Medical image segmentation is a fundamental yet challenging task due to the arduous process of acquiring large volumes of high-quality labeled data from experts. Contrastive learning offers a promising but still problematic solution to this dilemma. Because existing medical contrastive learning strategies focus on extracting image-level representation, which ignores abundant multi-level representations. And they underutilize the decoder either by random initialization or separate pre-training from the encoder, thereby neglecting the potential collaboration between the encoder and decoder. To address these issues, we propose a novel multi-level asymmetric contrastive learning framework named MACL for volumetric medical image segmentation pre-training. Specifically, we design an asymmetric contrastive learning structure to pre-train encoder and decoder simultaneously to provide better initialization for segmentation models. Moreover, we develop a multi-level contrastive learning strategy that integrates correspondences across feature-level, image-level, and pixel-level representations to ensure the encoder and decoder capture comprehensive details from representations of varying scales and granularities during the pre-training phase. Finally, experiments on 12 volumetric medical image datasets indicate our MACL framework outperforms existing 11 contrastive learning strategies. {\itshape i.e.} Our MACL achieves a superior performance with more precise predictions from visualization figures and 2.28\%, 1.32\%, 1.62\% and 1.60\% Average Dice higher than previous best results on CHD, MMWHS, CHAOS and AMOS, respectively. And our MACL also has a strong generalization ability among 5 variant U-Net backbones. Our code will be available at https://github.com/stevezs315/MACL.

翻译：医学图像分割是一项基础但具有挑战性的任务，原因在于从专家获取大规模高质量标注数据的流程极为困难。对比学习为解决这一困境提供了有希望但仍存在问题的方案。现有医学对比学习策略聚焦于提取图像级表征，忽略了丰富的多层表征。同时，它们对解码器的利用不足，要么采用随机初始化，要么将解码器与编码器分离预训练，从而忽视了编码器与解码器之间的潜在协同作用。针对这些问题，我们提出了一种名为MACL的新型多层非对称对比学习框架，用于体素医学图像分割预训练。具体而言，我们设计了一种非对称对比学习结构，同时预训练编码器和解码器，从而为分割模型提供更优的初始化。此外，我们开发了一种多层对比学习策略，该策略整合了特征级、图像级和像素级表征之间的对应关系，确保编码器和解码器在预训练阶段能够从不同尺度和粒度的表征中捕获全面细节。最后，在12个体素医学图像数据集上的实验表明，我们的MACL框架优于现有的11种对比学习策略。即，我们的MACL取得了更优性能，可视化图显示预测更精确，且在CHD、MMWHS、CHAOS和AMOS数据集上的平均Dice系数分别比此前最佳结果高出2.28%、1.32%、1.62%和1.60%。此外，MACL在5种U-Net变体骨干网络上也展现出强大的泛化能力。我们的代码将在https://github.com/stevezs315/MACL上公开。