Diffusion tensor tractography in children with sensory processing disorder: Potentials for devising machine learning classifiers
The “sensory processing disorder” (SPD) refers to brain's inability to organize sensory input for appropriate use. In this study, we determined the diffusion tensor imaging (DTI) microstructural and connectivity correlates of SPD, and apply machine learning algorithms for identification of chil...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2019-01-01
|
| Series: | NeuroImage: Clinical |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2213158219301810 |
| _version_ | 1818839315996737536 |
|---|---|
| author | Seyedmehdi Payabvash Eva M. Palacios Julia P. Owen Maxwell B. Wang Teresa Tavassoli Molly Gerdes Anne Brandes-Aitken Elysa J. Marco Pratik Mukherjee |
| author_facet | Seyedmehdi Payabvash Eva M. Palacios Julia P. Owen Maxwell B. Wang Teresa Tavassoli Molly Gerdes Anne Brandes-Aitken Elysa J. Marco Pratik Mukherjee |
| author_sort | Seyedmehdi Payabvash |
| collection | DOAJ |
| description | The “sensory processing disorder” (SPD) refers to brain's inability to organize sensory input for appropriate use. In this study, we determined the diffusion tensor imaging (DTI) microstructural and connectivity correlates of SPD, and apply machine learning algorithms for identification of children with SPD based on DTI/tractography metrics. A total of 44 children with SPD and 41 typically developing children (TDC) were prospectively recruited and scanned. In addition to fractional anisotropy (FA), mean diffusivity (MD), and radial diffusivity (RD), we applied probabilistic tractography to generate edge density (ED) and track density (TD) from DTI maps. For identification of children with SPD, accurate classification rates from a combination of DTI microstructural (FA, MD, AD, and RD), connectivity (TD) and connectomic (ED) metrics with different machine learning algorithms – including naïve Bayes, random forest, support vector machine, and neural networks – were determined. In voxel-wise analysis, children with SPD had lower FA, ED, and TD but higher MD and RD compared to TDC – predominantly in posterior white matter tracts including posterior corona radiata, posterior thalamic radiation, and posterior body and splenium of corpus callosum. In stepwise penalized logistic regression, the only independent variable distinguishing children with SPD from TDC was the average TD in the splenium (p < 0.001). Among different combinations of machine learning algorithms and DTI/connectivity metrics, random forest models using tract-based TD yielded the highest accuracy in classification of SPD – 77.5% accuracy, 73.8% sensitivity, and 81.6% specificity. Our findings demonstrate impaired microstructural and connectivity/connectomic integrity in children with SPD, predominantly in posterior white matter tracts, and with reduced TD of the splenium of corpus callosum as the most distinctive pattern. Applying machine learning algorithms, these connectivity metrics can be used to devise novel imaging biomarkers for neurodevelopmental disorders. Keywords: Probabilistic tractography, Edge density imaging, Diffusion tensor imaging, Machine learning, Neurodevelopmental disorders, Sensory processing disorders |
| first_indexed | 2024-12-19T03:52:21Z |
| format | Article |
| id | doaj.art-0ee9fc81e8684b61a0d73364cca82cd4 |
| institution | Directory Open Access Journal |
| issn | 2213-1582 |
| language | English |
| last_indexed | 2024-12-19T03:52:21Z |
| publishDate | 2019-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage: Clinical |
| spelling | doaj.art-0ee9fc81e8684b61a0d73364cca82cd42022-12-21T20:36:55ZengElsevierNeuroImage: Clinical2213-15822019-01-0123Diffusion tensor tractography in children with sensory processing disorder: Potentials for devising machine learning classifiersSeyedmehdi Payabvash0Eva M. Palacios1Julia P. Owen2Maxwell B. Wang3Teresa Tavassoli4Molly Gerdes5Anne Brandes-Aitken6Elysa J. Marco7Pratik Mukherjee8Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, United States of America; Department of Radiology and Biomedical Imaging, University of California, San Francisco, CA, United States of AmericaDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, United States of AmericaDepartment of Radiology, University of Washington, Seattle, WA, United States of AmericaDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, United States of AmericaDepartment of Psychology and Clinical Sciences, University of Reading, Reading, United KingdomDepartment of Neurology, University of California, San Francisco, CA, United States of AmericaDepartment of Applied Psychology, New York University, New York, NY, United States of AmericaDepartment of Neurology, University of California, San Francisco, CA, United States of America; Department of Pediatric Neurology, Cortica Healthcare, San Rafael, CA, United States of AmericaDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, United States of America; Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, CA, United States of America; Corresponding author at: Center for Molecular and Functional Imaging, Department of Radiology and Biomedical Imaging, University of California, UCSF Box 0946, 185 Berry Street, Suite 350, San Francisco, CA 94107, USA.The “sensory processing disorder” (SPD) refers to brain's inability to organize sensory input for appropriate use. In this study, we determined the diffusion tensor imaging (DTI) microstructural and connectivity correlates of SPD, and apply machine learning algorithms for identification of children with SPD based on DTI/tractography metrics. A total of 44 children with SPD and 41 typically developing children (TDC) were prospectively recruited and scanned. In addition to fractional anisotropy (FA), mean diffusivity (MD), and radial diffusivity (RD), we applied probabilistic tractography to generate edge density (ED) and track density (TD) from DTI maps. For identification of children with SPD, accurate classification rates from a combination of DTI microstructural (FA, MD, AD, and RD), connectivity (TD) and connectomic (ED) metrics with different machine learning algorithms – including naïve Bayes, random forest, support vector machine, and neural networks – were determined. In voxel-wise analysis, children with SPD had lower FA, ED, and TD but higher MD and RD compared to TDC – predominantly in posterior white matter tracts including posterior corona radiata, posterior thalamic radiation, and posterior body and splenium of corpus callosum. In stepwise penalized logistic regression, the only independent variable distinguishing children with SPD from TDC was the average TD in the splenium (p < 0.001). Among different combinations of machine learning algorithms and DTI/connectivity metrics, random forest models using tract-based TD yielded the highest accuracy in classification of SPD – 77.5% accuracy, 73.8% sensitivity, and 81.6% specificity. Our findings demonstrate impaired microstructural and connectivity/connectomic integrity in children with SPD, predominantly in posterior white matter tracts, and with reduced TD of the splenium of corpus callosum as the most distinctive pattern. Applying machine learning algorithms, these connectivity metrics can be used to devise novel imaging biomarkers for neurodevelopmental disorders. Keywords: Probabilistic tractography, Edge density imaging, Diffusion tensor imaging, Machine learning, Neurodevelopmental disorders, Sensory processing disordershttp://www.sciencedirect.com/science/article/pii/S2213158219301810 |
| spellingShingle | Seyedmehdi Payabvash Eva M. Palacios Julia P. Owen Maxwell B. Wang Teresa Tavassoli Molly Gerdes Anne Brandes-Aitken Elysa J. Marco Pratik Mukherjee Diffusion tensor tractography in children with sensory processing disorder: Potentials for devising machine learning classifiers NeuroImage: Clinical |
| title | Diffusion tensor tractography in children with sensory processing disorder: Potentials for devising machine learning classifiers |
| title_full | Diffusion tensor tractography in children with sensory processing disorder: Potentials for devising machine learning classifiers |
| title_fullStr | Diffusion tensor tractography in children with sensory processing disorder: Potentials for devising machine learning classifiers |
| title_full_unstemmed | Diffusion tensor tractography in children with sensory processing disorder: Potentials for devising machine learning classifiers |
| title_short | Diffusion tensor tractography in children with sensory processing disorder: Potentials for devising machine learning classifiers |
| title_sort | diffusion tensor tractography in children with sensory processing disorder potentials for devising machine learning classifiers |
| url | http://www.sciencedirect.com/science/article/pii/S2213158219301810 |
| work_keys_str_mv | AT seyedmehdipayabvash diffusiontensortractographyinchildrenwithsensoryprocessingdisorderpotentialsfordevisingmachinelearningclassifiers AT evampalacios diffusiontensortractographyinchildrenwithsensoryprocessingdisorderpotentialsfordevisingmachinelearningclassifiers AT juliapowen diffusiontensortractographyinchildrenwithsensoryprocessingdisorderpotentialsfordevisingmachinelearningclassifiers AT maxwellbwang diffusiontensortractographyinchildrenwithsensoryprocessingdisorderpotentialsfordevisingmachinelearningclassifiers AT teresatavassoli diffusiontensortractographyinchildrenwithsensoryprocessingdisorderpotentialsfordevisingmachinelearningclassifiers AT mollygerdes diffusiontensortractographyinchildrenwithsensoryprocessingdisorderpotentialsfordevisingmachinelearningclassifiers AT annebrandesaitken diffusiontensortractographyinchildrenwithsensoryprocessingdisorderpotentialsfordevisingmachinelearningclassifiers AT elysajmarco diffusiontensortractographyinchildrenwithsensoryprocessingdisorderpotentialsfordevisingmachinelearningclassifiers AT pratikmukherjee diffusiontensortractographyinchildrenwithsensoryprocessingdisorderpotentialsfordevisingmachinelearningclassifiers |