Intervertebral Foramen Research Articles

Development of a deep learning model for automatic detection of narrowed intervertebral disc space sites in caudal thoracic and lumbar lateral X-ray images of dogs

Intervertebral disc disease is the most common spinal cord-related disease in dogs, caused by disc material protrusion or extrusion that compresses the spinal cord, leading to clinical symptoms. Diagnosis involves identifying radiographic signs such as intervertebral disc space narrowing, increased opacity of the intervertebral foramen, spondylosis deformans, and magnetic resonance imaging findings like spinal cord compression and lesions, alongside clinical symptoms and neurological examination findings. Intervertebral disc space narrowing on radiographs is the most common finding in intervertebral disc extrusion. This study aimed to develop a deep learning model to automatically recognize narrowed intervertebral disc space on caudal thoracic and lumbar X-ray images of dogs. In total, 241 caudal thoracic and lumbar lateral X-ray images from 142 dogs were used to develop and evaluate the model, which quantified intervertebral disc space distance and detected narrowing using a large-kernel one-dimensional convolutional neural network. When comparing veterinary clinicians and the deep learning model, the kappa value was 0.780, with 81.5% sensitivity and 95.6% specificity, showing substantial agreement. In conclusion, the deep learning model developed in this study, automatically and accurately quantified intervertebral disc space distance and detected narrowed sites in dogs, aiding in the initial screening of intervertebral disc disease and lesion localization.

Deep learning model for the automated detection and classification of central canal and neural foraminal stenosis upon cervical spine magnetic resonance imaging.

A deep learning (DL) model that can automatically detect and classify cervical canal and neural foraminal stenosis using cervical spine magnetic resonance imaging (MRI) can improve diagnostic accuracy and efficiency. A method comprising region-of-interest (ROI) detection and cascade prediction was formulated for diagnosing cervical spinal stenosis based on a DL model. First, three part-specific convolutional neural networks were employed to detect the ROIs in different parts of the cervical MR images. Cascade prediction of the stenosis categories was subsequently performed to record the stenosis level and position on each patient slice. Finally, the results were combined to obtain a patient-level diagnostic report. Performance was evaluated based on the accuracy (ACC), area under the curve (AUC), sensitivity, specificity, F1 Score, diagnosis time of the DL model, and recall rate for ROI detection localization. The average recall rate of the ROI localization was 89.3% (neural foramen) and 99.7% (central canal) under the five-fold cross-validation of the DL model. In the dichotomous classification (normal or mild vs. moderate or severe), the ACC and AUC of the DL model were comparable to those of the radiologists, and the F1 score (84.8%) of the DL model was slightly higher than that of the radiologists (83.8%) for the central canal. Diagnosing whether the central canal or neural foramen of a slice is narrowed in the cervical MRI scan required an average of 15 and 0.098s for the radiologists and DL model, respectively. The DL model demonstrated comparable performance with subspecialist radiologists for the detection and classification of central canal and neural foraminal stenosis on cervical spine MRI. Moreover, the DL model demonstrated significant timesaving ability.

New ultrasound-guided L5 selective nerve root block puncture approach for the treatment of pain due to high-iliac-crest lumbar disc herniation: A case report.

Lumbar 5 (L5) selective nerve root block is a common treatment for lumbar 4/5 disc herniation. It is difficult to perform real-time ultrasound-guided targeted L5 nerve root block because of the deep structure of the L5/S1 intervertebral foramen and the occlusion of the sacrum and ilium. Therefore, the safe and efficient implementation of L5 nerve root block is very important for improving the clinical promotion and use of this procedure. A 43-year-old male, who presented with a 1-month history of lumbosacral and left lower limb pain. The characteristic manifestation of pain symptoms was continuous and distending-like pain, accompanied by numbness on the posterior side of the left lower limb. The pain could be exacerbated by prolonged standing, sedentary behavior, and turning over while being relieved by lying down to rest. The visual analog score was 7 triggered by innocuous stimuli, configuring a clinical picture of typical protrusion of the lumbar intervertebral disc. Physical examination: muscle tenderness, straight leg-raising test of the left lower limb was 60° (+), test of supinating and throwing out one's belly (+), and Achilles tendon reflex (-). The patient underwent an ultrasound-guided L5 nerve root block with a modified puncture approach technique called the "transverse process-zygapophysis separation method." The patient had a successful nerve blockade characterized by significant reduction in pain after the operation. The innovative puncture approach method may be considered a therapeutic option in patients with chronic pain.

Surgical resection following chemoradiotherapy for thoracic SMARCA4-deficient undifferentiated tumor: a report of two cases

BackgroundThoracic SMARCA4-deficient undifferentiated tumor (SMARCA4-UT) is a high-grade malignant neoplasm with a poor prognosis. Most cases of SMARCA4-UT have extensive chest wall and mediastinum involvement. The efficacy of surgical resection has not been clearly established. Here, we report two surgical cases of SMARCA4-UT with chest wall invasion after chemoradiotherapy.Case presentationThe first patient was a 40-year-old man with back pain. Computed tomography revealed a 6.8 cm mass in contact with the thoracic vertebrae near the intervertebral foramen, which was suspected to involve the third to fifth ribs. The patient was diagnosed with SMARCA4-UT with clinical T3N0M0 stage IIB. The tumor shrank after chemoradiotherapy, and conversion surgery combined with partial vertebrectomy was performed. Histopathological findings revealed 30% residual tumor in the tumor bed. Thirty-six days after surgery, the patient developed multiple liver metastases and peritoneal dissemination. Chemotherapy combined with immune checkpoint inhibitor treatment was performed, resulting in tumor shrinkage. However, peritoneal dissemination recurred within a short interval. The patient died 5 months postoperatively. The second patient was a 74-year-old man with chest pain. Computed tomography revealed a 7.4-cm mass in the left upper lobe with invasion of the third and fourth ribs. The patient was initially diagnosed with non-small cell lung cancer with clinical T4N1M0 stage IIIA. The tumor shrank after induction chemoradiotherapy, and a left upper lobectomy combined with the chest wall resection was performed. Based on histopathological findings, the patient was diagnosed with SMARCA4-UT. The residual tumor percentage was 3%. The patient was followed up for 12 months postoperatively without recurrence.ConclusionsWe performed the complete resection of SMARCA4-UT following chemoradiotherapy. The two surgical cases had different postoperative courses. Radical surgery after chemoradiotherapy is effective for local control. However, its long-term prognostic efficacy remains unclear. Multidisciplinary approaches and further investigations of novel therapeutic options are required.

K wire migration into spinal canal: An infrequent cause of neurological morbidity: A case report

Introduction: K wire is one of the most common implants used for fixation of acromioclavicular joint dislocation. The migration of K wire from the AC joint to the spinal canal is a rare occurrence. In this report, we present a case of a young adult who presented with weakness of left upper limb secondary to migration of K wire from the AC joint to the spinal canal. Case presentation: A 46-year-old male farmer presented with complaints of pain in the neck, tingling sensation in the left upper limb, and a tender palpable swelling on the left side of his neck with weakness of finger flexors and abductors. He had had an open reduction and fixation with K wire for Acromioclavicular dislocation three months back. CT confirmed the K wire passing through neural foramen between C5 and C6 vertebra and extending across the entire diameter of spinal canal. Under intravenous anesthesia, a transverse skin incision was made over the prominent swelling on the neck and the wire was gently removed. Minimal seepage of spinal fluid was observed which stopped on its own after few days. Discussion: Although AC joint stabilization by K wire fixation provides a safe and easy fixation with low morbidity, complications such as a loss of fixation or loosening can occur. Migration of K wire into a spinal canal is a well-known but infrequent complication. Resorption of bone, muscle action, and negative intrathoracic pressures associated with respiration and heat necrosis causes progressive loosening and dislodgement. Spinal migration is very dangerous because it can cause serious damage to the dura mater, spinal cord, and vertebral artery. Conclusion: Early identification and removal of the K wire, once it has migrated from the site of use, is mandatory to prevent its grievous complications.

Rare posterior mediastinal hemangiomas invading the spinal cord through the intervertebral foramen and causing acute symptoms: illustrative case.

Hemangioma is a rare vascular tumor characterized by endothelial cell proliferation that primarily occurs in soft tissues. While most cases in the paraspinal posterior mediastinum are clinically indolent, they can also exhibit aggressive growth, leading to severe clinical outcomes and necessitating urgent treatment. A 61-year-old right-handed female presented with reduced lower-extremity mobility that had begun 4 days earlier. An examination revealed that both lower limbs had grade 4 muscle strength. Computed tomography and magnetic resonance imaging revealed a right T1-3 paravertebral dumbbell-shaped soft tissue mass invading the spinal canal, destroying the T2 vertebra, and compressing the spinal cord and nerve roots. Elective surgery was planned, but a rapid muscle strength decline prompted emergency surgery. Postoperative muscle strength improved to grade 4, and at the 3-month follow-up, muscle strength had fully recovered. Postoperative pathological examination revealed that the mediastinal dumbbell-shaped lesion was a hemangioma. While most hemangiomas progress slowly, acute symptoms of spinal cord compression are exceedingly rare. This case demonstrates the aggressive behavior of hemangioma, which invaded through the intervertebral foramen and compressed the spinal cord, resulting in acute symptoms. This case also shows that surgical removal of the tumor and restoration of spine stability via a posterior approach has proven beneficial. https://thejns.org/doi/10.3171/CASE24485.

Advances in diagnosis and imaging of cervical dysfunction in the sports horse

Cervical imaging provides an abundance of data. It is important not to lose sight of the horse and to determine what clinical relevance these findings have. Good clinical examination, in combination with knowledge of functional anatomy and biomechanics, are essential in anticipation of more research which will allow veterinarians to work in a more evidence-based manner. The location of cervical pain can be pinpointed to a single or multiple locations with an extensive history, static observation, general palpation, motion evaluation, specific palpation and dynamic evaluation. The whole body should be evaluated. The majority of cervical pathology (80%) is located in the caudal cervical area (C5–T1). Radiography of this region can be improved with good quality equipment, collimation, correct positioning of the horse and a correct distance between generator and plate. Radiography and ultrasonography may underestimate cervical pathology. Computed tomography is the preferred method of imaging but may lead to over interpretation. The most common finding is narrowing of the intervertebral foramen because of enlargement of the articular process joint(s). More than one location with abnormalities is often identified.

A rare cause of low back pain: lumbar lateral meningocele

Lumbar meningocele is the herniation of the arachnoid mater enlarged neural foramen to the thecal sac. A 55-year-old female patient applied with low back pain. Physical examination there were multiple cutaneous neurofibromas. The strength of lower extremity muscles was normal bilaterally. Babinski sign was negative bilaterally with normoactive deep tendon reflexes. Lumbal magnetic resonance imaging images show ectasia. The diagnosis was lateral meningocele associated with neurofibromatosis. Lumbar meningocele is a benign pathology that can be seen in a wide range from asymptomatic to paraparesis, which does not require surgical treatment, unless it is symptomatic, which is frequently associated with NF1. Key words: Lateral meningocele, Neurofibromatosis Type 1, Low back pain

Medication of the cervical spinal nerves for the treatment of equine cervical radiculopathy

SummaryBackgroundSeveral perineural injection techniques have been described to medicate the cervical spinal nerves of horses with suspected radiculopathy due to lesions at the intervertebral foramen (IVF). The technique and outcome have never been described in live, standing horses with suspected clinical disease.ObjectivesTo assess the safety and efficacy of medication of the ventral rami of the cervical spinal nerves (VRCSNs) for the treatment of cervical radiculopathy in horses.Study designCase series.MethodsHorses that underwent ultrasound‐guided perineural injection of the VRCSNs following radiographic and/or computed tomography (CT) evaluation of the cervical spine were included. Perineural injection with corticosteroids was performed using a standardised technique under ultrasound guidance as previously described. Outcome data were collected by clinical record review and unstructured follow‐up telephone conversations.ResultsForty‐seven injections of the VRCSNs were performed in 12 horses with only two self‐limiting adverse reactions noted. All horses that underwent CT examination had at least one site of IVF narrowing with the foramina at the C6/C7 articulation most frequently affected. Nine horses improved following medication of the VRCSNs with eight returning to their previous levels of exercise. All seven horses that underwent CT of the cervical spine had an initial improvement in clinical signs. Six horses were in full work and still performing at their intended level of exercise at a median of 21.5 months post injection.Main limitationsLack of definitive diagnosis of spinal nerve compression without histopathology of the spinal nerves which is not possible in the live horse.ConclusionsMedication of the VRCSNs is a safe treatment option which may provide benefit to horses with suspected spinal nerve compression but should be reserved for horses that have undergone a detailed clinical examination and CT evaluation of the cervical spine.

3D digital anatomical measurements for clinical application of minimally invasive lumbar foraminal surgery in adolescents aged 12–21 years

ObjectiveThe purpose of this study was to establish an anatomical foundation for minimally invasive lumbar spine surgery in adolescents by assessing the 3D anatomical parameters of the lumbar vertebrae in the age group of 12–21 years. MethodsWe collected CT data from 90 adolescents and performed 3D reconstructions using Mimics 16.0 software. The dimensions assessed included the height and sagittal diameter of the intervertebral foramen, as well as the length and widths of the transverse and spinous processes. ResultsThe intervertebral foramen height exhibited variation corresponding to the vertebral level, being smallest at L5/S1 and largest at L3/4. The sagittal diameter of the intervertebral foramen increased with age, reaching a minimum at L1/2 and a maximum at L4/5. Significant gender differences were observed in the 12–14 age group, with females exhibiting larger measurements than males. The length and width of the transverse processes were maximal at L3 and L5, respectively. The spinous process length was greatest at L3 and smallest at L5, with notable gender differences present in the 12–14 and 19–21 age groups. ConclusionThe study reveals that gender and age are significant factors influencing the anatomy of the adolescent lumbar spine, which is essential for the development of minimally invasive surgical techniques. Our findings contribute valuable insights for the design and surgical planning of spinal devices tailored to adolescents.

C-arm-guided versus ultrasound volumetric navigation-guided percutaneous transforaminal endoscopic discectomy for the treatment of lumbar disc herniation: A retrospective study.

To compare the clinical efficacy of lumbar percutaneous transforaminal endoscopic discectomy (PTED) for lumbar disc herniation (LDH) guided by C-arm fluoroscopy and ultrasound volumetric navigation (UVN). Fifty patients with LDH treated with PTED were retrospectively evaluated in this study. Groups A (n = 25) and B (n = 25) had intervertebral foramina punctures guided by C-arm fluoroscopy and UVN, respectively. The age, gender, height, weight, and body mass index of patients were recorded. We compared the puncture time, number of punctures, and puncture accuracy of patients in both groups. We also evaluated the clinical effectiveness of PTED surgery using the visual analog scale (VAS) and the Oswestry Disability Index (ODI). In addition, we recorded the duration of surgery, hospitalization, medical costs, and surgical complications in both groups. The average follow-up time of the 50 patients was 18.5 ± 4.3 months. The mean puncture time in groups A and B was 25.76 ± 5.28 and 14.34 ± 4.96 minutes, respectively, and the difference was statistically significant (P < .05). The mean number of fluoroscopies was significantly lower in group B than in group A, with 15.82 ± 2.29 versus 4.52 ± 0.51 times (P < .05). The puncture accuracy rate was 100% in both groups, with no statistical difference (P > .05). The VAS and ODI scores of patients in group A were similar to group B at all 3-time points: preoperatively, at 3 months postoperatively, and at 1 year postoperatively. However, both VAS and ODI were significantly improved postoperatively compared to preoperatively (P < .05). Moreover, group B has shorter operative time and higher medical cost than group A (P < .05). There was no significant difference in the length of hospitalization and surgical complication rate (P > .05). Both C-arm-guided and the UVN-guided PTED are safe and effective methods for the treatment of LDH. UVN-guided technique has the advantage of reducing puncture time and the number of punctures. However, UVN also has the disadvantage of high hospitalization costs.

Performance of Artificial Intelligence in Diagnosing Lumbar Spinal Stenosis: A Systematic Review and Meta-analysis.

The present study followed the reporting guidelines for systematic reviews and meta-analyses. Therefore, we conducted this study to review the diagnostic value of AI for various types of LSS and the level of stenosis, offering evidence-based support for the development of smart diagnostic tools. Artificial intelligence (AI) is currently being utilized for image processing in clinical practice. Some studies have explored AI techniques for identifying the severity of lumbar spinal stenosis (LSS) in recent years. Nevertheless, there remains a shortage of structured data proving its effectiveness. Four databases (PubMed, Cochrane, Embase, and Web of Science) were searched until March 2024, including original studies that utilized deep learning and machine learning models to diagnose LSS. The risk of bias (RoB) of included studies was assessed using QUADAS-2. The accuracy in the validation set was extracted for a meta-analysis. The meta-analysis was completed in R4.4.0. A total of 48 articles were included, with an overall accuracy of 0.885 (95% CI: 0.860-0907) for dichotomous tasks. Among them, the accuracy was 0.892 (95% CI: 0.867-0915) for deep learning (DL) and 0.833 (95% CI: 0.760-0895) for machine learning (ML). The overall accuracy for LSS was 0.895 (95% CI: 0.858-0927), with an accuracy of 0.912 (95% CI: 0.873-0.944) for DL and 0.843 (95% CI: 0.766-0.907) for ML. The overall accuracy for central canal stenosis was 0.875 (95% CI: 0.821-0920), with an accuracy of 0.881 (95% CI: 0.829-0.925) for DL and 0.733 (95% CI: 0.541-0.877) for ML. The overall accuracy for neural foramen stenosis was 0.893 (95% CI: 0.851-0.928). In polytomous tasks, the accuracy was 0.936 (95% CI: 0.895-0.967) for no LSS, 0.503 (95% CI: 0.391-0.614) for mild LSS, 0.512 (95% CI: 0.336-0.688) for moderate LSS, and 0.860 for severe LSS (95% CI: 0.733-0.954). AI is highly valuable for diagnosing LSS. However, further external validation is necessary to enhance the analysis of different stenosis categories and improve the diagnostic accuracy for mild to moderate stenosis levels.

Current research status and prospects for clinical application of robotics in spinal surgery

With the rapid advancement of artificial intelligence and the increasing integration of medical engineering, robot-assisted (RA) technology in spinal surgery has made significant strides, with its clinical application range continuously expanding. This article provides a comprehensive review of relevant literature on spinal surgery robots over the past decade, summarizing recent advancements in screw placement techniques such as cervical, thoracic, and lumbar pedicle screws; cortical bone trajectory (CBT) screws; cervical lateral mass screws; and S2 sacroiliac (S2AI) screws. It also discusses RA-guided targeted puncture and endoscope placement through intervertebral foramen as well as decompressive laminectomy procedures. Furthermore, this article systematically analyzes the advantages and disadvantages of RA technology while elucidating its accuracy, safety, and practicality. We believe that this article will help clinicians to gain a deeper understanding of the current clinical application status of spinal surgery robots while promoting further enhancements and wider adoption of RA technology to ultimately benefit more patients.

The Application of Deep Learning to Accurately Identify the Dimensions of Spinal Canal and Intervertebral Foramen as Evaluated by the IoU Index.

Artificial intelligence has garnered significant attention in recent years as a rapidly advancing field of computer technology. With the continual advancement of computer hardware, deep learning has made breakthrough developments within the realm of artificial intelligence. Over the past few years, applying deep learning architecture in medicine and industrial anomaly inspection has significantly contributed to solving numerous challenges related to efficiency and accuracy. For excellent results in radiological, pathological, endoscopic, ultrasonic, and biochemical examinations, this paper utilizes deep learning combined with image processing to identify spinal canal and vertebral foramen dimensions. In existing research, technologies such as corrosion and expansion in magnetic resonance image (MRI) processing have also strengthened the accuracy of results. Indicators such as area and Intersection over Union (IoU) are also provided for assessment. Among them, the mean Average Precision (mAP) for identifying intervertebral foramen (IVF) and intervertebral disc (IVD) through YOLOv4 is 95.6%. Resnet50 mixing U-Net was employed to identify the spinal canal and intervertebral foramen and achieved IoU scores of 79.11% and 80.89%.

Surgical Treatment of Spinal Intra-Extradural Meningioma: A Clinical Case

Spinal meningiomas are rare, predominantly benign tumors that exhibit slow growth and typically have a non-invasive pattern of development. They originate from arachnoid cells and fibroblasts of the dura mater. Despite their benign nature, some meningiomas can exhibit intra-extradural extension, complicating both diagnosis and treatment. This article presents a clinical case involving a patient with an intra-extradural spinal meningioma. Despite radiological imaging suggesting a neurinoma, the final diagnosis confirmed a meningioma. Case Report: A female patient underwent surgical tumor resection through a posterolateral approach with laminectomy and facetectomy at the C4-C5 vertebral levels. The tumor, extending through the intervertebral foramen, was completely resected along with the affected nerve root. Histological examination verified a Grade II meningioma. Discussion: Despite advancements in neuroimaging and surgical techniques, intraoperative findings can be unpredictable, necessitating an adaptive approach to tumor resection. The article emphasizes the importance of adequate preoperative planning and the use of intraoperative neurophysiological monitoring to reduce the risk of complications and improve treatment outcomes. Conclusions: The primary treatment for spinal meningiomas is surgical. For dorsal and lateral localizations, total resection with the involved dura mater (Simpson Grade I) is optimal. For ventral localizations, tumor resection with coagulation of the dural attachment site (Simpson Grade II) is preferred. Preoperative and intraoperative use of electrophysiological methods is recommended to assess the functional status of neural structures. Intra-extradural localization of meningiomas is rare and presents significant challenges in preoperative diagnosis, requiring specific skills for effective removal.

The Cervical Intervertebral Foramen: Microanatomy, Pathology, and Clinical Implications.

This is an evidence-based narrative review article. We hope to provide a primer on cervical intervertebral foramen (cIVF) anatomy for spine surgeons, interventionalists, and physiatrists who regularly treat cervical spine pathology, and encourage further exploration of this topic. This corridor for exiting cervical nerve roots is characterized by its intricate microanatomy involving ligamentous, nervous, and vascular structures. Degenerative changes such as facet hypertrophy and disc herniations alter these relationships, potentially leading to nerve root compression and cervical radiculopathy. This review synthesizes existing knowledge on the cIVF. Key imaging, cadaveric, and clinical studies serve as a foundation for this anatomic review. We explore topics such as dynamic changes that affect foraminal size and their implications for nerve root compression, the relationship of the dorsal root ganglion to the cervical foramen, and the function and clinical significance of foraminal ligaments, arteries, and veins. Changes in the cIVF are frequently the basis of cervical degenerative pathologies. A comprehensive understanding of its microanatomical structure will allow the practitioner to better treat the underlying disease process causing their symptoms and signs.

How to Set Working Cannula in Endoscopic-Assisted Transforaminal Lumbar Interbody Fusion: A Morphometric Analysis Based on Computed Tomography.

There is a high risk of nerve root injury during endoscopic-assisted transforaminal lumbar interbody fusion (Endo-TLIF). This study used computed tomography (CT) imaging to assess the relationship between the exiting nerve root and its surroundings, and the corresponding intervertebral disc. We also measured the approximate position and angle for the placement of the working cannula to reduce the risk of nerve root injury during Endo-TLIF procedures in the Chinese population. This retrospective study was conducted at our institution between December 2021 and December 2022. A total of 115 patients suffering from low back pain were recruited for the study. For each participant, three-dimensional (3D) vertebral models of the lumbar segments from L3 to S1 were constructed based on their CT images. The nerve root-disc distance, cannula insertion bypass distance and angle, foraminal height and width, exiting nerve root height, and nerve root-pedicle distance were measured. A paired t-test was used to compare measurements between the left and right sides, while inter- and intraobserver reproducibility was assessed using the intraclass correlation coefficient (ICC). From L3/4 to L5/S1 segments, the ideal cannula insertion distance range was 37.51 ± 4.91-120.38 ± 37.71 mm at L3/4; 42.38 ± 5.29-116.25 ± 27.22 mm at L4/5; and 37.78 ± 4.86-69.26 ± 12.64 mm at L5/S1. The appropriate cannula insertion angle range was 30.86° ± 5.05°-62.59° ± 6.66° at L3/4; 34.30° ± 4.73°-60.88° ± 7.34° at L4/5; and 35.89° ± 4.18°-47.65° ± 7.38° at L5/S1. The height of the intervertebral foramen (IVF) gradually decreased, and the width steadily increased. The exiting nerve root height and the nerve root-pedicle distance slightly decreased caudally. From L3/4 to L5/S1, the range of working cannula insertion distance and angle gradually decreased, and the exiting nerve root height occupying the IVF gradually increased. Our measurement can reduce the risk of nerve root injury caused by inserting the working cannula during Endo-TLIF.

Deep learning constrained compressed sensing reconstruction improves high-resolution three-dimensional (3D) T2-weighted turbo spin echo magnetic resonance imaging (MRI) of the lumbar spine

We sought to assess the image quality of three-dimensional (3D) T2-weighted (T2w) turbo spin echo (TSE) sequences with deep learning (DL)-constrained compressed sensing (CS) reconstruction relative to a reference two-dimensional (2D) T2w TSE sequence for routine clinical lumbar spine MRI. Fifty-three patients underwent imaging of the lumbar spine with a sagittal 2D T2w TSE sequence and with two CS-accelerated 3D T2w TSE sequences (voxel size of 0.4×0.4×0.5 mm) with CS factors of 7 and 11. The CS-accelerated sequences were reconstructed with iterative reconstruction with wavelet transformation (conventional CS) and secondly with a DL-constrained CS reconstruction (named CS-AI). Two readers graded image quality, based on 8 metrics (overall image quality, presence of image noise, presence of motion artifacts, delineation/conspicuity and clarity of anatomical structures such as the spinal cord, cauda equine nerve roots, cerebrospinal fluid (CSF), intervertebral disc, and bone marrow and intervertebral foramen) using Likert scales. Overall inter-readout agreement was substantial (Krippendorff's α=0.724, 95% confidence interval [CI]: 0.692-0.755). The CS7-AI and CS11-AI sequences were comparable or better than the 2D sequence in all 8 metrics (p < 0.001-p > 0.99). The CS7 and CS11 sequences were comparable or better than the 2D sequence in only 5 and 3 of the 8 metrics, respectively (p < 0.001-p > 0.99). A DL-constrained CS reconstruction significantly improves the quality of accelerated high-resolution 3D T2w TSE imaging of the lumbar spine. Thus, high-quality imaging in a submillimeter resolution in all three imaging planes can be achieved without compromising the image quality as compared with standard 2D T2w TSE imaging.

Deep learning model for automated diagnosis of degenerative cervical spondylosis and altered spinal cord signal on MRI

BACKGROUND CONTEXTA deep learning (DL) model for degenerative cervical spondylosis on MRI could enhance reporting consistency and efficiency, addressing a significant global health issue. PURPOSECreate a DL model to detect and classify cervical cord signal abnormalities, spinal canal and neural foraminal stenosis. STUDY DESIGN/SETTINGRetrospective study conducted from January 2013 to July 2021, excluding cases with instrumentation. PATIENT SAMPLEOverall, 504 MRI cervical spines were analyzed (504 patients, mean=58 years±13.7[SD]; 202 women) with 454 for training (90%) and 50 (10%) for internal testing. In addition, 100 MRI cervical spines were available for external testing (100 patients, mean=60 years±13.0[SD];26 women). OUTCOME MEASURESAutomated detection and classification of spinal canal stenosis, neural foraminal stenosis, and cord signal abnormality using the DL model. Recall(%), inter-rater agreement (Gwet's kappa), sensitivity, and specificity were calculated. METHODSUtilizing axial T2-weighted gradient echo and sagittal T2-weighted images, a transformer-based DL model was trained on data labeled by an experienced musculoskeletal radiologist (12 years of experience). Internal testing involved data labeled in consensus by 2 musculoskeletal radiologists (reference standard, both with 12-years-experience), 2 subspecialist radiologists, and 2 in-training radiologists. External testing was performed. RESULTSThe DL model exhibited substantial agreement surpassing all readers in all classes for spinal canal (κ=0.78, p<.001 vs. κ range=0.57–0.70 for readers) and neural foraminal stenosis (κ=0.80, p<.001 vs. κ range=0.63–0.69 for readers) classification. The DL model's recall for cord signal abnormality (92.3%) was similar to all readers (range: 92.3–100.0%). Nearly perfect agreement was demonstrated for binary classification (grades 0/1 vs. 2/3) (κ=0.95, p<.001 for spinal canal; κ=0.90, p<.001 for neural foramina). External testing showed substantial agreement using all classes (κ=0.76, p<.001 for spinal canal; κ=0.66, p<.001 for neural foramina) and high recall for cord signal abnormality (91.9%). The DL model demonstrated high sensitivities (range:83.7%–92.4%) and specificities (range:87.8%–98.3%) on both internal and external datasets for spinal canal and neural foramina classification. CONCLUSIONSOur DL model for degenerative cervical spondylosis on MRI showed good performance, demonstrating substantial agreement with the reference standard. This tool could assist radiologists in improving the efficiency and consistency of MRI cervical spondylosis assessments in clinical practice.

Lumbar foraminal stenosis was associated with back pain and leg pain: epidemiological evidence from a population-based cohort.

To determine the characteristics of lumbar foraminal stenosis (LFS) on magnetic resonance (MR) images and their association with back pain and radiating leg pain in a population-based sample of Chinese subjects. This study was an extension of the Hangzhou Lumbar Spine Study, a cross-sectional study focusing on back pain and lumbar spine MR imaging findings. Questionnaire data, including demographics, lifestyle, occupational exposures, back pain and radiating leg pain were included. On lumbar spine MR images, disc degeneration was assessed using Pfirrmann grade and Modic changes were evaluated. Using Lee's scale, the L3-S1 intervertebral foramina were evaluated, with grade 2-3 representing substantial LFS and grade 0-1 no LFS. Characteristics of LFS were noted, and associations of LFS with back pain and radiating leg pain were examined. Among the 644 study subjects, 141 (21.9%) had at least one LFS, and its occurrence was associated with greater age (OR = 1.93 for each 10 years, p < 0.001). Substantial LFS was associated with the presence of back pain (OR = 1.92, p = 0.001) and the intensity of the worst back pain (Coef = 8.30, p < 0.001) over the past 12 months, and disabling back pain during their lifetime (OR = 2.25, p < 0.001). Substantial LFS was also associated with leg pain (OR = 14.27, p < 0.001), with a sensitivity of 75.7% for the presence of radiating leg pain and a specificity of 81.4%. Substantial LFS on MR images was a common age-related degenerative phenotype in adults, and appears to be an independent risk factor for back pain and leg pain.