Next Article in Journal
Effect of Additional Shielding Gas on Welding Seam Formation during Twin Wire DP-MIG High-Speed Welding
Next Article in Special Issue
No-reference Automatic Quality Assessment for Colorfulness-Adjusted, Contrast-Adjusted, and Sharpness-Adjusted Images Using High-Dynamic-Range-Derived Features
Previous Article in Journal
Broadband and Triple-Wavelength Continuous Wave Orange Laser by Single-Pass Sum-Frequency Generation in Step-Chirped MgO:PPLN
Previous Article in Special Issue
Double Low-Rank and Sparse Decomposition for Surface Defect Segmentation of Steel Sheet
Article

Fine-Grain Segmentation of the Intervertebral Discs from MR Spine Images Using Deep Convolutional Neural Networks: BSU-Net

1
School of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, Korea
2
Department of Radiology, VA San Diego Healthcare System, San Diego, CA 92161-0114, USA
3
Department of Radiology, University of California-San Diego, La Jolla, CA 92093-0997, USA
4
Department of Orthopedic Surgery, University of California-San Diego, La Jolla, CA 92037, USA
*
Author to whom correspondence should be addressed.
Appl. Sci. 2018, 8(9), 1656; https://doi.org/10.3390/app8091656
Received: 13 August 2018 / Revised: 6 September 2018 / Accepted: 12 September 2018 / Published: 14 September 2018
(This article belongs to the Special Issue Intelligent Imaging and Analysis)
We propose a new deep learning network capable of successfully segmenting intervertebral discs and their complex boundaries from magnetic resonance (MR) spine images. The existing U-network (U-net) is known to perform well in various segmentation tasks in medical images; however, its performance with respect to details of segmentation such as boundaries is limited by the structural limitations of a max-pooling layer that plays a key role in feature extraction process in the U-net. We designed a modified convolutional and pooling layer scheme and applied a cascaded learning method to overcome these structural limitations of the max-pooling layer of a conventional U-net. The proposed network achieved 3% higher Dice similarity coefficient (DSC) than conventional U-net for intervertebral disc segmentation (89.44% vs. 86.44%, respectively; p < 0.001). For intervertebral disc boundary segmentation, the proposed network achieved 10.46% higher DSC than conventional U-net (54.62% vs. 44.16%, respectively; p < 0.001). View Full-Text
Keywords: intervertebral disc; segmentation; convolutional neural network; fine grain segmentation; U-net; deep learning; magnetic resonance image; lumbar spine intervertebral disc; segmentation; convolutional neural network; fine grain segmentation; U-net; deep learning; magnetic resonance image; lumbar spine
Show Figures

Graphical abstract

MDPI and ACS Style

Kim, S.; Bae, W.C.; Masuda, K.; Chung, C.B.; Hwang, D. Fine-Grain Segmentation of the Intervertebral Discs from MR Spine Images Using Deep Convolutional Neural Networks: BSU-Net. Appl. Sci. 2018, 8, 1656. https://doi.org/10.3390/app8091656

AMA Style

Kim S, Bae WC, Masuda K, Chung CB, Hwang D. Fine-Grain Segmentation of the Intervertebral Discs from MR Spine Images Using Deep Convolutional Neural Networks: BSU-Net. Applied Sciences. 2018; 8(9):1656. https://doi.org/10.3390/app8091656

Chicago/Turabian Style

Kim, Sewon, Won C. Bae, Koichi Masuda, Christine B. Chung, and Dosik Hwang. 2018. "Fine-Grain Segmentation of the Intervertebral Discs from MR Spine Images Using Deep Convolutional Neural Networks: BSU-Net" Applied Sciences 8, no. 9: 1656. https://doi.org/10.3390/app8091656

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop