Non-local means inpainting of MS lesions in longitudinal image processing
In medical imaging, multiple sclerosis (MS) lesions can lead to confounding effects in automatic morphometric processing tools such as registration, segmentation and cortical extraction and subsequently alter individual longitudinal measurements. Multiple magnetic resonance imaging (MRI) inpainting...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2015-12-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fnins.2015.00456/full |
| _version_ | 1818555748381097984 |
|---|---|
| author | Nicolas eGuizard Kunio eNakamura Kunio eNakamura Pierrick eCoupé Vladimir S. Fonov Douglas L Arnold D Louis Collins |
| author_facet | Nicolas eGuizard Kunio eNakamura Kunio eNakamura Pierrick eCoupé Vladimir S. Fonov Douglas L Arnold D Louis Collins |
| author_sort | Nicolas eGuizard |
| collection | DOAJ |
| description | In medical imaging, multiple sclerosis (MS) lesions can lead to confounding effects in automatic morphometric processing tools such as registration, segmentation and cortical extraction and subsequently alter individual longitudinal measurements. Multiple magnetic resonance imaging (MRI) inpainting techniques have been proposed to decrease the impact of MS lesions in medical image processing, however, most of these methods make the assumption that lesions only affect white matter. Here, we propose a method to fill lesion regions using the patch-based non-local mean (NLM) strategy. The method consists of a hierarchical concentric filling strategy after identification of the lesion region. The lesion is filled iteratively, based on the surrounding tissue intensity, using an onion peel strategy. This concentric technique presents the advantage of preserving the local information and therefore the continuity of the anatomy and does not require identification of any a priori normal brain tissues. The method is first evaluated on simulated artificial MS lesions and, second, we performed a power analysis to evaluate brain atrophy and ventricular growth in patients with MS. The method was compared to two different publicly available methods (FSL lesion fill and Lesion LEAP) and more classic method approaches. The proposed method was shown to exceed the other methods in reproducing the fidelity of the images where the lesions were inpainted. The method also improved the power to detect brain atrophy or ventricular growth by decreasing the sample size by 25% in the presence of MS lesions. |
| first_indexed | 2024-12-12T09:57:38Z |
| format | Article |
| id | doaj.art-7ca988ac06fd4ecab28f696152558d6f |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-12T09:57:38Z |
| publishDate | 2015-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-7ca988ac06fd4ecab28f696152558d6f2022-12-22T00:28:05ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2015-12-01910.3389/fnins.2015.00456170255Non-local means inpainting of MS lesions in longitudinal image processingNicolas eGuizard0Kunio eNakamura1Kunio eNakamura2Pierrick eCoupé3Vladimir S. Fonov4Douglas L Arnold5D Louis Collins6McGill UniversityMcGill UniversityLerner Research Institute, Cleveland ClinicLaboratoire Bordelais de Recherche en Informatique, Unité Mixte de Recherche CNRS (UMR 5800), »McGill UniversityMcGill UniversityMcGill UniversityIn medical imaging, multiple sclerosis (MS) lesions can lead to confounding effects in automatic morphometric processing tools such as registration, segmentation and cortical extraction and subsequently alter individual longitudinal measurements. Multiple magnetic resonance imaging (MRI) inpainting techniques have been proposed to decrease the impact of MS lesions in medical image processing, however, most of these methods make the assumption that lesions only affect white matter. Here, we propose a method to fill lesion regions using the patch-based non-local mean (NLM) strategy. The method consists of a hierarchical concentric filling strategy after identification of the lesion region. The lesion is filled iteratively, based on the surrounding tissue intensity, using an onion peel strategy. This concentric technique presents the advantage of preserving the local information and therefore the continuity of the anatomy and does not require identification of any a priori normal brain tissues. The method is first evaluated on simulated artificial MS lesions and, second, we performed a power analysis to evaluate brain atrophy and ventricular growth in patients with MS. The method was compared to two different publicly available methods (FSL lesion fill and Lesion LEAP) and more classic method approaches. The proposed method was shown to exceed the other methods in reproducing the fidelity of the images where the lesions were inpainted. The method also improved the power to detect brain atrophy or ventricular growth by decreasing the sample size by 25% in the presence of MS lesions.http://journal.frontiersin.org/Journal/10.3389/fnins.2015.00456/fullMRIlesionsMSsegmentationInpaintingnon-local |
| spellingShingle | Nicolas eGuizard Kunio eNakamura Kunio eNakamura Pierrick eCoupé Vladimir S. Fonov Douglas L Arnold D Louis Collins Non-local means inpainting of MS lesions in longitudinal image processing Frontiers in Neuroscience MRI lesions MS segmentation Inpainting non-local |
| title | Non-local means inpainting of MS lesions in longitudinal image processing |
| title_full | Non-local means inpainting of MS lesions in longitudinal image processing |
| title_fullStr | Non-local means inpainting of MS lesions in longitudinal image processing |
| title_full_unstemmed | Non-local means inpainting of MS lesions in longitudinal image processing |
| title_short | Non-local means inpainting of MS lesions in longitudinal image processing |
| title_sort | non local means inpainting of ms lesions in longitudinal image processing |
| topic | MRI lesions MS segmentation Inpainting non-local |
| url | http://journal.frontiersin.org/Journal/10.3389/fnins.2015.00456/full |
| work_keys_str_mv | AT nicolaseguizard nonlocalmeansinpaintingofmslesionsinlongitudinalimageprocessing AT kunioenakamura nonlocalmeansinpaintingofmslesionsinlongitudinalimageprocessing AT kunioenakamura nonlocalmeansinpaintingofmslesionsinlongitudinalimageprocessing AT pierrickecoupe nonlocalmeansinpaintingofmslesionsinlongitudinalimageprocessing AT vladimirsfonov nonlocalmeansinpaintingofmslesionsinlongitudinalimageprocessing AT douglaslarnold nonlocalmeansinpaintingofmslesionsinlongitudinalimageprocessing AT dlouiscollins nonlocalmeansinpaintingofmslesionsinlongitudinalimageprocessing |