Reliable Evaluation of MRI Motion Correction: Dataset and Insights
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916782296530944 |
|---|---|
| author | Wang, Kun Klug, Tobit Ruschke, Stefan Kirschke, Jan S. Heckel, Reinhard |
| author_facet | Wang, Kun Klug, Tobit Ruschke, Stefan Kirschke, Jan S. Heckel, Reinhard |
| contents | Correcting motion artifacts in MRI is important, as they can hinder accurate diagnosis. However, evaluating deep learning-based and classical motion correction methods remains fundamentally difficult due to the lack of accessible ground-truth target data. To address this challenge, we study three evaluation approaches: real-world evaluation based on reference scans, simulated motion, and reference-free evaluation, each with its merits and shortcomings. To enable evaluation with real-world motion artifacts, we release PMoC3D, a dataset consisting of unprocessed Paired Motion-Corrupted 3D brain MRI data. To advance evaluation quality, we introduce MoMRISim, a feature-space metric trained for evaluating motion reconstructions. We assess each evaluation approach and find real-world evaluation together with MoMRISim, while not perfect, to be most reliable. Evaluation based on simulated motion systematically exaggerates algorithm performance, and reference-free evaluation overrates oversmoothed deep learning outputs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05975 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reliable Evaluation of MRI Motion Correction: Dataset and Insights Wang, Kun Klug, Tobit Ruschke, Stefan Kirschke, Jan S. Heckel, Reinhard Image and Video Processing Correcting motion artifacts in MRI is important, as they can hinder accurate diagnosis. However, evaluating deep learning-based and classical motion correction methods remains fundamentally difficult due to the lack of accessible ground-truth target data. To address this challenge, we study three evaluation approaches: real-world evaluation based on reference scans, simulated motion, and reference-free evaluation, each with its merits and shortcomings. To enable evaluation with real-world motion artifacts, we release PMoC3D, a dataset consisting of unprocessed Paired Motion-Corrupted 3D brain MRI data. To advance evaluation quality, we introduce MoMRISim, a feature-space metric trained for evaluating motion reconstructions. We assess each evaluation approach and find real-world evaluation together with MoMRISim, while not perfect, to be most reliable. Evaluation based on simulated motion systematically exaggerates algorithm performance, and reference-free evaluation overrates oversmoothed deep learning outputs. |
| title | Reliable Evaluation of MRI Motion Correction: Dataset and Insights |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2506.05975 |