Self-supervised learning (SSL) has recently achieved promising performance for 3D medical image segmentation tasks. Most current methods follow existing SSL paradigm originally designed for photographic or natural images, which cannot explicitly and thoroughly exploit the intrinsic similar anatomical structures across varying medical images. This may in fact degrade the quality of learned deep representations by maximizing the similarity among features containing spatial misalignment information and different anatomical semantics. In this work, we propose a new self-supervised learning framework, namely Alice, that explicitly fulfills Anatomical invariance modeling and semantic alignment via elaborately combining discriminative and generative objectives. Alice introduces a new contrastive learning strategy which encourages the similarity between views that are diversely mined but with consistent high-level semantics, in order to learn invariant anatomical features. Moreover, we design a conditional anatomical feature alignment module to complement corrupted embeddings with globally matched semantics and inter-patch topology information, conditioned by the distribution of local image content, which permits to create better contrastive pairs. Our extensive quantitative experiments on two public 3D medical image segmentation benchmarks of FLARE 2022 and BTCV demonstrate and validate the performance superiority of Alice, surpassing the previous best SSL counterpart methods by 2.11% and 1.77% in Dice coefficients, respectively.

翻译：自监督学习（SSL）近期在三维医学图像分割任务中展现出令人瞩目的性能。现有方法大多遵循为摄影或自然图像设计的传统SSL范式，无法显式且充分地利用不同医学图像中固有的相似解剖结构。通过最大化包含空间错位信息与不同解剖语义的特征之间的相似性，实际上可能降低所学深度表征的质量。本文提出一种名为Alice的新型自监督学习框架，通过精巧结合判别式与生成式目标，显式实现解剖学不变性建模与语义对齐。Alice引入新型对比学习策略，鼓励多样挖掘但具有一致高层语义的视图之间的相似性，以学习不变解剖特征。此外，我们设计条件解剖特征对齐模块，通过局部图像内容分布的条件约束，用全局匹配的语义和块间拓扑信息补充受损嵌入，从而生成更优的对比对。在FLARE 2022与BTCV两个公开三维医学图像分割基准上的大量定量实验表明，Alice展现出性能优越性：其Dice系数分别超越现有最优SSL方法2.11%与1.77%。