Research

Paper

TESTING March 05, 2026

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

Authors

Zahra Karimaghaloo, Dumitru Fetco, Haz-Edine Assemlal, Hassan Rivaz, Douglas L. Arnold

Abstract

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.

Metadata

arXiv ID: 2603.05693
Provider: ARXIV
Primary Category: eess.IV
Published: 2026-03-05
Fetched: 2026-03-09 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.05693v1</id>\n    <title>Longitudinal Lesion Inpainting in Brain MRI via 3D Region Aware Diffusion</title>\n    <updated>2026-03-05T21:34:47Z</updated>\n    <link href='https://arxiv.org/abs/2603.05693v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.05693v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='eess.IV'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-05T21:34:47Z</published>\n    <arxiv:primary_category term='eess.IV'/>\n    <author>\n      <name>Zahra Karimaghaloo</name>\n    </author>\n    <author>\n      <name>Dumitru Fetco</name>\n    </author>\n    <author>\n      <name>Haz-Edine Assemlal</name>\n    </author>\n    <author>\n      <name>Hassan Rivaz</name>\n    </author>\n    <author>\n      <name>Douglas L. Arnold</name>\n    </author>\n  </entry>"
}