Next Article in Journal
Advanced Fault Ride-Through Strategy by an MMC HVDC Transmission for Off-Shore Wind Farm Interconnection
Next Article in Special Issue
A Method to Detect Type 1 Diabetes Based on Physical Activity Measurements Using a Mobile Device
Previous Article in Journal
Dual-Channel Speech Enhancement Based on Extended Kalman Filter Relative Transfer Function Estimation
Previous Article in Special Issue
A Sample-Encoding Generalization of the Kohonen Associative Memory and Application to Knee Kinematic Data Representation and Pathology Classification
Article

DC2Anet: Generating Lumbar Spine MR Images from CT Scan Data Based on Semi-Supervised Learning

1
School of Information and Communication Engineering, INHA University, Incheon 22212, Korea
2
Department of Neurosurgery, Medical Research Institute, Pusan National University Hospital, Pusan 49241, Korea
3
Team Elysium Inc., Seoul 93525, Korea
4
Department of Computer Engineering, INHA University, Incheon 22212, Korea
*
Author to whom correspondence should be addressed.
Appl. Sci. 2019, 9(12), 2521; https://doi.org/10.3390/app9122521
Received: 14 May 2019 / Revised: 8 June 2019 / Accepted: 18 June 2019 / Published: 20 June 2019
(This article belongs to the Special Issue Machine Learning for Biomedical Data Analysis)
Magnetic resonance imaging (MRI) plays a significant role in the diagnosis of lumbar disc disease. However, the use of MRI is limited because of its high cost and significant operating and processing time. More importantly, MRI is contraindicated for some patients with claustrophobia or cardiac pacemakers due to the possibility of injury. In contrast, computed tomography (CT) scans are much less expensive, are faster, and do not face the same limitations. In this paper, we propose a method for estimating lumbar spine MR images based on CT images using a novel objective function and a dual cycle-consistent adversarial network (DC 2 Anet) with semi-supervised learning. The objective function includes six independent loss terms to balance quantitative and qualitative losses, enabling the generation of a realistic and accurate synthetic MR image. DC 2 Anet is also capable of semi-supervised learning, and the network is general enough for supervised or unsupervised setups. Experimental results prove that the method is accurate, being able to construct MR images that closely approximate reference MR images, while also outperforming four other state-of-the-art methods. View Full-Text
Keywords: image cross-modality synthesis; lumbar spine; dual cycle-consistent adversarial network; semi-supervised learning; adversarial training image cross-modality synthesis; lumbar spine; dual cycle-consistent adversarial network; semi-supervised learning; adversarial training
Show Figures

Figure 1

MDPI and ACS Style

Jin, C.-B.; Kim, H.; Liu, M.; Han, I.H.; Lee, J.I.; Lee, J.H.; Joo, S.; Park, E.; Ahn, Y.S.; Cui, X. DC2Anet: Generating Lumbar Spine MR Images from CT Scan Data Based on Semi-Supervised Learning. Appl. Sci. 2019, 9, 2521. https://doi.org/10.3390/app9122521

AMA Style

Jin C-B, Kim H, Liu M, Han IH, Lee JI, Lee JH, Joo S, Park E, Ahn YS, Cui X. DC2Anet: Generating Lumbar Spine MR Images from CT Scan Data Based on Semi-Supervised Learning. Applied Sciences. 2019; 9(12):2521. https://doi.org/10.3390/app9122521

Chicago/Turabian Style

Jin, Cheng-Bin, Hakil Kim, Mingjie Liu, In H. Han, Jae I. Lee, Jung H. Lee, Seongsu Joo, Eunsik Park, Young S. Ahn, and Xuenan Cui. 2019. "DC2Anet: Generating Lumbar Spine MR Images from CT Scan Data Based on Semi-Supervised Learning" Applied Sciences 9, no. 12: 2521. https://doi.org/10.3390/app9122521

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