On the influence of Dice loss function in multi-class organ segmentation of abdominal CT using 3D fully convolutional networks

TL;DR

This study examines how different Dice loss function weightings and initial learning rates affect multi-organ segmentation accuracy in 3D abdominal CT images using deep learning, highlighting the importance of loss function choice.

Contribution

It provides a comparative analysis of various Dice loss weightings and initial learning rates, revealing their combined impact on segmentation performance in medical imaging.

Findings

Uniform weighting achieved highest average Dice score at low learning rate.

Square weighting performed poorly at low learning rate but well at higher rate.

Class balancing weights and learning rate significantly influence segmentation accuracy.

Abstract

Deep learning-based methods achieved impressive results for the segmentation of medical images. With the development of 3D fully convolutional networks (FCNs), it has become feasible to produce improved results for multi-organ segmentation of 3D computed tomography (CT) images. The results of multi-organ segmentation using deep learning-based methods not only depend on the choice of networks architecture, but also strongly rely on the choice of loss function. In this paper, we present a discussion on the influence of Dice-based loss functions for multi-class organ segmentation using a dataset of abdominal CT volumes. We investigated three different types of weighting the Dice loss functions based on class label frequencies (uniform, simple and square) and evaluate their influence on segmentation accuracies. Furthermore, we compared the influence of different initial learning rates. We achieved average Dice scores of 81.3%, 59.5% and 31.7% for uniform, simple and square types of weighting when the learning rate is 0.001, and 78.2%, 81.0% and 58.5% for each weighting when the learning rate is 0.01. Our experiments indicated a strong relationship between class balancing weights and initial learning rate in training.