Efficient Semi-Supervised Gross Target Volume of Nasopharyngeal Carcinoma Segmentation via Uncertainty Rectified Pyramid Consistency

TL;DR

This paper introduces a semi-supervised segmentation framework for nasopharyngeal carcinoma that leverages pyramid predictions and uncertainty rectification to improve accuracy with limited labeled data.

Contribution

It proposes a novel Uncertainty Rectified Pyramid Consistency (URPC) regularization method that enhances semi-supervised segmentation by learning from multi-scale predictions and uncertainty estimation.

Findings

Significant performance improvement with only 10-20% labeled data.

Outperforms five state-of-the-art semi-supervised methods.

Achieves near fully supervised accuracy with 50% labeled data.

Abstract

Gross Target Volume (GTV) segmentation plays an irreplaceable role in radiotherapy planning for Nasopharyngeal Carcinoma (NPC). Despite that Convolutional Neural Networks (CNN) have achieved good performance for this task, they rely on a large set of labeled images for training, which is expensive and time-consuming to acquire. In this paper, we propose a novel framework with Uncertainty Rectified Pyramid Consistency (URPC) regularization for semi-supervised NPC GTV segmentation. Concretely, we extend a backbone segmentation network to produce pyramid predictions at different scales. The pyramid predictions network (PPNet) is supervised by the ground truth of labeled images and a multi-scale consistency loss for unlabeled images, motivated by the fact that prediction at different scales for the same input should be similar and consistent. However, due to the different resolution of these predictions, encouraging them to be consistent at each pixel directly has low robustness and may lose some fine details. To address this problem, we further design a novel uncertainty rectifying module to enable the framework to gradually learn from meaningful and reliable consensual regions at different scales. Experimental results on a dataset with 258 NPC MR images showed that with only 10% or 20% images labeled, our method largely improved the segmentation performance by leveraging the unlabeled images, and it also outperformed five state-of-the-art semi-supervised segmentation methods. Moreover, when only 50% images labeled, URPC achieved an average Dice score of 82.74% that was close to fully supervised learning.