Retrospective motion artifact correction of structural MRI images using deep learning improves the quality of cortical surface reconstructions
Head motion during MRI acquisition presents significant challenges for neuroimaging analyses. In this work, we present a retrospective motion correction framework built on a Fourier domain motion simulation model combined with established 3D convolutional neural network (CNN) architectures. Quantita...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-04-01
|
| Series: | NeuroImage |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1053811921000331 |
| _version_ | 1818418911875432448 |
|---|---|
| author | Ben A Duffy Lu Zhao Farshid Sepehrband Joyce Min Danny JJ Wang Yonggang Shi Arthur W Toga Hosung Kim |
| author_facet | Ben A Duffy Lu Zhao Farshid Sepehrband Joyce Min Danny JJ Wang Yonggang Shi Arthur W Toga Hosung Kim |
| author_sort | Ben A Duffy |
| collection | DOAJ |
| description | Head motion during MRI acquisition presents significant challenges for neuroimaging analyses. In this work, we present a retrospective motion correction framework built on a Fourier domain motion simulation model combined with established 3D convolutional neural network (CNN) architectures. Quantitative evaluation metrics were used to validate the method on three separate multi-site datasets. The 3D CNN was trained using motion-free images that were corrupted using simulated artifacts. CNN based correction successfully diminished the severity of artifacts on real motion affected data on a separate test dataset as measured by significant improvements in image quality metrics compared to a minimal motion reference image. On the test set of 13 image pairs, the mean peak signal-to-noise-ratio was improved from 31.7 to 33.3 dB. Furthermore, improvements in cortical surface reconstruction quality were demonstrated using a blinded manual quality assessment on the Parkinson's Progression Markers Initiative (PPMI) dataset. Upon applying the correction algorithm, out of a total of 617 images, the number of quality control failures was reduced from 61 to 38. On this same dataset, we investigated whether motion correction resulted in a more statistically significant relationship between cortical thickness and Parkinson's disease. Before correction, significant cortical thinning was found to be restricted to limited regions within the temporal and frontal lobes. After correction, there was found to be more widespread and significant cortical thinning bilaterally across the temporal lobes and frontal cortex. Our results highlight the utility of image domain motion correction for use in studies with a high prevalence of motion artifacts, such as studies of movement disorders as well as infant and pediatric subjects. |
| first_indexed | 2024-12-14T12:30:12Z |
| format | Article |
| id | doaj.art-db9599bdbff2485485df6adb919ae50d |
| institution | Directory Open Access Journal |
| issn | 1095-9572 |
| language | English |
| last_indexed | 2024-12-14T12:30:12Z |
| publishDate | 2021-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj.art-db9599bdbff2485485df6adb919ae50d2022-12-21T23:01:13ZengElsevierNeuroImage1095-95722021-04-01230117756Retrospective motion artifact correction of structural MRI images using deep learning improves the quality of cortical surface reconstructionsBen A Duffy0Lu Zhao1Farshid Sepehrband2Joyce Min3Danny JJ Wang4Yonggang Shi5Arthur W Toga6Hosung Kim7Laboratory of Neuro Imaging (LONI), Stevens Institute for Neuroimaging and Informatics, Keck School of Medicine, University of Southern California, Los Angeles, CA, USALaboratory of Neuro Imaging (LONI), Stevens Institute for Neuroimaging and Informatics, Keck School of Medicine, University of Southern California, Los Angeles, CA, USALaboratory of Neuro Imaging (LONI), Stevens Institute for Neuroimaging and Informatics, Keck School of Medicine, University of Southern California, Los Angeles, CA, USALaboratory of Neuro Imaging (LONI), Stevens Institute for Neuroimaging and Informatics, Keck School of Medicine, University of Southern California, Los Angeles, CA, USALaboratory of Neuro Imaging (LONI), Stevens Institute for Neuroimaging and Informatics, Keck School of Medicine, University of Southern California, Los Angeles, CA, USALaboratory of Neuro Imaging (LONI), Stevens Institute for Neuroimaging and Informatics, Keck School of Medicine, University of Southern California, Los Angeles, CA, USALaboratory of Neuro Imaging (LONI), Stevens Institute for Neuroimaging and Informatics, Keck School of Medicine, University of Southern California, Los Angeles, CA, USACorresponding author.; Laboratory of Neuro Imaging (LONI), Stevens Institute for Neuroimaging and Informatics, Keck School of Medicine, University of Southern California, Los Angeles, CA, USAHead motion during MRI acquisition presents significant challenges for neuroimaging analyses. In this work, we present a retrospective motion correction framework built on a Fourier domain motion simulation model combined with established 3D convolutional neural network (CNN) architectures. Quantitative evaluation metrics were used to validate the method on three separate multi-site datasets. The 3D CNN was trained using motion-free images that were corrupted using simulated artifacts. CNN based correction successfully diminished the severity of artifacts on real motion affected data on a separate test dataset as measured by significant improvements in image quality metrics compared to a minimal motion reference image. On the test set of 13 image pairs, the mean peak signal-to-noise-ratio was improved from 31.7 to 33.3 dB. Furthermore, improvements in cortical surface reconstruction quality were demonstrated using a blinded manual quality assessment on the Parkinson's Progression Markers Initiative (PPMI) dataset. Upon applying the correction algorithm, out of a total of 617 images, the number of quality control failures was reduced from 61 to 38. On this same dataset, we investigated whether motion correction resulted in a more statistically significant relationship between cortical thickness and Parkinson's disease. Before correction, significant cortical thinning was found to be restricted to limited regions within the temporal and frontal lobes. After correction, there was found to be more widespread and significant cortical thinning bilaterally across the temporal lobes and frontal cortex. Our results highlight the utility of image domain motion correction for use in studies with a high prevalence of motion artifacts, such as studies of movement disorders as well as infant and pediatric subjects.http://www.sciencedirect.com/science/article/pii/S1053811921000331Motion artifactT1Image qualityCortical surfaceCortical thicknessParkinson's disease |
| spellingShingle | Ben A Duffy Lu Zhao Farshid Sepehrband Joyce Min Danny JJ Wang Yonggang Shi Arthur W Toga Hosung Kim Retrospective motion artifact correction of structural MRI images using deep learning improves the quality of cortical surface reconstructions NeuroImage Motion artifact T1 Image quality Cortical surface Cortical thickness Parkinson's disease |
| title | Retrospective motion artifact correction of structural MRI images using deep learning improves the quality of cortical surface reconstructions |
| title_full | Retrospective motion artifact correction of structural MRI images using deep learning improves the quality of cortical surface reconstructions |
| title_fullStr | Retrospective motion artifact correction of structural MRI images using deep learning improves the quality of cortical surface reconstructions |
| title_full_unstemmed | Retrospective motion artifact correction of structural MRI images using deep learning improves the quality of cortical surface reconstructions |
| title_short | Retrospective motion artifact correction of structural MRI images using deep learning improves the quality of cortical surface reconstructions |
| title_sort | retrospective motion artifact correction of structural mri images using deep learning improves the quality of cortical surface reconstructions |
| topic | Motion artifact T1 Image quality Cortical surface Cortical thickness Parkinson's disease |
| url | http://www.sciencedirect.com/science/article/pii/S1053811921000331 |
| work_keys_str_mv | AT benaduffy retrospectivemotionartifactcorrectionofstructuralmriimagesusingdeeplearningimprovesthequalityofcorticalsurfacereconstructions AT luzhao retrospectivemotionartifactcorrectionofstructuralmriimagesusingdeeplearningimprovesthequalityofcorticalsurfacereconstructions AT farshidsepehrband retrospectivemotionartifactcorrectionofstructuralmriimagesusingdeeplearningimprovesthequalityofcorticalsurfacereconstructions AT joycemin retrospectivemotionartifactcorrectionofstructuralmriimagesusingdeeplearningimprovesthequalityofcorticalsurfacereconstructions AT dannyjjwang retrospectivemotionartifactcorrectionofstructuralmriimagesusingdeeplearningimprovesthequalityofcorticalsurfacereconstructions AT yonggangshi retrospectivemotionartifactcorrectionofstructuralmriimagesusingdeeplearningimprovesthequalityofcorticalsurfacereconstructions AT arthurwtoga retrospectivemotionartifactcorrectionofstructuralmriimagesusingdeeplearningimprovesthequalityofcorticalsurfacereconstructions AT hosungkim retrospectivemotionartifactcorrectionofstructuralmriimagesusingdeeplearningimprovesthequalityofcorticalsurfacereconstructions |