3D Segmentation with Fully Trainable Gabor Kernels and Pearson's Correlation Coefficient

TL;DR

This paper introduces a fully trainable Gabor kernel layer and a Pearson correlation-based loss function for 3D image segmentation, achieving high accuracy with significantly fewer parameters than traditional models.

Contribution

It proposes a novel trainable Gabor kernel layer and a Pearson correlation-based loss function, enhancing feature extraction and robustness in 3D segmentation tasks.

Findings

Achieved 83% Dice coefficient on 3D brain MRI segmentation.

Reduced model size to 1.6 million parameters, 44 times smaller than V-Net.

Demonstrated effectiveness of learnable Gabor kernels in deep learning.

Abstract

The convolutional layer and loss function are two fundamental components in deep learning. Because of the success of conventional deep learning kernels, the less versatile Gabor kernels become less popular despite the fact that they can provide abundant features at different frequencies, orientations, and scales with much fewer parameters. For existing loss functions for multi-class image segmentation, there is usually a tradeoff among accuracy, robustness to hyperparameters, and manual weight selections for combining different losses. Therefore, to gain the benefits of using Gabor kernels while keeping the advantage of automatic feature generation in deep learning, we propose a fully trainable Gabor-based convolutional layer where all Gabor parameters are trainable through backpropagation. Furthermore, we propose a loss function based on the Pearson's correlation coefficient, which is accurate, robust to learning rates, and does not require manual weight selections. Experiments on 43 3D brain magnetic resonance images with 19 anatomical structures show that, using the proposed loss function with a proper combination of conventional and Gabor-based kernels, we can train a network with only 1.6 million parameters to achieve an average Dice coefficient of 83%. This size is 44 times smaller than the original V-Net which has 71 million parameters. This paper demonstrates the potentials of using learnable parametric kernels in deep learning for 3D segmentation.