Tackling the Class Imbalance Problem of Deep Learning Based Head and Neck Organ Segmentation

TL;DR

This paper improves deep learning-based head and neck organ segmentation by optimizing patch size and introducing a class adaptive Dice loss, significantly enhancing accuracy and reducing boundary errors in imbalanced data.

Contribution

It proposes a novel approach combining patch-size optimization and a new loss function to address class imbalance in medical image segmentation.

Findings

3% increase in Dice score

22% reduction in Hausdorff distance

Achieved segmentation accuracy of 0.8±0.15 with improved boundary precision

Abstract

The segmentation of organs at risk (OAR) is a required precondition for the cancer treatment with image guided radiation therapy. The automation of the segmentation task is therefore of high clinical relevance. Deep Learning (DL) based medical image segmentation is currently the most successful approach, but suffers from the over-presence of the background class and the anatomically given organ size difference, which is most severe in the head and neck (HAN) area. To tackle the HAN area specific class imbalance problem we first optimize the patch-size of the currently best performing general purpose segmentation framework, the nnU-Net, based on the introduced class imbalance measurement, and second, introduce the class adaptive Dice loss to further compensate for the highly imbalanced setting. Both the patch-size and the loss function are parameters with direct influence on the class imbalance and their optimization leads to a 3\% increase of the Dice score and 22% reduction of the 95% Hausdorff distance compared to the baseline, finally reaching $0.8\pm0.15$ and $3.17\pm1.7$ mm for the segmentation of seven HAN organs using a single and simple neural network. The patch-size optimization and the class adaptive Dice loss are both simply integrable in current DL based segmentation approaches and allow to increase the performance for class imbalanced segmentation tasks.