Quantitative Analysis of Neural Foramina in the Lumbar Spine: An Imaging Informatics and Machine Learning Study

Artificial Intelligence in Spinal Imaging and Patient Care: A Review of Recent Advances

Artificial intelligence (AI) is transforming spinal imaging and patient care through automated analysis and enhanced decision-making. This review presents a clinical task-based evaluation, highlighting the specific impact of AI techniques on different aspects of spinal imaging and patient care. We first discuss how AI can potentially improve image quality through techniques like denoising or artifact reduction. We then explore how AI enables efficient quantification of anatomical measurements, spinal curvature parameters, vertebral segmentation, and disc grading. This facilitates objective, accurate interpretation and diagnosis. AI models now reliably detect key spinal pathologies, achieving expert-level performance in tasks like identifying fractures, stenosis, infections, and tumors. Beyond diagnosis, AI also assists surgical planning via synthetic computed tomography generation, augmented reality systems, and robotic guidance. Furthermore, AI image analysis combined with clinical data enables personalized predictions to guide treatment decisions, such as forecasting spine surgery outcomes. However, challenges still need to be addressed in implementing AI clinically, including model interpretability, generalizability, and data limitations. Multicenter collaboration using large, diverse datasets is critical to advance the field further. While adoption barriers persist, AI presents a transformative opportunity to revolutionize spinal imaging workflows, empowering clinicians to translate data into actionable insights for improved patient care.

Normative Measurements of L1-S1 Segmental Angulation, Disk Space Height, and Neuroforaminal Dimensions Using Computed Tomography

BACKGROUND AND OBJECTIVES

To establish normative anatomic measurements of lumbar segmental angulation (SA) and disk space height (DSH) in relation to neuroforaminal dimensions (NFDs), and to uncover the influence of patient demographic and anthropometric characteristics on SA, DSH, and NFDs.

METHODS

NFDs, SA, and anterior, middle, and posterior DSH were measured using computed tomography of 969 patients. NFDs were defined as sagittal anterior-to-posterior width, foraminal height, and area. Statistical analyses were performed to assess associations among SA, DSH, NFDs, and patient height, weight, body mass index, sex, and ethnicity.

RESULTS

SA and DSH measurements increased moving caudally from L1 to S1. Foraminal width decreased moving caudally from L1 to S1. Foraminal height and area demonstrated unimodal distribution patterns with the largest values clustered at L2-L3 on the right side and L3-L4 on the left. Significant differences in SA, DSH, and NFD measurements were observed based on the disk level. Inconsistent, marginal NFD differences were observed based on laterality. Across all disk levels, only weak-to-moderate correlations were observed between SA and DSH in relation to NFDs. Patient height, weight, and body mass index were only weakly associated with SA, DSH, and NFDs. Based on patient sex, significant differences were observed for SA, DSH, and NFD measurements from L1 to S1, with males demonstrating consistently larger values compared with females. Based on patient race and ethnicity, significant differences in SA and NFD measurements were observed from L1 to S1.

CONCLUSION

This study describes 48 450 normative measurements of L1-S1 SA, DSH, and NFDs. These measurements serve as representative models of normal anatomic dimensions necessary for several applications including surgical planning and diagnosis of foraminal stenosis. Normative values of SA and DSH are not moderately or strongly associated with NFDs. SA, DSH, and NFDs are influenced by sex and ethnicity, but are not strongly or moderately influenced by patient anthropometric factors.

Anatomic Assessment of L1-S1 Neuroforaminal Dimensions Using Computed Tomography in 1,000 Patients: A Follow-Up Study

OBJECTIVES

While the radiographic criteria for diagnosing central lumbar stenosis are well described, criteria for diagnosing neuroforaminal stenosis (NFS) are unclear. Prior research has utilized magnetic resonance imaging (MRI) to characterize neuroforaminal dimensions (NFDs). However, this approach has inherent limitations that can adversely impact measurement accuracy. Existing literature on the use of computed tomography (CT) to investigate normal NFDs is limited. The purpose of the present study was to describe normal lumbar NFDs that would aid in the establishment of objective quantitative criteria for the diagnosis of NFS.

METHODS

This study evaluated CT imaging of 494 female and 506 male subjects between 18 and 35 years of age to determine normal NFDs, specifically the sagittal anteroposterior width, craniocaudal height, and area. Statistical analyses were performed to assess differences in NFDs according to variables including sex, height, weight, body mass index, and ethnicity.

RESULTS

Without differentiating between sides or disc levels, mean NFDs were 8.71 mm for sagittal anteroposterior width, 17.73 mm for craniocaudal height, and 133.26 mm2 for area (n = 10,000 measurements each). Male subjects had larger NFDs than females at multiple levels. Asian and Caucasian subjects had larger NFDs than Hispanic and African American subjects at multiple levels. There were no associations between NFDs and anthropometric factors.

CONCLUSIONS

The present study describes normal lumbar NFDs in young, healthy patients. NFDs were influenced by sex and ethnicity but not by anthropometric factors.

Anatomic Assessment of L1-S1 Neuroforaminal Dimensions Using Computed Tomography

BACKGROUND

Although the radiographic parameters for diagnosing central lumbar canal stenosis are well described, parameters for the diagnosis of neuroforaminal stenosis (NFS) are less well defined. Previous studies have used magnetic resonance imaging (MRI) and radiography to describe neuroforaminal dimensions (NFDs). Those methods, however, have limitations that may substantially distort measurements. Existing literature on the use of computed tomography (CT) to investigate normal NFDs is limited.

METHODS

This anatomic assessment evaluated CT imaging of 300 female and 300 male subjects between 18 and 35 years of age to determine normal NFDs, specifically the sagittal anteroposterior width, axial anteroposterior width, craniocaudal height, and area. Statistical analyses were performed to assess differences in NFDs according to variables including sex, age, height, weight, body mass index, and ethnicity.

RESULTS

Overall, mean NFDs were 9.08 mm for sagittal anteroposterior width, 8.93 mm for axial anteroposterior width, 17.46 mm for craniocaudal height, and 134.78 mm 2 for area (n = 6,000 measurements each). Male subjects had larger NFDs than females at multiple levels. Both Caucasian and Asian subjects had larger NFDs than African-American subjects at multiple levels. There were no associations between foraminal dimensions and anthropometric factors.

CONCLUSIONS

This study describes CT-based L1-S1 NFDs in young, healthy patients who presented with reasons other than back pain or pathology affecting the neuroforamen. Dimensions were influenced by sex and ethnicity but were not influenced by anthropometric factors.

LEVEL OF EVIDENCE

Diagnostic Level III . See Instructions for Authors for a complete description of levels of evidence.

Lumbar Spinal Canal Segmentation in Cases with Lumbar Stenosis Using Deep-U-Net Ensembles

BACKGROUND

Narrowing of the lumbar spinal canal, or lumbar stenosis (LS), may cause debilitating radicular pain or muscle weakness. It is the most frequent indication for spinal surgery in the elderly population. Modern diagnosis relies on magnetic resonance imaging and its inherently subjective interpretation. Diagnostic rigor, accuracy, and speed may be improved by automation. In this work, we aimed to determine whether a deep-U-Net ensemble trained to segment spinal canals on a heterogeneous mix of clinical data is comparable to radiologists' segmentation of these canals in patients with LS.

METHODS

The deep U-nets were trained on spinal canals segmented by physicians on 100 axial T2 lumbar magnetic resonance imaging selected randomly from our institutional database. Test data included a total of 279 elderly patients with LS that were separate from the training set.

RESULTS

Machine-generated segmentations (MA) were qualitatively similar to expert-generated segmentations (ME1, ME2). Machine- and expert-generated segmentations were quantitatively similar, as evidenced by Dice scores (MA vs. ME1: 0.88 ± 0.04, MA vs. ME2: 0.89 ± 0.04), the Hausdorff distance (MA vs. ME1: 11.7 mm ± 13.8, MA vs. ME2: 13.1 mm ± 16.3), and average surface distance (MAvs. ME1: 0.18 mm ± 0.13, MA vs. ME2 0.18 mm ± 0.16) metrics. These metrics are comparable to inter-rater variation (ME1 vs. ME2 Dice scores: 0.94 ± 0.02, the Hausdorff distances: 9.3 mm ± 15.6, average surface distances: 0.08 mm ± 0.09).

CONCLUSION

We conclude that machine learning algorithms can segment lumbar spinal canals in LS patients, and automatic delineations are both qualitatively and quantitatively comparable to expert-generated segmentations.

Establishment of Age- and Sex-Specific Reference Cerebral Ventricle Volumes

BACKGROUND

The diagnosis of hydrocephalus is dependent on clinical symptoms and radiographic findings including ventriculomegaly. Our goal was to generate a data set of ventricular volume utilizing non-pathologic computed tomography (CT) scans for adults to help define reference ventricle size.

METHODS

We performed a retrospective analysis of non-contrast head CTs for adults at a single institution to identify patients who had undergone imaging and did not have a diagnosis of hydrocephalus, history of ventriculoperitoneal shunting, or treatments for hydrocephalus. A convolutional neural network was trained on hand-segmented scans from a variety of age ranges and then utilized to automate the segmentation of the entire data set.

RESULTS

Ventricles on 866 CT scans were segmented to generate a reference range of volumes for both male and female individuals ranging in age from 18-99 years. The generated data were binned by age ranges.

CONCLUSIONS

We have developed a convolutional neural network that can segment the ventricles on CT scans of adult patients over a range of ages. This network was used to measure the ventricular volume of non-pathologic head CTs to produce reference ranges for several age bins. This data set could be utilized to aid in the diagnosis of hydrocephalus by comparing potentially pathologic scans to reference ventricular volumes.

The role of Artificial intelligence in the assessment of the spine and spinal cord

Artificial intelligence (AI) application development is underway in all areas of radiology where many promising tools are focused on the spine and spinal cord. In the past decade, multiple spine AI algorithms have been created based on radiographs, computed tomography, and magnetic resonance imaging. These algorithms have wide-ranging purposes including automatic labeling of vertebral levels, automated description of disc degenerative changes, detection and classification of spine trauma, identification of osseous lesions, and the assessment of cord pathology. The overarching goals for these algorithms include improved patient throughput, reducing radiologist workload burden, and improving diagnostic accuracy. There are several pre-requisite tasks required in order to achieve these goals, such as automatic image segmentation, facilitating image acquisition and postprocessing. In this narrative review, we discuss some of the important imaging AI solutions that have been developed for the assessment of the spine and spinal cord. We focus on their practical applications and briefly discuss some key requirements for the successful integration of these tools into practice. The potential impact of AI in the imaging assessment of the spine and cord is vast and promises to provide broad reaching improvements for clinicians, radiologists, and patients alike.

Semi-automatic quantitative analysis of the pelvic bony structures on apparent diffusion coefficient maps based on deep learning: establishment of reference ranges

BACKGROUND

Apparent diffusion coefficient (ADC) maps provide quantitative information on both normal and abnormal tissues. However, it is difficult to distinguish between these tissues unless consistent and precise ADC values can be obtained from normal tissues. For this study we developed a deep learning-based convolutional neural network (CNN) for pelvic bony structure segmentation and established the reference ranges of ADC parameters for normal pelvic bony structures.

METHODS

We retrospectively enrolled 767 prostate cancer (PCa) patients for quantitative ADC analyses of normal pelvic bony structures. A subset of 288 patients who did not receive treatment for PCa (S1) were used to develop a CNN model for the segmentation of 8 pelvic bony structures (lumbar vertebra, sacrococcyx, ilium, acetabulum, femoral head, femoral neck, ischium, and pubis). The proposed CNN was used for the automated segmentation of these pelvic bony structures from a subset of 405 patients who did not receive treatment (S2) and 74 patients who received treatment [radiotherapy (S3) or endocrine therapy (S4)]. The 95% confidence interval (CI) was used to establish reference ranges for the ADC values from the normal pelvic bony structures of S1 and S2.

RESULTS

The Dice scores (Sørensen-Dice coefficient) for the CNN segmentation of the 8 pelvic bones on the ADC maps ranged from 0.90±0.02 (ilium) to 0.95±0.03 (femoral head) in the S1 testing set. In the S2 data set, the Dice scores showed no significant difference among the different scanners (P>0.05), and no significant differences were found among the S2, S3, and S4 data sets. The correlation analysis revealed that the b value and field strength were significantly correlated with ADC values (all P<0.001), while age and treatment were not significant variables (all P>0.05). The ADC reference ranges (95% CI) were as follows: lumbar vertebra, 1.11 (0.90-1.54); sacrococcyx, 0.82 (0.61-1.15); ilium, 0.57 (0.45-0.62); acetabulum, 0.59 (0.40-0.69); femoral head, 0.46 (0.25-0.58); femoral neck, 0.43 (0.25-0.48); ischium, 0.45 (0.26-0.55); and pubis, 0.57 (0.45-0.65).

CONCLUSIONS

This study preliminarily established reference ranges for the ADC values of normal pelvic bony structures. The image acquisition parameters had an influence on the ADC values.

Utility of machine learning algorithms in degenerative cervical and lumbar spine disease: a systematic review

Machine learning is a rapidly evolving field that offers physicians an innovative and comprehensive mechanism to examine various aspects of patient data. Cervical and lumbar degenerative spine disorders are commonly age-related disease processes that can utilize machine learning to improve patient outcomes with careful patient selection and intervention. The aim of this study is to examine the current applications of machine learning in cervical and lumbar degenerative spine disease. A systematic review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A search of PubMed, Embase, Medline, and Cochrane was conducted through May 31st, 2020, using the following terms: "artificial intelligence" OR "machine learning" AND "neurosurgery" AND "spine." Studies were included if original research on machine learning was utilized in patient care for degenerative spine disease, including radiographic machine learning applications. Studies focusing on robotic applications in neurosurgery, navigation, or stereotactic radiosurgery were excluded. The literature search identified 296 papers, with 35 articles meeting inclusion criteria. There were nine studies involving cervical degenerative spine disease and 26 studies on lumbar degenerative spine disease. The majority of studies for both cervical and lumbar spines utilized machine learning for the prediction of postoperative outcomes, with 5 (55.6%) and 15 (61.5%) studies, respectively. Machine learning applications focusing on degenerative lumbar spine greatly outnumber the current volume of cervical spine studies. The current research in lumbar spine also demonstrates more advanced clinical applications of radiographic, diagnostic, and predictive machine learning models.

Fully automated pelvic bone segmentation in multiparameteric MRI using a 3D convolutional neural network

BACKGROUND

Accurate segmentation of pelvic bones is an initial step to achieve accurate detection and localisation of pelvic bone metastases. This study presents a deep learning-based approach for automated segmentation of normal pelvic bony structures in multiparametric magnetic resonance imaging (mpMRI) using a 3D convolutional neural network (CNN).

METHODS

This retrospective study included 264 pelvic mpMRI data obtained between 2018 and 2019. The manual annotations of pelvic bony structures (which included lumbar vertebra, sacrococcyx, ilium, acetabulum, femoral head, femoral neck, ischium, and pubis) on diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) images were used to create reference standards. A 3D U-Net CNN was employed for automatic pelvic bone segmentation. Additionally, 60 mpMRI data from 2020 were included and used to evaluate the model externally.

RESULTS

The CNN achieved a high Dice similarity coefficient (DSC) average in both testing (0.80 [DWI images] and 0.85 [ADC images]) and external (0.79 [DWI images] and 0.84 [ADC images]) validation sets. Pelvic bone volumes measured with manual and CNN-predicted segmentations were highly correlated (R² value of 0.84-0.97) and in close agreement (mean bias of 2.6-4.5 cm³). A SCORE system was designed to qualitatively evaluate the model for which both testing and external validation sets achieved high scores in terms of both qualitative evaluation and concordance between two readers (ICC = 0.904; 95% confidence interval: 0.871-0.929).

CONCLUSIONS

A deep learning-based method can achieve automated pelvic bone segmentation on DWI and ADC images with suitable quantitative and qualitative performance.

Detection of Degenerative Changes on MR Images of the Lumbar Spine with a Convolutional Neural Network: A Feasibility Study

Our objective was to evaluate the diagnostic performance of a convolutional neural network (CNN) trained on multiple MR imaging features of the lumbar spine, to detect a variety of different degenerative changes of the lumbar spine. One hundred and forty-six consecutive patients underwent routine clinical MRI of the lumbar spine including T2-weighted imaging and were retrospectively analyzed using a CNN for detection and labeling of vertebrae, disc segments, as well as presence of disc herniation, disc bulging, spinal canal stenosis, nerve root compression, and spondylolisthesis. The assessment of a radiologist served as the diagnostic reference standard. We assessed the CNN’s diagnostic accuracy and consistency using confusion matrices and McNemar’s test. In our data, 77 disc herniations (thereof 46 further classified as extrusions), 133 disc bulgings, 35 spinal canal stenoses, 59 nerve root compressions, and 20 segments with spondylolisthesis were present in a total of 888 lumbar spine segments. The CNN yielded a perfect accuracy score for intervertebral disc detection and labeling (100%), and moderate to high diagnostic accuracy for the detection of disc herniations (87%; 95% CI: 0.84, 0.89), extrusions (86%; 95% CI: 0.84, 0.89), bulgings (76%; 95% CI: 0.73, 0.78), spinal canal stenoses (98%; 95% CI: 0.97, 0.99), nerve root compressions (91%; 95% CI: 0.89, 0.92), and spondylolisthesis (87.61%; 95% CI: 85.26, 89.21), respectively. Our data suggest that automatic diagnosis of multiple different degenerative changes of the lumbar spine is feasible using a single comprehensive CNN. The CNN provides high diagnostic accuracy for intervertebral disc labeling and detection of clinically relevant degenerative changes such as spinal canal stenosis and disc extrusion of the lumbar spine.

Artificial Intelligence and Deep Learning in Neuroradiology: Exploring the New Frontier

There have been many recently published studies exploring machine learning (ML) and deep learning applications within neuroradiology. The improvement in performance of these techniques has resulted in an ever-increasing number of commercially available tools for the neuroradiologist. In this narrative review, recent publications exploring ML in neuroradiology are assessed with a focus on several key clinical domains. In particular, major advances are reviewed in the context of: (1) intracranial hemorrhage detection, (2) stroke imaging, (3) intracranial aneurysm screening, (4) multiple sclerosis imaging, (5) neuro-oncology, (6) head and tumor imaging, and (7) spine imaging.

Quantitative Analysis of Spinal Canal Areas in the Lumbar Spine: An Imaging Informatics and Machine Learning Study

BACKGROUND AND PURPOSE

Quantitative imaging biomarkers have not been established for the diagnosis of spinal canal stenosis. This work aimed to lay the groundwork to establish such biomarkers by leveraging the developments in machine learning and medical imaging informatics.

MATERIALS AND METHODS

Machine learning algorithms were trained to segment lumbar spinal canal areas on axial views and intervertebral discs on sagittal views of lumbar MRIs. These were used to measure spinal canal areas at each lumbar level (L1 through L5). Machine-generated delineations were compared with 2 sets of human-generated delineations to validate the proposed techniques. Then, we use these machine learning methods to delineate and measure lumbar spinal canal areas in a normative cohort and to analyze their variation with respect to age, sex, and height using a variable-intercept mixed model.

RESULTS

We established that machine-generated delineations are comparable with human-generated segmentations. Spinal canal areas as measured by machine are statistically significantly correlated with height (P < .05) but not with age or sex.

CONCLUSIONS

Our machine learning methodology demonstrates that this important anatomic structure can be accurately detected and quantitatively measured without human input in a manner comparable with that of human raters. Anatomic deviations measured against the normative model established here could be used to flag spinal stenosis in the future.