# Longitudinal Lesion Inpainting in Brain MRI via 3D Region Aware Diffusion

arXiv: https://arxiv.org/abs/2603.05693 · HTML: https://mlsanity.com/paper/2603.05693/

## 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 19 of its 28 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Efficient Diffusion Training via Min-SNR Weighting Strategy](https://mlsanity.com/paper/2303.09556/) (2023)
- [BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion](https://mlsanity.com/paper/2403.06976/) (2024)
- [MedGAN: Medical Image Translation using GANs](https://mlsanity.com/paper/1806.06397/) (2018)
- [SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truth](https://mlsanity.com/paper/1810.06498/) (2018)
- [Make-A-Volume: Leveraging Latent Diffusion Models for Cross-Modality 3D Brain MRI Synthesis](https://mlsanity.com/paper/2307.10094/) (2023)
- [Region-Adaptive Sampling for Diffusion Transformers](https://mlsanity.com/paper/2502.10389/) (2025)
- [Denoising Diffusion Models for 3D Healthy Brain Tissue Inpainting](https://mlsanity.com/paper/2403.14499/) (2024)
- [RAD: Region-Aware Diffusion Models for Image Inpainting](https://mlsanity.com/paper/2412.09191/) (2024)
- [Bi-Directional MS Lesion Filling and Synthesis Using Denoising Diffusion Implicit Model-based Lesion Repainting](https://mlsanity.com/paper/2410.05027/) (2024)
- [Rethinking Perceptual Metrics for Medical Image Translation](https://mlsanity.com/paper/2404.07318/) (2024)
- [LesionDiffusion: Towards Text-controlled General Lesion Synthesis](https://mlsanity.com/paper/2503.00741/) (2025)
- [PathoPainter: Augmenting Histopathology Segmentation via Tumor-aware Inpainting](https://mlsanity.com/paper/2503.04634/) (2025)
- [Diffusion-Based User-Guided Data Augmentation for Coronary Stenosis Detection](https://mlsanity.com/paper/2508.00438/) (2025)

## Abstract (arXiv)

Accurate longitudinal analysis of brain MRI is often hindered by evolving lesions, which bias automated neuroimaging pipelines. While deep generative models have shown promise in inpainting these lesions, most existing methods operate cross-sectionally or lack 3D anatomical continuity. We present a novel pseudo-3D longitudinal inpainting framework based on Denoising Diffusion Probabilistic Models (DDPM). Our approach utilizes multi-channel conditioning to incorporate longitudinal context from distinct visits (t_1, t_2) and extends Region-Aware Diffusion (RAD) to the medical domain, focusing the generative process on pathological regions without altering surrounding healthy tissue. We evaluated our model against state-of-the-art baselines on longitudinal brain MRI from 93 patients. Our model significantly outperforms the leading baseline (FastSurfer-LIT) in terms of perceptual fidelity, reducing the Learned Perceptual Image Patch Similarity (LPIPS) distance from 0.07 to 0.03 while effectively eliminating inter-slice discontinuities. Furthermore, our model demonstrates high longitudinal stability with a Temporal Fidelity Index of 1.024, closely approaching the ideal value of 1.0 and substantially narrowing the gap compared to LIT's TFI of 1.22. Notably, the RAD mechanism provides a substantial gain in efficiency; our framework achieves an average processing time of 2.53 min per volume, representing approximately 10x speedup over the 24.30 min required by LIT. By leveraging longitudinal priors and region-specific denoising, our framework provides a highly reliable and efficient preprocessing step for the study of progressive neurodegenerative diseases. A derivative dataset consisting of 93 pre-processed scans used for testing will be available upon request after acceptance. Code will be released upon acceptance.