Large-Scale 3D Medical Image Pre-Training With Geometric Context Priors
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026
DOI: 10.1109/tpami.2025.3639593 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026. Verfasst von Linshan Wu und 2 weiteren Autor:innen. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 151 Literaturangaben. Gefördert von: Innovation and Technology Commission, Research Grants Council of the Hong Kong Special Administrative Region.
Abstract (Originalsprache)
The scarcity of annotations poses a significant challenge in medical image analysis, which demands extensive efforts from radiologists, especially for high-dimension 3D medical images. 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 implicitly encodes the inherent geometric context into model representations, facilitating high-level semantic learning without annotations. To assess effectiveness, we (1) introduce PreCT-160 K, the largest medical image pre-training dataset to date, which comprises 160 K Computed Tomography (CT) volumes covering diverse anatomic structures; (2) investigate scaling laws and propose guidelines for tailoring different model sizes to various medical tasks; (3) build a comprehensive benchmark encompassing 51 medical tasks, including segmentation, classification, registration, and vision-language. Extensive experiments highlight the superiority of VoCo, showcasing promising transferability to unseen modalities and datasets. VoCo notably enhances performance on datasets with limited labeled cases and significantly expedites fine-tuning convergence.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- Innovation and Technology Commission
- Research Grants Council of the Hong Kong Special Administrative Region
Zitieren
APA
Wu, L., Zhuang, J., & Chen, H. (2026). Large-Scale 3D Medical Image Pre-Training With Geometric Context Priors. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/tpami.2025.3639593
Vancouver
Wu L, Zhuang J, Chen H. Large-Scale 3D Medical Image Pre-Training With Geometric Context Priors. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026. doi:10.1109/tpami.2025.3639593
BibTeX
@article{Wu2026,
author = {Wu, Linshan and Zhuang, Jiaxin and Chen, Hao},
title = {Large-Scale 3D Medical Image Pre-Training With Geometric Context Priors},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
doi = {10.1109/tpami.2025.3639593}
}
EUVIMED