Analysis of the paraspinal muscle morphology of the lumbar spine using a convolutional neural network (CNN)

A Convolutional Neural Network for Automated Detection of Cervical Ossification of the Posterior Longitudinal Ligament using Magnetic Resonance Imaging

STUDY DESIGN

Retrospective cohort study.

OBJECTIVE

We aimed to develop and validate a convolutional neural network (CNN) model to distinguish between cervical ossification of posterior longitudinal ligament (OPLL) and multilevel degenerative spinal stenosis using Magnetic Resonance Imaging (MRI) and to compare the diagnostic ability with spine surgeons.

SUMMARY OF BACKGROUND DATA

Some artificial intelligence models have been applied in spinal image analysis and many of promising results were obtained; however, there was still no study attempted to develop a deep learning model in detecting cervical OPLL using MRI images.

MATERIALS AND METHODS

In this retrospective study, 272 cervical OPLL and 412 degenerative patients underwent surgical treatment were enrolled and divided into the training (513 cases) and test dataset (171 cases). CNN models applying ResNet architecture with 34, 50, and 101 layers of residual blocks were constructed and trained with the sagittal MRI images from the training dataset. To evaluate the performance of CNN, the receiver operating characteristic curves of 3 ResNet models were plotted and the area under the curve were calculated on the test dataset. The accuracy, sensitivity, and specificity of the diagnosis by the CNN were calculated and compared with 3 senior spine surgeons.

RESULTS

The diagnostic accuracies of our ResNet34, ResNet50, and ResNet101 models were 92.98%, 95.32%, and 97.66%, respectively; the area under the curve of receiver operating characteristic curves of these models were 0.914, 0.942, and 0.971, respectively. The accuracies and specificities of ResNet50 and ResNet101 models were significantly higher than all spine surgeons; for the sensitivity, ResNet101 model achieved better values than that of the 2 surgeons.

CONCLUSION

The performance of our ResNet model in differentiating cervical OPLL from degenerative spinal stenosis using MRI is promising, better results were achieved with more layers of residual blocks applied.

Spinopelvic measurements of sagittal balance with deep learning: systematic review and critical evaluation

PURPOSE

To summarize and critically evaluate the existing studies for spinopelvic measurements of sagittal balance that are based on deep learning (DL).

METHODS

Three databases (PubMed, WoS and Scopus) were queried for records using keywords related to DL and measurement of sagittal balance. After screening the resulting 529 records that were augmented with specific web search, 34 studies published between 2017 and 2022 were included in the final review, and evaluated from the perspective of the observed sagittal spinopelvic parameters, properties of spine image datasets, applied DL methodology and resulting measurement performance.

RESULTS

Studies reported DL measurement of up to 18 different spinopelvic parameters, but the actual number depended on the image field of view. Image datasets were composed of lateral lumbar spine and whole spine X-rays, biplanar whole spine X-rays and lumbar spine magnetic resonance cross sections, and were increasing in size or enriched by augmentation techniques. Spinopelvic parameter measurement was approached either by landmark detection or structure segmentation, and U-Net was the most frequently applied DL architecture. The latest DL methods achieved excellent performance in terms of mean absolute error against reference manual measurements (~ 2° or ~ 1 mm).

CONCLUSION

Although the application of relatively complex DL architectures resulted in an improved measurement accuracy of sagittal spinopelvic parameters, future methods should focus on multi-institution and multi-observer analyses as well as uncertainty estimation and error handling implementations for integration into the clinical workflow. Further advances will enhance the predictive analytics of DL methods for spinopelvic parameter measurement.

LEVEL OF EVIDENCE I

Diagnostic: individual cross-sectional studies with the consistently applied reference standard and blinding.

Reliability and agreement of lumbar multifidus volume and fat fraction quantification using magnetic resonance imaging

INTRODUCTION

Magnetic resonance imaging (MRI) is the standard to quantify size and structure of lumbar muscles. Three-dimensional volumetric measures are expected to be more closely related to muscle function than two-dimensional measures such as cross-sectional area. Reliability and agreement of a standardized method should be established to enable the use of MRI to assess lumbar muscle characteristics.

OBJECTIVES

This study investigates the intra- and inter-processor reliability for the quantification of (1) muscle volume and (2) fat fraction based on chemical shift MRI images using axial 3D-volume measurements of the lumbar multifidus in patients with low back pain.

METHODS

Two processors manually segmented the lumbar multifidus on the MRI scans of 18 patients with low back pain using Mevislab software following a well-defined method. Fat fraction of the segmented volume was calculated. Reliability and agreement were determined using intra-class correlation coefficients (ICC), Bland-Altman plots and calculation of the standard error of measurement (SEM) and minimal detectable change (MDC).

RESULTS

Excellent ICCs were found for both intra-processor and inter-processor analysis of lumbar multifidus volume measurement, with slightly better results for the intra-processor reliability. The SEMs for volume were lower than 4.1 cm³. Excellent reliability and agreement were also found for fat fraction measures, with ICCs of 0.985-0.998 and SEMs below 0.946%.

CONCLUSION

The proposed method to quantify muscle volume and fat fraction of the lumbar multifidus on MRI was highly reliable, and can be used in further research on lumbar multifidus structure.