Deep Learning–Based Automatic Segmentation of Lumbosacral Nerves on CT for Spinal Intervention: A Translational Study
G. Fan, H. Liu, Z. Wu, Y. Li, C. Feng, D. Wang, J. Luo, W.M. Wells and S. He
American Journal of Neuroradiology May 2019, DOI: https://doi.org/10.3174/ajnr.A6070
ArticleFigures & DataSupplementalInfo & MetricsReferences PDF
Abstract
BACKGROUND AND PURPOSE: 3D reconstruction of a targeted area (“safe” triangle and Kambin triangle) may benefit the viability assessment of transforaminal epidural steroid injection, especially at the L5/S1 level. However, manual segmentation of lumbosacral nerves for 3D reconstruction is time-consuming. The aim of this study was to investigate the feasibility of deep learning–based segmentation of lumbosacral nerves on CT and the reconstruction of the safe triangle and Kambin triangle.
MATERIALS AND METHODS: A total of 50 cases of spinal CT were manually labeled for lumbosacral nerves and bones using Slicer 4.8. The ratio of training/validation/testing was 32:8:10. A 3D U-Net was adopted to build the model SPINECT for automatic segmentations of lumbosacral structures. The Dice score, pixel accuracy, and Intersection over Union were computed to assess the segmentation performance of SPINECT. The areas of Kambin and safe triangles were measured to validate the 3D reconstruction.
RESULTS: The results revealed successful segmentation of lumbosacral bone and nerve on CT. The average pixel accuracy for bone was 0.940, and for nerve, 0.918. The average Intersection over Union for bone was 0.897 and for nerve, 0.827. The Dice score for bone was 0.945, and for nerve, it was 0.905. There were no significant differences in the quantified Kambin triangle or safe triangle between manually segmented images and automatically segmented images (P > .05).
CONCLUSIONS: Deep learning–based automatic segmentation of lumbosacral structures (nerves and bone) on routine CT is feasible, and SPINECT-based 3D reconstruction of safe and Kambin triangles is also validated.
ABBREVIATIONS:
ESI
epidural steroid injection
IoU
Intersection over Union
tESI
transforaminal epidural steroid injection
Footnotes
G. Fan and H. Liu contributed equally to the study.
Disclosures: William M. Wells—RELATED: Grant: National Institutes of Health, Comments: P41*; UNRELATED: Employment: Brigham and Women's Hospital, Massachusetts Institute of Technology; Grants/Grants Pending: National Institutes of Health, Comments: P41, R01s.* Shisheng He—RELATED: Grant: Shanghai Shenkang Hospital Development Center.* *Money paid to the institution.
This work is supported by the China Scholarship Council (201706260169), Shanghai Hospital Development Center (16CR3017A), and National Institutes of Health grant P41EB015898 (W.M.W.).
© 2019 by American Journal of Neuroradiology
Indicates open access to non-subscribers at www.ajnr.org
G. Fan, H. Liu, Z. Wu, Y. Li, C. Feng, D. Wang, J. Luo, W.M. Wells and S. He
American Journal of Neuroradiology May 2019, DOI: https://doi.org/10.3174/ajnr.A6070
ArticleFigures & DataSupplementalInfo & MetricsReferences PDF
Abstract
BACKGROUND AND PURPOSE: 3D reconstruction of a targeted area (“safe” triangle and Kambin triangle) may benefit the viability assessment of transforaminal epidural steroid injection, especially at the L5/S1 level. However, manual segmentation of lumbosacral nerves for 3D reconstruction is time-consuming. The aim of this study was to investigate the feasibility of deep learning–based segmentation of lumbosacral nerves on CT and the reconstruction of the safe triangle and Kambin triangle.
MATERIALS AND METHODS: A total of 50 cases of spinal CT were manually labeled for lumbosacral nerves and bones using Slicer 4.8. The ratio of training/validation/testing was 32:8:10. A 3D U-Net was adopted to build the model SPINECT for automatic segmentations of lumbosacral structures. The Dice score, pixel accuracy, and Intersection over Union were computed to assess the segmentation performance of SPINECT. The areas of Kambin and safe triangles were measured to validate the 3D reconstruction.
RESULTS: The results revealed successful segmentation of lumbosacral bone and nerve on CT. The average pixel accuracy for bone was 0.940, and for nerve, 0.918. The average Intersection over Union for bone was 0.897 and for nerve, 0.827. The Dice score for bone was 0.945, and for nerve, it was 0.905. There were no significant differences in the quantified Kambin triangle or safe triangle between manually segmented images and automatically segmented images (P > .05).
CONCLUSIONS: Deep learning–based automatic segmentation of lumbosacral structures (nerves and bone) on routine CT is feasible, and SPINECT-based 3D reconstruction of safe and Kambin triangles is also validated.
ABBREVIATIONS:
ESI
epidural steroid injection
IoU
Intersection over Union
tESI
transforaminal epidural steroid injection
Footnotes
G. Fan and H. Liu contributed equally to the study.
Disclosures: William M. Wells—RELATED: Grant: National Institutes of Health, Comments: P41*; UNRELATED: Employment: Brigham and Women's Hospital, Massachusetts Institute of Technology; Grants/Grants Pending: National Institutes of Health, Comments: P41, R01s.* Shisheng He—RELATED: Grant: Shanghai Shenkang Hospital Development Center.* *Money paid to the institution.
This work is supported by the China Scholarship Council (201706260169), Shanghai Hospital Development Center (16CR3017A), and National Institutes of Health grant P41EB015898 (W.M.W.).
© 2019 by American Journal of Neuroradiology
Indicates open access to non-subscribers at www.ajnr.org
Δεν υπάρχουν σχόλια:
Δημοσίευση σχολίου