improvement and optimization.