Localizing the L5 Vertebra Using Nerve Morphology on MRI: An Accurate and Reliable Technique

Identification of L5 vertebra on lumbar spine radiographs using deep learning

OBJECTIVE

Deep learning is an advanced machine-learning approach that is used in several medical fields. Here, we developed a deep learning model using an object detection algorithm to identify the L5 vertebra on anteroposterior lumbar spine radiographs, and assessed its detection accuracy.

METHODS

We retrospectively recruited 150 participants for whom both anteroposterior whole-spine and lumbar spine radiographs were available. The anteroposterior lumbar spine radiographs of these patients were used as the input data. Of the 150 images, 105 (70%) were randomly selected as the training set, and the remaining 45 (30%) were assigned to the validation set. YOLOv5x, of the YOLOv5 family model, was used to detect the L5 vertebra area.

RESULTS

The mean average precisions 0.5 and 0.75 of the trained L5 detection model were 99.2% and 96.9%, respectively. The model's precision was 95.7% and its recall was 97.8%. Furthermore, 93.3% of the validation data were correctly detected.

CONCLUSION

Our deep learning model showed an outstanding ability to identify L5 vertebrae.

The current state of radiodiagnostics of degenerative changes in the lumbar spine (literature review)

Examination of the spine using radiological methods remains the most frequently conducted study in the outpatient practice of almost any radiologist. In most cases, changes in the spine are degenerative and dystrophic in nature. These changes in the spine are the leading cause of loss of activity among adults and the elderly, and cover a wide range of age-related structural changes. It is of great importance to understand the possibilities and limitations of radiological methods of diagnostics. The description of morphological changes observed in degenerative and dystrophic changes requires the use of unified terminology and classifications among clinicians and radiologists.The aim. To present modern concepts in the assessment of degenerative changes of the spine using radiological methods. A description of the standardized international nomenclature of intervertebral disc pathology and current classifications of spinal canal stenosis are presented.Material and methods. For literature search, we used electronic databases MEDLINE (PubMed), eLibrary, EMBASE and Cochrane Library with a selection of sources published from 2000 to 2021. We analyzed the works devoted to the diagnosis of degenerative changes in lumbar spine and to degenerative stenosis.Conclusion. The key to productive communication between physicians is the uniformity or standardization of terminology and definitions used. It is important that the protocol of description, its terms, semantic expressions be uniform and understandable to specialists who are involved in the diagnosis and treatment of the spine. Magnetic resonance imaging is a valuable method in the diagnosis of degenerative changes of the spinal column, but it has its limitations.

The value of magnetic resonance imaging and computed tomography in the study of spinal disorders

Computed tomography (CT) and magnetic resonance imaging (MRI) have replaced conventional radiography in the study of many spinal conditions, it is essential to know when these techniques are indicated instead of or as complementary tests to radiography, which findings can be expected in different clinical settings, and their significance in the diagnosis of different spinal conditions. Proper use of CT and MRI in spinal disorders may facilitate diagnosis and management of spinal conditions. An adequate clinical approach, a good understanding of the pathological manifestations demonstrated by these imaging techniques and a comprehensive report based on a universally accepted nomenclature represent the indispensable tools to improve the diagnostic approach and the decision-making process in patients with spinal pain. Several guidelines are available to assist clinicians in ordering appropriate imaging techniques to achieve an accurate diagnosis and to ensure appropriate medical care that meets the efficacy and safety needs of patients. This article reviews the clinical indications of CT and MRI in different pathologic conditions affecting the spine, including congenital, traumatic, degenerative, inflammatory, infectious and tumor disorders, as well as their main imaging features. It is intended to be a pictorial guide to clinicians involved in the diagnosis and treatment of spinal disorders.

Lumbosacral Transitional Vertebra Contributed to Lumbar Spine Degeneration: An MR Study of Clinical Patients

We aimed to comprehensively characterize degenerative findings associated with various types of lumbosacral transitional vertebra (LSTV) on magnetic resonance images. Three hundred and fifty patients with LSTV (52.3 ± 10.9 years), including 182 Castellvi type I, 107 type II, 43 type III, and 18 type IV, and 179 controls without LSTV (50.6 ± 13.1 years), were studied. Discs, endplates, and posterior vertebral structures were assessed and compared to those of controls for the most caudal three discs on MRIs. There were no differences in degenerative findings between patients with type I LSTV and controls. For types III and IV, the transitional discs had smaller sizes, lower Pfirrmann scores, and lower rates of disc bulging (2.3% and 5.6% vs. 39.1%), osteophytes (2.3% vs. 15.1%), disc herniation (2.3% and 5.6% vs. 31.8%), and Modic changes (2.3% and 5.6% vs. 16.8%) than controls. However, the cranial discs had more severe Pfirrmann scores, disc narrowing and spinal canal narrowing, and greater rates of disc herniation (41.9% and 50.0% vs. 25.7%), endplate defects (27.9% and 33.3% vs. 14.4%) and spondylolisthesis (18.6% vs. 7.3%) than controls. Type II LSTV was associated with degenerative findings in the cranial segments but to a lesser degree, as compared with type III/IV LSTV. Thus, Castellvi type III/IV LSTV predisposed the adjacent spinal components to degeneration and protected the transitional discs. Type II LSTV had significant effects in promoting transitional and adjacent disc degeneration. Type I LSTV was not related to spinal degeneration.

Quantitative measurements at the lumbosacral junction are more reliable parameters for identifying and numbering lumbosacral transitional vertebrae

OBJECTIVES

To evaluate quantitative parameters to identify the anatomic variation lumbosacral transitional vertebrae (LSTV) and compare them with the landmarks commonly used at present.

METHODS

A total of 2,845 PET/CT scans were reviewed, and the patients with 23 and 25 presacral vertebrae were included. The quantitative parameters, including the anterior-edge vertebral angle (AVA) of the lowest lumbar-type vertebra, the ratio of the length of the inferior endplate to that of the superior endplate (RISE) of the uppermost sacral-type vertebra and the lumbosacral intervertebral disc angle (LSIVDA), and the anatomical landmarks, including the iliac crest tangent (ICT) level, the iliolumbar ligament (ILL) origin level and psoas proximal insertion, were all evaluated to determine their ability to identify LSTV.

RESULTS

The values of AVA and RISE were significantly different between the LSTV group and the control group, and between subgroups of LSTV. The cutoff value for AVA was 73.0°, with an accuracy, sensitivity, and specificity of 91.1%, 77.5%, and 88.3%, and that for RISE was 0.79, with an accuracy, sensitivity, and specificity of 90.3%, 77.5%, and 94.2%, while that for LSIVDA was 14.15°, with an accuracy, sensitivity, and specificity of 75.9%, 65.7%, and 78.3%, to differentiate L5 sacralization from S1 lumbarization. For differentiating the controls from LSTV, the accuracy, sensitivity, and specificity of the ICT level and proximal psoas insertion were 78.0%, 70.2%, and 95.0%, versus 71.7%, 61.7%, and 94.0%.

CONCLUSIONS

Compared with the anatomical landmarks, the quantitative measurements at the lumbosacral junction, including AVA and RISE, may be more helpful for differentiating subgroups of LSTV especially if only lumbar spine imaging is available.

KEY POINTS

• The quantitative parameters, the anterior-edge vertebral angle (AVA) of the lowest lumbar-type vertebra and the ratio of the length of the inferior endplate to that of the superior endplate (RISE) of the uppermost sacral-type vertebra, are more helpful for distinguishing L5 sacralization from S1 lumbarization than the previously proposed anatomic landmarks. • AVA and RISE represent relevant changes in the curvature at the lumbosacral region and the shape of the transitional vertebral body, respectively. • AVA and RISE are easily assessed, with high intra- and inter-reader reliability.

Fetal magnetic resonance imaging of lumbar spine development in vivo: a retrospective study

OBJECTIVE

The aim of this study is to describe MR imaging appearances of the fetal lumbar spine in vivo at different gestational ages (GAs).

METHODS

This retrospective study was approved by the Third Affiliated Hospital of Zhengzhou University. We collected MR images and clinical data of 93 fetuses in our hospital. All the MR images were obtained by 3-T MR. All had the mid-sagittal plane of steady state free precession sequence (Trufi) of the lumbar spine, which could show the lumbar vertebra and conus medullaris (CM). Regression analysis was made between GA and heights of lumbar vertebral body ossification center (LVBOC), lengths of LVBOC, and heights of intervertebral gap (IVG).

RESULTS

There were good linear correlations between the heights of LVBOC and GA (P < 0.001), lengths of LVBOC and GA (P < 0.001), and heights of IVG and GA (P < 0.001).

CONCLUSION

We showed the different development of each LVBOC and IVG which caused the difference of the shape of LVBOC and IVG.

Variations in the Number of Thoracic and Lumbar Vertebrae in Patients With Adolescent Idiopathic Scoliosis: A Retrospective, Observational Study

BACKGROUND

Abnormal anatomy is a contributory factor to wrong-level surgery. Variations in the number of vertebrae in populations from different races and geographical regions have been described. A ∼10% prevalence of variations in number of thoracic and lumbar vertebrae in adolescent idiopathic scoliosis (AIS) patients has been previously reported. The objectives of present study were (i) to find out the prevalence of variations in the number of thoracic and lumbar vertebrae and the presence of lumbosacral transitional vertebrae (LSTV) in Indian AIS patients and (ii) to correlate these variations with gender and type of curve.

METHODS

Hospital records and imaging of 198 AIS patients were reviewed retrospectively. A standardized numbering strategy was used to identify the number of thoracic vertebrae, number of lumbar vertebrae, and presence of LSTV. Patients' gender and curve type were correlated with the presence of an abnormal number of thoracic or lumbar vertebrae. Radiology reports and operation notes were reviewed to find out instances when the radiologist or surgeon had identified an abnormal number of vertebrae.

RESULTS

Forty patients (20.2%) with abnormally numbered thoracic or lumbar vertebrae were identified. Twenty patients (10.1%) had abnormally numbered thoracic vertebrae, and 33 patients (16.7%) had abnormally numbered lumbar vertebrae. The prevalence of LSTV was 18.2%. Presence of variations did not correlate with gender or curve type. Radiology reports identified 2/40 patients with variations, whereas operation notes showed 4/40 patients had been correctly identified to have abnormally numbered vertebrae.

CONCLUSIONS

There is high prevalence of variation in the number of thoracic or lumbar vertebrae in AIS patients, with most of those missed being identified by radiologists or surgeons. The patient's preoperative imaging must be scrutinized to identify these patients and take the variation into account to avoid wrong selection of fusion levels.

LEVEL OF EVIDENCE

3.

CLINICAL RELEVANCE

Text. The study raises awareness about possibility of wrong selection in fusion levels due to anatomical variations in surgery for AIS.

Spinal Enumeration by Morphologic Analysis of Spinal Variants: Comparison to Counting in a Cranial-To-Caudal Manner

Objective

To compare the spinal enumeration methods that establish the first lumbar vertebra in patients with spinal variants.

Materials and Methods

Of the 1446 consecutive patients who had undergone computed tomography of the spine from March 2012 to July 2016, 100 patients (62 men, 38 women; mean age, 47.9 years; age range, 19-88 years) with spinal variants were included. Two radiologists (readers 1 and 2) established the first lumbar vertebra through morphologic analysis of the thoracolumbar junction, and labeled the vertebra by counting in a cranial-to-caudal manner. Inter-observer agreement was established. Additionally, reader 1 detected the 20th vertebra under the assumption that there are 12 thoracic vertebra, and then classified it as a thoracic vertebra, lumbar vertebra, or thoracolumbar transitional vertebra (TLTV), on the basis of morphologic analysis.

Results

The first lumbar vertebra, as established by morphologic analysis, was labeled by each reader as the 21st segment in 65.0% of the patients, as the 20th segment in 31.0%, and as the 19th segment in 4.0%. Inter-observer agreement between the two readers in determining the first lumbar vertebra, based on morphologic analysis, was nearly perfect (κ value: 1.00). The 20th vertebra was morphologically classified as a TLTV in 60.0% of the patients, as the first lumbar segment in 31.0%, as the second lumbar segment in 4.0%, and as a thoracic segment in 5.0%.

Conclusion

The establishment of the first lumbar vertebra using morphologic characteristics of the thoracolumbar junction in patients with spinal variants was consistent with the morphologic traits of vertebral segmentation.