Task-Conditioned 3D U-Nets via Hypernetworks for Data-Scarce Medical Segmentation

Hagen L, Müller J, Gmeiner M, Kainz B (2026)

Publication Type: Conference contribution

Publication year: 2026

Publisher: ML Research Press

Book Volume: 315

Pages Range: 3542-3560

Conference Proceedings Title: Proceedings of Machine Learning Research

Event location: Chientan TW

Abstract

Training 3D segmentation models typically requires extensive expert annotation, which is costly and often unavailable for rare or low-prevalence pathologies. We propose a hypernetwork-based framework that amortises the prediction of parameters for compact 3D U-Nets, enabling task-specific specialisation from as little as a single annotated volume. By learning shared anatomical structure, such as coarse shape, scale, and spatial organisation, across organs and imaging modalities, the hypernetwork generates task-conditioned network parameters, allowing controlled adaptation to previously unseen but anatomically related targets without full retraining. We evaluate the proposed approach on the CT TotalSegmentator and Medical Segmentation Decathlon benchmarks. The method achieves strong one-shot performance for anatomically homogeneous structures (e.g., liver, spleen, atrium) and demonstrates stable few-shot adaptation for more heterogeneous or low-contrast targets (e.g., tumours, prostate). In regimes with two to four annotated volumes, hypernetwork-generated U-Nets consistently outperform pretrained baselines and substantially reduce the performance gap to fully supervised models while using minimal annotation. These results indicate that weight prediction serves as an effective task-informed prior for data-scarce 3D medical image segmentation.

Authors with CRIS profile

Luca Hagen Professur für Image Data Exploration and Analysis Johanna Müller Professur für Image Data Exploration and Analysis Bernhard Kainz Professur für Image Data Exploration and Analysis

How to cite

APA:

Hagen, L., Müller, J., Gmeiner, M., & Kainz, B. (2026). Task-Conditioned 3D U-Nets via Hypernetworks for Data-Scarce Medical Segmentation. In Yuankai Huo, Mingchen Gao, Chang-Fu Kuo, Yueming Jin, Ruining Deng (Eds.), Proceedings of Machine Learning Research (pp. 3542-3560). Chientan, TW: ML Research Press.

MLA:

Hagen, Luca, et al. "Task-Conditioned 3D U-Nets via Hypernetworks for Data-Scarce Medical Segmentation." Proceedings of the 9th International Conference on Medical Imaging with Deep Learning, MIDL 2026, Chientan Ed. Yuankai Huo, Mingchen Gao, Chang-Fu Kuo, Yueming Jin, Ruining Deng, ML Research Press, 2026. 3542-3560.

BibTeX: Download