AdLER: Adversarial Training with Label Error Rectification for One-Shot Medical Image Segmentation

TL;DR

AdLER introduces adversarial training and label error rectification to improve one-shot medical image segmentation, addressing data diversity and label errors for better accuracy in limited-data scenarios.

Contribution

The paper proposes a novel one-shot segmentation method combining adversarial training, dual consistency constraints, and label error rectification to enhance segmentation performance with limited data.

Findings

Outperforms state-of-the-art methods on CANDI and ABIDE datasets.

Achieves up to 4.9% higher Dice scores in experiments.

Improves robustness and authenticity of segmentation results.

Abstract

Accurate automatic segmentation of medical images typically requires large datasets with high-quality annotations, making it less applicable in clinical settings due to limited training data. One-shot segmentation based on learned transformations (OSSLT) has shown promise when labeled data is extremely limited, typically including unsupervised deformable registration, data augmentation with learned registration, and segmentation learned from augmented data. However, current one-shot segmentation methods are challenged by limited data diversity during augmentation, and potential label errors caused by imperfect registration. To address these issues, we propose a novel one-shot medical image segmentation method with adversarial training and label error rectification (AdLER), with the aim of improving the diversity of generated data and correcting label errors to enhance segmentation performance. Specifically, we implement a novel dual consistency constraint to ensure anatomy-aligned registration that lessens registration errors. Furthermore, we develop an adversarial training strategy to augment the atlas image, which ensures both generation diversity and segmentation robustness. We also propose to rectify potential label errors in the augmented atlas images by estimating segmentation uncertainty, which can compensate for the imperfect nature of deformable registration and improve segmentation authenticity. Experiments on the CANDI and ABIDE datasets demonstrate that the proposed AdLER outperforms previous state-of-the-art methods by 0.7% (CANDI), 3.6% (ABIDE "seen"), and 4.9% (ABIDE "unseen") in segmentation based on Dice scores, respectively. The source code will be available at https://github.com/hsiangyuzhao/AdLER.