DeepGRAI (Deep Gray Rating via Artificial Intelligence): Fast, feasible, and clinically relevant thalamic atrophy measurement on clinical quality T2-FLAIR MRI in multiple sclerosis
Background: Thalamic volume loss is a key marker of neurodegeneration in multiple sclerosis (MS). T2-FLAIR MRI is a common denominator in clinical routine MS imaging, but current methods for thalamic volumetry are not applicable to it. Objective: To develop and validate a robust algorithm to measure...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-01-01
|
| Series: | NeuroImage: Clinical |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2213158221000966 |
| _version_ | 1828146828585992192 |
|---|---|
| author | Michael Dwyer Cassondra Lyman Hannah Ferrari Niels Bergsland Tom A. Fuchs Dejan Jakimovski Ferdinand Schweser Bianca Weinstock-Guttmann Ralph H.B. Benedict Jon Riolo Diego Silva Robert Zivadinov |
| author_facet | Michael Dwyer Cassondra Lyman Hannah Ferrari Niels Bergsland Tom A. Fuchs Dejan Jakimovski Ferdinand Schweser Bianca Weinstock-Guttmann Ralph H.B. Benedict Jon Riolo Diego Silva Robert Zivadinov |
| author_sort | Michael Dwyer |
| collection | DOAJ |
| description | Background: Thalamic volume loss is a key marker of neurodegeneration in multiple sclerosis (MS). T2-FLAIR MRI is a common denominator in clinical routine MS imaging, but current methods for thalamic volumetry are not applicable to it. Objective: To develop and validate a robust algorithm to measure thalamic volume using clinical routine T2-FLAIR MRI. Methods: A dual-stage deep learning approach based on 3D U-net (DeepGRAI – Deep Gray Rating via Artificial Intelligence) was created and trained/validated/tested on 4,590 MRI exams (4288 2D-FLAIR, 302 3D-FLAIR) from 59 centers (80/10/10 train/validation/test split). As training/test targets, FIRST was used to generate thalamic masks from 3D T1 images. Masks were reviewed, corrected, and aligned into T2-FLAIR space. Additional validation was performed to assess inter-scanner reliability (177 subjects at 1.5 T and 3 T within one week) and scan-rescan-reliability (5 subjects scanned, repositioned, and then re-scanned). A longitudinal dataset including assessment of disability and cognition was used to evaluate the predictive value of the approach. Results: DeepGRAI automatically quantified thalamic volume in approximately 7 s per case, and has been made publicly available. Accuracy on T2-FLAIR relative to 3D T1 FIRST was 99.4% (r = 0.94, p < 0.001,TPR = 93.0%, FPR = 0.3%). Inter-scanner error was 3.21%. Scan-rescan error with repositioning was 0.43%. DeepGRAI-derived thalamic volume was associated with disability (r = -0.427,p < 0.001) and cognition (r = -0.537,p < 0.001), and was a significant predictor of longitudinal cognitive decline (R2 = 0.081, p = 0.024; comparatively, FIRST-derived volume was R2 = 0.080, p = 0.025). Conclusions: DeepGRAI provides fast, reliable, and clinically relevant thalamic volume measurement on multicenter clinical-quality T2-FLAIR images. This indicates potential for real-world thalamic volumetry, as well as quantification on legacy datasets without 3D T1 imaging. |
| first_indexed | 2024-04-11T20:52:39Z |
| format | Article |
| id | doaj.art-3bfd81a320ea4849822ce78b7fe0dd7f |
| institution | Directory Open Access Journal |
| issn | 2213-1582 |
| language | English |
| last_indexed | 2024-04-11T20:52:39Z |
| publishDate | 2021-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage: Clinical |
| spelling | doaj.art-3bfd81a320ea4849822ce78b7fe0dd7f2022-12-22T04:03:48ZengElsevierNeuroImage: Clinical2213-15822021-01-0130102652DeepGRAI (Deep Gray Rating via Artificial Intelligence): Fast, feasible, and clinically relevant thalamic atrophy measurement on clinical quality T2-FLAIR MRI in multiple sclerosisMichael Dwyer0Cassondra Lyman1Hannah Ferrari2Niels Bergsland3Tom A. Fuchs4Dejan Jakimovski5Ferdinand Schweser6Bianca Weinstock-Guttmann7Ralph H.B. Benedict8Jon Riolo9Diego Silva10Robert Zivadinov11Buffalo Neuroimaging Analysis Center, Department of Neurology, School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USA; Jacobs MS Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USA; Corresponding author at: Buffalo Neuroimaging Analysis Center, Department of Neurology, School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USA.Buffalo Neuroimaging Analysis Center, Department of Neurology, School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USABuffalo Neuroimaging Analysis Center, Department of Neurology, School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USABuffalo Neuroimaging Analysis Center, Department of Neurology, School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USA; IRCCS, Fondazione Don Carlo Gnocchi, Milan, ItalyBuffalo Neuroimaging Analysis Center, Department of Neurology, School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USABuffalo Neuroimaging Analysis Center, Department of Neurology, School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USABuffalo Neuroimaging Analysis Center, Department of Neurology, School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USA; Jacobs MS Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USAJacobs MS Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USAJacobs MS Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USABristol Myers Squibb, Summit, NJ, USABristol Myers Squibb, Summit, NJ, USABuffalo Neuroimaging Analysis Center, Department of Neurology, School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USA; Jacobs MS Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, State University of New York, Buffalo, NY, USABackground: Thalamic volume loss is a key marker of neurodegeneration in multiple sclerosis (MS). T2-FLAIR MRI is a common denominator in clinical routine MS imaging, but current methods for thalamic volumetry are not applicable to it. Objective: To develop and validate a robust algorithm to measure thalamic volume using clinical routine T2-FLAIR MRI. Methods: A dual-stage deep learning approach based on 3D U-net (DeepGRAI – Deep Gray Rating via Artificial Intelligence) was created and trained/validated/tested on 4,590 MRI exams (4288 2D-FLAIR, 302 3D-FLAIR) from 59 centers (80/10/10 train/validation/test split). As training/test targets, FIRST was used to generate thalamic masks from 3D T1 images. Masks were reviewed, corrected, and aligned into T2-FLAIR space. Additional validation was performed to assess inter-scanner reliability (177 subjects at 1.5 T and 3 T within one week) and scan-rescan-reliability (5 subjects scanned, repositioned, and then re-scanned). A longitudinal dataset including assessment of disability and cognition was used to evaluate the predictive value of the approach. Results: DeepGRAI automatically quantified thalamic volume in approximately 7 s per case, and has been made publicly available. Accuracy on T2-FLAIR relative to 3D T1 FIRST was 99.4% (r = 0.94, p < 0.001,TPR = 93.0%, FPR = 0.3%). Inter-scanner error was 3.21%. Scan-rescan error with repositioning was 0.43%. DeepGRAI-derived thalamic volume was associated with disability (r = -0.427,p < 0.001) and cognition (r = -0.537,p < 0.001), and was a significant predictor of longitudinal cognitive decline (R2 = 0.081, p = 0.024; comparatively, FIRST-derived volume was R2 = 0.080, p = 0.025). Conclusions: DeepGRAI provides fast, reliable, and clinically relevant thalamic volume measurement on multicenter clinical-quality T2-FLAIR images. This indicates potential for real-world thalamic volumetry, as well as quantification on legacy datasets without 3D T1 imaging.http://www.sciencedirect.com/science/article/pii/S2213158221000966Thalamus volumeThalamic atrophyArtificial intelligenceMultiple sclerosis |
| spellingShingle | Michael Dwyer Cassondra Lyman Hannah Ferrari Niels Bergsland Tom A. Fuchs Dejan Jakimovski Ferdinand Schweser Bianca Weinstock-Guttmann Ralph H.B. Benedict Jon Riolo Diego Silva Robert Zivadinov DeepGRAI (Deep Gray Rating via Artificial Intelligence): Fast, feasible, and clinically relevant thalamic atrophy measurement on clinical quality T2-FLAIR MRI in multiple sclerosis NeuroImage: Clinical Thalamus volume Thalamic atrophy Artificial intelligence Multiple sclerosis |
| title | DeepGRAI (Deep Gray Rating via Artificial Intelligence): Fast, feasible, and clinically relevant thalamic atrophy measurement on clinical quality T2-FLAIR MRI in multiple sclerosis |
| title_full | DeepGRAI (Deep Gray Rating via Artificial Intelligence): Fast, feasible, and clinically relevant thalamic atrophy measurement on clinical quality T2-FLAIR MRI in multiple sclerosis |
| title_fullStr | DeepGRAI (Deep Gray Rating via Artificial Intelligence): Fast, feasible, and clinically relevant thalamic atrophy measurement on clinical quality T2-FLAIR MRI in multiple sclerosis |
| title_full_unstemmed | DeepGRAI (Deep Gray Rating via Artificial Intelligence): Fast, feasible, and clinically relevant thalamic atrophy measurement on clinical quality T2-FLAIR MRI in multiple sclerosis |
| title_short | DeepGRAI (Deep Gray Rating via Artificial Intelligence): Fast, feasible, and clinically relevant thalamic atrophy measurement on clinical quality T2-FLAIR MRI in multiple sclerosis |
| title_sort | deepgrai deep gray rating via artificial intelligence fast feasible and clinically relevant thalamic atrophy measurement on clinical quality t2 flair mri in multiple sclerosis |
| topic | Thalamus volume Thalamic atrophy Artificial intelligence Multiple sclerosis |
| url | http://www.sciencedirect.com/science/article/pii/S2213158221000966 |
| work_keys_str_mv | AT michaeldwyer deepgraideepgrayratingviaartificialintelligencefastfeasibleandclinicallyrelevantthalamicatrophymeasurementonclinicalqualityt2flairmriinmultiplesclerosis AT cassondralyman deepgraideepgrayratingviaartificialintelligencefastfeasibleandclinicallyrelevantthalamicatrophymeasurementonclinicalqualityt2flairmriinmultiplesclerosis AT hannahferrari deepgraideepgrayratingviaartificialintelligencefastfeasibleandclinicallyrelevantthalamicatrophymeasurementonclinicalqualityt2flairmriinmultiplesclerosis AT nielsbergsland deepgraideepgrayratingviaartificialintelligencefastfeasibleandclinicallyrelevantthalamicatrophymeasurementonclinicalqualityt2flairmriinmultiplesclerosis AT tomafuchs deepgraideepgrayratingviaartificialintelligencefastfeasibleandclinicallyrelevantthalamicatrophymeasurementonclinicalqualityt2flairmriinmultiplesclerosis AT dejanjakimovski deepgraideepgrayratingviaartificialintelligencefastfeasibleandclinicallyrelevantthalamicatrophymeasurementonclinicalqualityt2flairmriinmultiplesclerosis AT ferdinandschweser deepgraideepgrayratingviaartificialintelligencefastfeasibleandclinicallyrelevantthalamicatrophymeasurementonclinicalqualityt2flairmriinmultiplesclerosis AT biancaweinstockguttmann deepgraideepgrayratingviaartificialintelligencefastfeasibleandclinicallyrelevantthalamicatrophymeasurementonclinicalqualityt2flairmriinmultiplesclerosis AT ralphhbbenedict deepgraideepgrayratingviaartificialintelligencefastfeasibleandclinicallyrelevantthalamicatrophymeasurementonclinicalqualityt2flairmriinmultiplesclerosis AT jonriolo deepgraideepgrayratingviaartificialintelligencefastfeasibleandclinicallyrelevantthalamicatrophymeasurementonclinicalqualityt2flairmriinmultiplesclerosis AT diegosilva deepgraideepgrayratingviaartificialintelligencefastfeasibleandclinicallyrelevantthalamicatrophymeasurementonclinicalqualityt2flairmriinmultiplesclerosis AT robertzivadinov deepgraideepgrayratingviaartificialintelligencefastfeasibleandclinicallyrelevantthalamicatrophymeasurementonclinicalqualityt2flairmriinmultiplesclerosis |