CDPM-align: multi-scale guidance-aligned diffusion pretraining for robust few-shot anatomical landmark detection

Conference item

Anatomical landmark detection is a fundamental task in medical image analysis supporting a wide range of diagnostic and interventional workflows. Although recent methods have achieved submillimetric localisation, accuracy alone is not sufficient for clinical deployment, requiring reliability and robustness in prediction. Despite its clinical relevance, the impact of representation learning in this context is still underexplored. In this work, we introduce CDPM-align, a multiscale guidance-aligned conditional diffusion pre-training for anatomical landmark detection. Our experimental setup focuses on a few images and a few annotation regimes. Specifically, we employ three popular heterogeneous small-scale benchmark datasets for representation learning via conditional generative pre-training. Furthermore, we consider lowannotation scenarios for the downstream task of landmark detection, with 10 and 25 annotated images, reflecting realistic trade-offs between clinical effort and resource constraints for annotations. Our results confirm that generative pre-training enables the model to learn a robust representation. This improves both accuracy and uncertainty on the downstream tasks, advancing towards safe and efficient clinical deployment.

Authors: Di Via, R; Voiculescu, I; Odone, F; Pastore, VP

• Publication status: Accepted
• Peer review status: Peer reviewed
• Publication date: 2026-10-01
• Acceptance date: 2026-05-07
• Event title: International Conference of Medical Image Computing and Computer Assisted Intervention (MICCAI 2026)
• Event location: Strasbourg, France
• Event website: https://conferences.miccai.org/2026/
• Event start date: 2026-09-27
• Event end date: 2026-10-01
• Language: English
• Keywords: anatomical landmark detection; generative pretraining; diffusion models; few-shot learning; uncertainty quantification