Large-Scale 3D Medical Image Pre-training with Geometric Context Priors
About
The scarcity of annotations poses a significant challenge in medical image analysis. Large-scale pre-training has emerged as a promising label-efficient solution, owing to the utilization of large-scale data, large models, and advanced pre-training techniques. However, its development in medical images remains underexplored. The primary challenge lies in harnessing large-scale unlabeled data and learning high-level semantics without annotations. We observe that 3D medical images exhibit consistent geometric context, i.e., consistent geometric relations between different organs, which leads to a promising way for learning consistent representations. Motivated by this, we introduce a simple-yet-effective Volume Contrast (VoCo) framework to leverage geometric context priors for self-supervision. Given an input volume, we extract base crops from different regions to construct positive and negative pairs for contrastive learning. Then we predict the contextual position of a random crop by contrasting its similarity to the base crops. In this way, VoCo encodes the inherent geometric context into model representations, facilitating high-level semantic learning without annotations. Specifically, we (1) introduce the largest medical pre-training dataset PreCT-160K; (2) investigate scaling laws and propose guidelines for tailoring different model sizes to various medical tasks; (3) build a benchmark encompassing 48 medical tasks. Extensive experiments highlight the superiority of VoCo. Codes at https://github.com/Luffy03/Large-Scale-Medical.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Pan-cancer Segmentation | Internal datasets | Lung Tumor DSC53.4 | 14 | |
| Pan-cancer Screening | FLARE 2023 | DSC50.6 | 10 | |
| Pan-cancer Segmentation | IRCADb liver tumors (External) | DSC0.565 | 10 | |
| Pan-cancer Segmentation | Rider lung tumors (External) | DSC (%)31.3 | 10 | |
| Pan-cancer Segmentation | External Datasets Rider, Corona, IRCADb Average | Average DSC (%)47.9 | 10 | |
| Abdominal Organ Segmentation | FLARE 23 | Duration114 | 10 | |
| Pan-cancer Segmentation | Corona COVID-19 (External) | DSC55.8 | 10 | |
| Pan-cancer detection | Internal 16 datasets (val) | Lung Tumor91.1 | 10 | |
| Pan-cancer Segmentation | Healthy Datasets CHAOS, TCIA, Atlas | CHAOS Score40 | 10 | |
| Pan-cancer Screening | MICCAI FLARE25 leaderboard (val) | DSC47.5 | 4 |