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

Cheng-Bin Jin,Hakil Kim,Jung Hwan Lee,Xuenan Cui,In Ho Han,Mingjie Liu,Seongsu Joo,Jae Il Lee,Young Saem Ahn,Eunsik Park

doi:10.3390/app9122521

Cheng-Bin Jin, Hakil Kim + Show 8 more

Open Access

https://doi.org/10.3390/app9122521

Copy DOI

Abstract

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.

Highlights

Computed tomography (CT) scanning is a medical imaging technique that is widely used for diagnostic and therapeutic purposes in a variety of clinical applications
We propose a synthesis method based on convolutional neural networks (CNNs) [1] with adversarial training [3] to produce a lumbar spine magnetic resonance (MR) image from a CT scan
To stabilize the DC2 Anet training process, we used an image pooling technique [59] that updates the discriminator networks DisMR and DisCT using a history of synthetic images rather than the ones generated by the latest synthesis networks

Summary

Introduction

Computed tomography (CT) scanning is a medical imaging technique that is widely used for diagnostic and therapeutic purposes in a variety of clinical applications. Magnetic resonance imaging (MRI) is another imaging technique that visualizes anatomical details and is used in radiology and nuclear medicine. Lumbar disc herniation is common among the elderly and people who sit for long periods. The use of MRI to observe the spinal cord and the disc signals of the lumbar spine is of great importance in the treatment of this condition. The ability to generate a reliable magnetic resonance (MR) image from a CT scan for these patients is vital

Objectives

Results

Conclusion