Medical image segmentation of gadolinium enhancement magnetic resonance imaging (GE MRI) is an important task in clinical applications. However, manual annotation is time-consuming and requires specialized expertise. Semi-supervised segmentation methods that leverage both labeled and unlabeled data have shown promise, with contrastive learning emerging as a particularly effective approach. In this paper, we propose a contrastive learning strategy of foreground and background representations for semi-supervised 3D medical image segmentation (FBA-Net). Specifically, we leverage the contrastive loss to learn representations of both the foreground and background regions in the images. By training the network to distinguish between foreground-background pairs, we aim to learn a representation that can effectively capture the anatomical structures of interest. Experiments on three medical segmentation datasets demonstrate state-of-the-art performance. Notably, our method achieves a Dice score of 91.31% with only 20% labeled data, which is remarkably close to the 91.62% score of the fully supervised method that uses 100% labeled data on the left atrium dataset. Our framework has the potential to advance the field of semi-supervised 3D medical image segmentation and enable more efficient and accurate analysis of medical images with a limited amount of annotated labels.

翻译：钆增强磁共振成像（GE MRI）的医学图像分割是临床应用中的重要任务。然而，手动标注既耗时又需要专业知识。利用标注和未标注数据的半监督分割方法已展现出潜力，其中对比学习作为一种特别有效的方法脱颖而出。本文提出一种前景与背景表征的对比学习策略，用于半监督三维医学图像分割（FBA-Net）。具体而言，我们利用对比损失来学习图像中前景和背景区域的表征。通过训练网络区分前景-背景对，我们旨在学习能够有效捕捉感兴趣解剖结构的表征。在三个医学分割数据集上的实验表明，该方法达到了最先进的性能。值得注意的是，在左心房数据集中，仅使用20%标注数据时，我们的方法取得了91.31%的Dice分数，这极接近使用100%标注数据的全监督方法所达到的91.62%的分数。我们的框架有望推动半监督三维医学图像分割领域的发展，并能在标注数据有限的情况下实现更高效、更准确的医学图像分析。