Magnetic resonance imaging–based synthetic computed tomography of the lumbar spine for surgical planning: a clinical proof-of-concept

Abstract

OBJECTIVEComputed tomography scanning of the lumbar spine incurs a radiation dose ranging from 3.5 mSv to 19.5 mSv as well as relevant costs and is commonly necessary for spinal neuronavigation. Mitigation of the need for treatment-planning CT scans in the presence of MRI facilitated by MRI-based synthetic CT (sCT) would revolutionize navigated lumbar spine surgery. The authors aim to demonstrate, as a proof of concept, the capability of deep learning–based generation of sCT scans from MRI of the lumbar spine in 3 cases and to evaluate the potential of sCT for surgical planning.METHODSSynthetic CT reconstructions were made using a prototype version of the “BoneMRI” software. This deep learning–based image synthesis method relies on a convolutional neural network trained on paired MRI-CT data. A specific but generally available 4-minute 3D radiofrequency-spoiled T1-weighted multiple gradient echo MRI sequence was supplemented to a 1.5T lumbar spine MRI acquisition protocol.RESULTSIn the 3 presented cases, the prototype sCT method allowed voxel-wise radiodensity estimation from MRI, resulting in qualitatively adequate CT images of the lumbar spine based on visual inspection. Normal as well as pathological structures were reliably visualized. In the first case, in which a spiral CT scan was available as a control, a volume CT dose index (CTDIvol) of 12.9 mGy could thus have been avoided. Pedicle screw trajectories and screw thickness were estimable based on sCT findings.CONCLUSIONSThe evaluated prototype BoneMRI method enables generation of sCT scans from MRI images with only minor changes in the acquisition protocol, with a potential to reduce workflow complexity, radiation exposure, and costs. The quality of the generated CT scans was adequate based on visual inspection and could potentially be used for surgical planning, intraoperative neuronavigation, or for diagnostic purposes in an adjunctive manner.

Deep learning based synthetic‐CT generation in radiotherapy and PET: A review

“…Also, commercial solutions start to be evaluated for the generation of DL-based sCT from MRI for lesion detection of suspected sacroiliitis 223 or to facilitate surgical planning of the spine. 224 An exciting application is also the generation of sCT to facilitate multimodal image registration, as proposed by Mckenzie et al 225 All the techniques of category I could be directly applied to MR-guided high-intensity focused ultrasound, where otherwise an additional CT would be required to properly plan the treatment. 226 Additionally, the methods here reviewed to generate sCT can be applied to translating other image modalities.…”

Real-world study for identifying the predictive factors of surgical intervention and the value of magnetic resonance imaging in patients with low back pain

“…Grassner et al found that preoperative MRI could precisely identify the injured levels of the spine, which provided evidence to change the planned surgical approach, so as to undertake timely surgical intervention (28). Moreover, the generation of synthetic CT scans from MR imaging has been shown to help reduce workflow complexity, radiation exposure, and costs associated with adjunctive CT scanning in the lumbar spine (29). In our study, we found that LBP patients with more significant disk protrusion, spondylolisthesis, and spinal stenosis in the preoperative MRI were inclined to undergo lumbar interbody fusion, while patients with less severe disk protrusion or extrusion tended to receive percutaneous lumbar discectomy.…”

Artificial Intelligence and Computer Vision in Low Back Pain: A Systematic Review

“…Furthermore, some of the latter have been used in order to synthesize CT images from MRI and vice versa. For example, Staartjes et al [64] introduced a CNN-based system able to generate synthetic CT images from spine MRI, so as to acquire more precise information about osseous structures compared to traditional MRI without the need to expose patients to additional radiation. On the other hand, Lee and colleagues [65] presented a model based on GANs capable of producing a synthetic MRI from spine CT scans, which resulted in a mean overall similarity with real MRI scans of 80.2%.…”

“…With regards to the articles performing a Reconstruction task, Staartjes et al [64] developed a CNN to segment and reconstruct the lumbar structures from 3D MRI of 3 patients, evaluating the performance by visual evaluation. Lee et al [65] used GANs to generate synthetic spine lumbar structures MRI from 280 CT images, with a MAE of 21 pixels.…”