Cross-Dimensional Medical Self-Supervised Representation Learning Based on a Pseudo-3D Transformation

TL;DR

This paper introduces a cross-dimensional self-supervised learning framework that leverages both 2D and 3D medical images through a pseudo-3D transformation, improving performance on various medical image analysis tasks.

Contribution

The paper proposes a novel cross-dimensional SSL framework using a pseudo-3D transformation to jointly utilize 2D and 3D data for medical image pre-training.

Findings

Outperforms existing SSL methods on 13 downstream tasks

Effectively integrates 2D and 3D data for improved learning

Enhances medical image analysis accuracy

Abstract

Medical image analysis suffers from a shortage of data, whether annotated or not. This becomes even more pronounced when it comes to 3D medical images. Self-Supervised Learning (SSL) can partially ease this situation by using unlabeled data. However, most existing SSL methods can only make use of data in a single dimensionality (e.g. 2D or 3D), and are incapable of enlarging the training dataset by using data with differing dimensionalities jointly. In this paper, we propose a new cross-dimensional SSL framework based on a pseudo-3D transformation (CDSSL-P3D), that can leverage both 2D and 3D data for joint pre-training. Specifically, we introduce an image transformation based on the im2col algorithm, which converts 2D images into a format consistent with 3D data. This transformation enables seamless integration of 2D and 3D data, and facilitates cross-dimensional self-supervised learning for 3D medical image analysis. We run extensive experiments on 13 downstream tasks, including 2D and 3D classification and segmentation. The results indicate that our CDSSL-P3D achieves superior performance, outperforming other advanced SSL methods.