Validation of a Denoising Method Using Deep Learning-Based Reconstruction to Quantify Multiple Sclerosis Lesion Load on Fast FLAIR Imaging.
| dc.rights.license | open | en_US |
| hal.structure.identifier | IBIO - Plateforme de bio-imagerie en sciences médicales | |
| dc.contributor.author | YAMAMOTO, Takayuki | |
| dc.contributor.author | LACHERET, C | |
| hal.structure.identifier | IBIO - Plateforme de bio-imagerie en sciences médicales | |
| dc.contributor.author | FUKUTOMI, Hikaru | |
| hal.structure.identifier | Laboratoire Bordelais de Recherche en Informatique [LaBRI] | |
| dc.contributor.author | KAMRAOUI, Reda Abdellah | |
| hal.structure.identifier | IBIO - Plateforme de bio-imagerie en sciences médicales | |
| dc.contributor.author | DENAT, L | |
| dc.contributor.author | ZHANG, B | |
| dc.contributor.author | PREVOST, V | |
| dc.contributor.author | ZHANG, L | |
| hal.structure.identifier | Neurocentre Magendie : Physiopathologie de la Plasticité Neuronale [U1215 Inserm - UB] | |
| dc.contributor.author | RUET, Aurelie | |
| dc.contributor.author | TRIAIRE, B | |
| hal.structure.identifier | Neurocentre Magendie : Physiopathologie de la Plasticité Neuronale [U1215 Inserm - UB] | |
| dc.contributor.author | DOUSSET, Vincent | |
| hal.structure.identifier | Laboratoire Bordelais de Recherche en Informatique [LaBRI] | |
| dc.contributor.author | COUPE, Pierrick | |
| hal.structure.identifier | Neurocentre Magendie : Physiopathologie de la Plasticité Neuronale [U1215 Inserm - UB] | |
| dc.contributor.author | TOURDIAS, Thomas | |
| dc.date.accessioned | 2022-12-12T15:35:06Z | |
| dc.date.available | 2022-12-12T15:35:06Z | |
| dc.date.issued | 2022-07-28 | |
| dc.identifier.issn | 1936-959X | en_US |
| dc.identifier.other | http://dx.doi.org/10.3174/ajnr.A7589 | en_US |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/170578 | |
| dc.description.abstractEn | Accurate quantification of WM lesion load is essential for the care of patients with multiple sclerosis. We tested whether the combination of accelerated 3D-FLAIR and denoising using deep learning-based reconstruction could provide a relevant strategy while shortening the imaging examination. Twenty-eight patients with multiple sclerosis were prospectively examined using 4 implementations of 3D-FLAIR with decreasing scan times (4 minutes 54 seconds, 2 minutes 35 seconds, 1 minute 40 seconds, and 1 minute 15 seconds). Each FLAIR sequence was reconstructed without and with denoising using deep learning-based reconstruction, resulting in 8 FLAIR sequences per patient. Image quality was assessed with the Likert scale, apparent SNR, and contrast-to-noise ratio. Manual and automatic lesion segmentations, performed randomly and blindly, were quantitatively evaluated against ground truth using the absolute volume difference, true-positive rate, positive predictive value, Dice similarity coefficient, Hausdorff distance, and F1 score based on the lesion count. The Wilcoxon signed-rank test and 2-way ANOVA were performed. Both image-quality evaluation and the various metrics showed deterioration when the FLAIR scan time was accelerated. However, denoising using deep learning-based reconstruction significantly improved subjective image quality and quantitative performance metrics, particularly for manual segmentation. Overall, denoising using deep learning-based reconstruction helped to recover contours closer to those from the criterion standard and to capture individual lesions otherwise overlooked. The Dice similarity coefficient was equivalent between the 2-minutes-35-seconds-long FLAIR with denoising using deep learning-based reconstruction and the 4-minutes-54-seconds-long reference FLAIR sequence. Denoising using deep learning-based reconstruction helps to recognize multiple sclerosis lesions buried in the noise of accelerated FLAIR acquisitions, a possibly useful strategy to efficiently shorten the scan time in clinical practice. | |
| dc.description.sponsorship | Translational Research and Advanced Imaging Laboratory - ANR-10-LABX-0057 | en_US |
| dc.language.iso | EN | en_US |
| dc.title.en | Validation of a Denoising Method Using Deep Learning-Based Reconstruction to Quantify Multiple Sclerosis Lesion Load on Fast FLAIR Imaging. | |
| dc.title.alternative | AJNR Am J Neuroradiol | en_US |
| dc.type | Article de revue | en_US |
| dc.subject.hal | Sciences du Vivant [q-bio]/Neurosciences [q-bio.NC] | en_US |
| dc.identifier.pubmed | 35902124 | en_US |
| bordeaux.journal | American Journal of Neuroradiology | en_US |
| bordeaux.page | 1099-1106 | en_US |
| bordeaux.volume | 43 | en_US |
| bordeaux.hal.laboratories | Neurocentre Magendie - U1215 | en_US |
| bordeaux.issue | 8 | en_US |
| bordeaux.institution | Université de Bordeaux | en_US |
| bordeaux.institution | INSERM | en_US |
| bordeaux.institution | CHU de Bordeaux | en_US |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| bordeaux.team | Relations glie-neurone | en_US |
| bordeaux.peerReviewed | oui | en_US |
| bordeaux.inpress | non | en_US |
| bordeaux.identifier.funderID | Fondation pour l'Aide à la Recherche sur la Sclérose en Plaques | en_US |
| bordeaux.import.source | pubmed | |
| hal.identifier | hal-03895141 | |
| hal.version | 1 | |
| hal.date.transferred | 2022-12-12T15:35:23Z | |
| hal.export | true | |
| workflow.import.source | pubmed | |
| dc.rights.cc | Pas de Licence CC | en_US |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=American%20Journal%20of%20Neuroradiology&rft.date=2022-07-28&rft.volume=43&rft.issue=8&rft.spage=1099-1106&rft.epage=1099-1106&rft.eissn=1936-959X&rft.issn=1936-959X&rft.au=YAMAMOTO,%20Takayuki&LACHERET,%20C&FUKUTOMI,%20Hikaru&KAMRAOUI,%20Reda%20Abdellah&DENAT,%20L&rft.genre=article |
