Show simple item record

dc.contributor.authorMajdi, Mohammad S
dc.contributor.authorKeerthivasan, Mahesh B
dc.contributor.authorRutt, Brian K
dc.contributor.authorZahr, Natalie M
dc.contributor.authorRodriguez, Jeffrey J
dc.contributor.authorSaranathan, Manojkumar
dc.date.accessioned2020-11-02T21:04:25Z
dc.date.available2020-11-02T21:04:25Z
dc.date.issued2020-08-21
dc.identifier.citationMajdi, M. S., Keerthivasan, M. B., Rutt, B. K., Zahr, N. M., Rodriguez, J. J., & Saranathan, M. (2020). Automated thalamic nuclei segmentation using multi-planar cascaded convolutional neural networks. Magnetic Resonance Imaging, 73, 45-54.en_US
dc.identifier.issn0730-725X
dc.identifier.pmid32828985
dc.identifier.doi10.1016/j.mri.2020.08.005
dc.identifier.urihttp://hdl.handle.net/10150/648078
dc.description.abstractPurpose: To develop a fast and accurate convolutional neural network based method for segmentation of thalamic nuclei. Methods: A cascaded multi-planar scheme with a modified residual U-Net architecture was used to segment thalamic nuclei on conventional and white-matter-nulled (WMn) magnetization prepared rapid gradient echo (MPRAGE) data. A single network was optimized to work with images from healthy controls and patients with multiple sclerosis (MS) and essential tremor (ET), acquired at both 3 T and 7 T field strengths. WMn-MPRAGE images were manually delineated by a trained neuroradiologist using the Morel histological atlas as a guide to generate reference ground truth labels. Dice similarity coefficient and volume similarity index (VSI) were used to evaluate performance. Clinical utility was demonstrated by applying this method to study the effect of MS on thalamic nuclei atrophy. Results: Segmentation of each thalamus into twelve nuclei was achieved in under a minute. For 7 T WMn-MPRAGE, the proposed method outperforms current state-of-the-art on patients with ET with statistically significant improvements in Dice for five nuclei (increase in the range of 0.05-0.18) and VSI for four nuclei (increase in the range of 0.05-0.19), while performing comparably for healthy and MS subjects. Dice and VSI achieved using 7 T WMn-MPRAGE data are comparable to those using 3 T WMn-MPRAGE data. For conventional MPRAGE, the proposed method shows a statistically significant Dice improvement in the range of 0.14-0.63 over FreeSurfer for all nuclei and disease types. Effect of noise on network performance shows robustness to images with SNR as low as half the baseline SNR. Atrophy of four thalamic nuclei and whole thalamus was observed for MS patients compared to healthy control subjects, after controlling for the effect of parallel imaging, intracranial volume, gender, and age (p < 0.004). Conclusion: The proposed segmentation method is fast, accurate, performs well across disease types and field strengths, and shows great potential for improving our understanding of thalamic nuclei involvement in neurological diseases.en_US
dc.language.isoenen_US
dc.publisherELSEVIER SCIENCE INCen_US
dc.rightsCopyright © 2020 Elsevier Inc. All rights reserved.en_US
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en_US
dc.subjectClinical analysisen_US
dc.subjectConvolutional neural networken_US
dc.subjectThalamic nuclei segmentationen_US
dc.subjectWhite-matter-nulled MPRAGEen_US
dc.titleAutomated thalamic nuclei segmentation using multi-planar cascaded convolutional neural networksen_US
dc.typeArticleen_US
dc.identifier.eissn1873-5894
dc.contributor.departmentUniv Arizona, Dept Elect & Comp Engnen_US
dc.contributor.departmentUniv Arizona, Dept Med Imagingen_US
dc.identifier.journalMAGNETIC RESONANCE IMAGINGen_US
dc.description.note12 month embargo; available online 21 August 2020en_US
dc.description.collectioninformationThis item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at repository@u.library.arizona.edu.en_US
dc.eprint.versionFinal accepted manuscripten_US
dc.source.journaltitleMagnetic resonance imaging
dc.source.volume73
dc.source.beginpage45
dc.source.endpage54
dc.source.countryUnited States
dc.source.countryNetherlands


Files in this item

Thumbnail
Name:
UARep.pdf
Size:
1.550Mb
Format:
PDF
Description:
Final Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record