# MedDIFT: Multi-Scale Diffusion-Based Correspondence in 3D Medical Imaging

arXiv: https://arxiv.org/abs/2512.05571 · HTML: https://mlsanity.com/paper/2512.05571/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 6 of its 9 references that are in the map.
- First posted on arXiv 5 Dec 2025.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 6 of 6)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Emergent Correspondence from Image Diffusion](https://mlsanity.com/paper/2306.03881/) (2023)
- [MAISI: Medical AI for Synthetic Imaging](https://mlsanity.com/paper/2409.11169/) (2024)
- [uniGradICON: A Foundation Model for Medical Image Registration](https://mlsanity.com/paper/2403.05780/) (2024)
- [Guiding Registration with Emergent Similarity from Pre-Trained Diffusion Models](https://mlsanity.com/paper/2506.02419/) (2025)

## Abstract (arXiv)

Accurate spatial correspondence between medical images is essential for longitudinal analysis, lesion tracking, and image-guided interventions. Medical image registration methods rely on local intensity-based similarity measures, which fail to capture global semantic structure and often yield mismatches in low-contrast or anatomically variable regions. Recent advances in diffusion models suggest that their intermediate representations encode rich geometric and semantic information. We present MedDIFT, a training-free 3D correspondence framework that leverages multi-scale features from a pretrained latent medical diffusion model as voxel descriptors. MedDIFT fuses diffusion activations into rich voxel-wise descriptors and matches them via cosine similarity, with an optional local-search prior. On a publicly available lung CT dataset, MedDIFT shows promising capability in identifying anatomical correspondence without requiring any task-specific model training. Ablation experiments confirm that multi-level feature fusion and modest diffusion noise improve performance. Code is available online.