Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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.

Linshan Wu, Jiaxin Zhuang, Hao Chen• 2024

Related benchmarks

TaskDatasetResultRank
Medical Image ClassificationOrganMNIST3D
Accuracy96
44
Medical Image SegmentationACDC
DSC85.57
33
Medical Image SegmentationMSD Pancreas (test)
DSC81.1
30
Medical Image ClassificationNoduleMNIST3D
AUC76
30
ClassificationCC-CCII--
24
Medical Image SegmentationMSD Pancreas
Dice51.37
23
Semantic segmentationCHAOS
Dice97
16
3D SegmentationMSD-Liver
DSC95
15
Pan-cancer SegmentationInternal datasets
Lung Tumor DSC53.4
14
Visual SegmentationKiTS23
KTC Dice Score0.975
14
Showing 10 of 45 rows

Other info

Follow for update