Deep Learning-Based Automatic Segmentation of Lumbosacral Nerves on CT for Spinal Intervention: A Translational Study.

Autor:	Fan G; From the Orthopedic Department, Shanghai Tenth People's Hospital (G.F., C.F., D.W., S.H.), Tongji University School of Medicine, Shanghai, China tjhss7418@tongji.edu.cn gfan@tongji.edu.cn.; Department of Spine Surgery (G.F.), Third Affiliated Hospital of Sun Yatsen University, Guangzhou, China.; Surgical Planning Lab (G.F., J.L., W.M.W.), Radiology Department, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts., Liu H; Spinal Pain Research Institute of Tongji University (H.L., C.F., D.W., S.H.), Shanghai, China., Wu Z; School of Data and Computer Science (Z.W.), Sun Yat-sen University, Guangzhou, China., Li Y; Shanghai Jiao Tong University School of Medicine (Y.L.), Shanghai, China., Feng C; From the Orthopedic Department, Shanghai Tenth People's Hospital (G.F., C.F., D.W., S.H.), Tongji University School of Medicine, Shanghai, China.; Spinal Pain Research Institute of Tongji University (H.L., C.F., D.W., S.H.), Shanghai, China., Wang D; From the Orthopedic Department, Shanghai Tenth People's Hospital (G.F., C.F., D.W., S.H.), Tongji University School of Medicine, Shanghai, China.; Spinal Pain Research Institute of Tongji University (H.L., C.F., D.W., S.H.), Shanghai, China., Luo J; Surgical Planning Lab (G.F., J.L., W.M.W.), Radiology Department, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts.; Graduate School of Frontier Sciences (J.L.), University of Tokyo, Tokyo, Japan., Wells WM 3rd; Surgical Planning Lab (G.F., J.L., W.M.W.), Radiology Department, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts., He S; From the Orthopedic Department, Shanghai Tenth People's Hospital (G.F., C.F., D.W., S.H.), Tongji University School of Medicine, Shanghai, China tjhss7418@tongji.edu.cn gfan@tongji.edu.cn.; Spinal Pain Research Institute of Tongji University (H.L., C.F., D.W., S.H.), Shanghai, China.
Jazyk:	angličtina
Zdroj:	AJNR. American journal of neuroradiology [AJNR Am J Neuroradiol] 2019 Jun; Vol. 40 (6), pp. 1074-1081. Date of Electronic Publication: 2019 May 30.
DOI:	10.3174/ajnr.A6070
Abstrakt:	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. (© 2019 by American Journal of Neuroradiology.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu