An OpenMind for 3D medical vision self-supervised learning
This work addresses inconsistency in 3D medical vision SSL for researchers and practitioners, providing a foundation for future advancements, though it is incremental in establishing benchmarks.
The paper tackled the lack of standardization in self-supervised learning for 3D medical images by publishing the largest public pre-training dataset of 114k 3D brain MRI volumes and benchmarking existing methods, showing that pre-trained methods can exceed a strong from-scratch baseline.
The field of self-supervised learning (SSL) for 3D medical images lacks consistency and standardization. While many methods have been developed, it is impossible to identify the current state-of-the-art, due to i) varying and small pretraining datasets, ii) varying architectures, and iii) being evaluated on differing downstream datasets. In this paper, we bring clarity to this field and lay the foundation for further method advancements through three key contributions: We a) publish the largest publicly available pre-training dataset comprising 114k 3D brain MRI volumes, enabling all practitioners to pre-train on a large-scale dataset. We b) benchmark existing 3D self-supervised learning methods on this dataset for a state-of-the-art CNN and Transformer architecture, clarifying the state of 3D SSL pre-training. Among many findings, we show that pre-trained methods can exceed a strong from-scratch nnU-Net ResEnc-L baseline. Lastly, we c) publish the code of our pre-training and fine-tuning frameworks and provide the pre-trained models created during the benchmarking process to facilitate rapid adoption and reproduction.