Anatomical Invariance Modeling and Semantic Alignment for Self-supervised Learning in 3D Medical Image Analysis

TL;DR

This paper introduces Alice, a self-supervised learning framework for 3D medical images that models anatomical invariance and semantic alignment, improving representation quality by leveraging intrinsic anatomical structures.

Contribution

Alice combines discriminative and generative objectives with a novel contrastive strategy and a conditional alignment module to better capture anatomical invariance and semantics in 3D medical images.

Findings

Outperforms previous SSL methods on three 3D medical tasks

Demonstrates superior representation learning capabilities

Validates effectiveness across diverse medical imaging datasets

Abstract

Self-supervised learning (SSL) has recently achieved promising performance for 3D medical image analysis 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 three 3D medical image analysis tasks demonstrate and validate the performance superiority of Alice, surpassing the previous best SSL counterpart methods and showing promising ability for united representation learning. Codes are available at https://github.com/alibaba-damo-academy/alice.