Prognostic Value of Michigan State University (MSU) Classification for Lumbar Disc Herniation: Is It Suitable for Surgical Selection?

Medium- to long-term functional outcomes of artcure diffusional patch therapy for lumbar disc herniation: which herniation is more likely to require surgery?

BACKGROUND

Artcure diffusional patch (ADP) is a novel transdermal therapeutic system that started to be used in the last decade for lumbar disc herniation (LDH). Previous studies have reported early results of the therapy. In this study, we aimed to evaluate the medium- to long-term functional outcomes of this treatment in LDH patients and examine factors predicting the need for surgery after treatment.

METHODS

Totally, 270 patients with single-level LDH were included. ADP was applied transdermally to the lumbar regions of the patients. Outcomes measures included the Oswestry Disability Index (ODI) and leg and low back visual analog scales (VAS). Herniations were graded using the Michigan State University (MSU) classification. The predictive factors for surgery need were analyzed with logistic regression analysis.

RESULTS

The average follow-up duration was 43.8 ± 4.8 months. The average VAS and ODI scores of the patients decreased significantly at the first month and final visits compared to admission values (p < 0.001). Within the follow-up period, 19 (7.0%) patients underwent surgery. The results of the multivariate analysis showed that ≥ 2 MSU grade of the herniation was a significant predictive factor for operation need (HR: 7.32 (1.87-28.57), p = 0.004).

CONCLUSION

Single-dose ADP therapy is a safe and feasible treatment option in the treatment of single-level LDH and can achieve favorable functional and pain scores at medium- to long-term. Patients with MSU grade two and three herniations should be monitored more closely, as they are more likely to experience a later surgical intervention.

CLINICAL TRIAL NUMBER

Not applicable.

The Relationship Between Disc Herniation Morphology and Patient-Reported Outcomes after Microdiscectomy

OBJECTIVE

Determine if herniation morphology based on the Michigan State University Classification is associated with differences in (1) patient-reported outcome measures (or (2) surgical outcomes after a microdiscectomy.

METHODS

Adult patients undergoing single-level microdiscectomy between 2014 and 2021 were identified. Demographics and surgical characteristics were collected through a query search and manual chart review. The Michigan State University classification, which assesses disc herniation laterality (zone A was central, zone B/C was lateral) and degree of extrusion into the central canal (grade 1 was up to 50% of the distance to the intra-facet line, grade >1 was beyond this line), was identified on preoperative MRIs. patient-reported outcome measures were collected at preoperative, 3-month, and 1-year postoperative time points.

RESULTS

Of 233 patients, 84 had zone A versus 149 zone B/C herniations while 76 had grade 1 disc extrusion and 157 had >1 grade. There was no difference in surgical outcomes between groups (P > 0.05). Patients with extrusion grade >1 were found to have lower Physical Component Score at baseline. On bivariate and multivariable logistic regression analysis, extrusion grade >1 was a significant independent predictor of greater improvement in Physical Component Score at three months (estimate = 7.957; CI: 4.443-11.471, P < 0.001), but not at 1 year.

CONCLUSIONS

Although all patients were found to improve after microdiscectomy, patients with disc herniations extending further posteriorly reported lower preoperative physical function but experienced significantly greater improvement three months after surgery. However, improvement in Visual Analog Scale Leg and back, ODI, and MCS at three and twelve months was unrelated to laterality or depth of disc herniation.

A fully automatic MRI-guided decision support system for lumbar disc herniation using machine learning

Background

Normalized decision support system for lumbar disc herniation (LDH) will improve reproducibility compared with subjective clinical diagnosis and treatment. Magnetic resonance imaging (MRI) plays an essential role in the evaluation of LDH. This study aimed to develop an MRI-based decision support system for LDH, which evaluates lumbar discs in a reproducible, consistent, and reliable manner.

Methods

The research team proposed a system based on machine learning that was trained and tested by a large, manually labeled data set comprising 217 patients' MRI scans (3255 lumbar discs). The system analyzes the radiological features of identified discs to diagnose herniation and classifies discs by Pfirrmann grade and MSU classification. Based on the assessment, the system provides clinical advice.

Results

Eventually, the accuracy of the diagnosis process reached 95.83%. An 83.5% agreement was observed between the system's prediction and the ground-truth in the Pfirrmann grade. In the case of MSU classification, 95.0% precision was achieved. With the assistance of this system, the accuracy, interpretation efficiency and interrater agreement among surgeons were improved substantially.

Conclusion

This system showed considerable accuracy and efficiency, and therefore could serve as an objective reference for the diagnosis and treatment procedure in clinical practice.

Functional Outcomes and Successful Predictors of Lumbar Transforaminal Epidural Steroid Injections (LTFESIs) for Lumbar Radiculopathy Under Fluoroscopic Guidance: A Prospective Study

BACKGROUND

Lumbar radiculopathy, a common and debilitating condition, often necessitates a multimodal approach for effective management. Lumbar transforaminal epidural steroid injection (LTFESI) has emerged as a valuable therapeutic option when conservative measures fall short. Recent interest in long-acting and non-particulate steroids prompts a critical examination of their impact on LTFESI outcomes. This prospective study aims to evaluate the efficacy of LTFESI in improving pain and functional outcomes in patients with lumbar radiculopathy, focusing on long-acting and non-particulate steroids, and analyse the associated economic burden.

METHODS

The study, conducted from October 2017 to April 2019, involved 52 patients with lumbar radiculopathy meeting specific criteria. LTFESI was administered using a hospital-based prospective design. Functional outcomes were assessed using the Oswestry Disability Index (ODI) and Numeric Rating Scale (NRS) scores at various intervals. Statistical analyses were performed to identify predictors of successful outcomes.

RESULTS

Participants (average age 43.22 years, 27 (51.92%) male) exhibited diverse Michigan State University (MSU) grade profiles and predominantly had pathology at the L4-5 level. The study demonstrated a significant and lasting functional improvement in 43 (82.69%) of patients after LTFESI. Patients with 2AB-type intervertebral disc prolapse (IVDP) showed lower response rates, emphasizing subtype influence. The efficacy of LTFESI was sustained for up to six months in almost 82.69% of patients, highlighting its potential for long-lasting benefits. The difference in the mean ODI score pre-injection and six months post-injection is statistically significant (p<0.0001). A total of four patients (7.69%) underwent surgical treatment for lumbar radiculopathy as their symptoms did not improve after injection. For all four patients (7.69%), surgery was done one month after injection. Five patients (9.61%) had ODI scores of more than 40, indicating severe disability at the end of six months. So, in nine patients (17.3%), the injection given was not effective at the end of six months, four (7.69%) of whom were operated on and five (9.61%) patients received conservative treatment. Thus, 43 (82.69%) of patients had a good outcome.

DISCUSSION

The study reinforces LTFESI as an effective and safe intervention, providing substantial and lasting benefits for lumbar radiculopathy. The majority experienced immediate relief, supporting its role as an intermediate option between conservative management and surgery. Identified predictors of decreased success underscore the importance of early intervention and tailored treatment plans. The study emphasizes LTFESI's diagnostic and therapeutic potential, with economic benefits and safety highlighted.

CONCLUSION

LTFESI emerges as a safe and effective intervention for lumbar radiculopathy, offering substantial and enduring pain relief. The study contributes valuable insights into the nuanced outcomes of LTFESI, including the impact of IVDP subtypes, factors influencing success, and the procedure's cost-effectiveness. While acknowledging limitations, this work adds to the growing evidence supporting LTFESI as a crucial component in the management of lumbar radiculopathy.

Deep learning-based detection and classification of lumbar disc herniation on magnetic resonance images

Background

The severity assessment of lumbar disc herniation (LDH) on MR images is crucial for selecting suitable surgical candidates. However, the interpretation of MR images is time-consuming and requires repetitive work. This study aims to develop and evaluate a deep learning-based diagnostic model for automated LDH detection and classification on lumbar axial T2-weighted MR images.

Methods

A total of 1115 patients were analyzed in this retrospective study; both a development dataset (1015 patients, 15 249 images) and an external test dataset (100 patients, 1273 images) were utilized. According to the Michigan State University (MSU) classification criterion, experts labeled all images with consensus, and the final labeled results were regarded as the reference standard. The automated diagnostic model comprised Faster R-CNN and ResNeXt101 as the detection and classification network, respectively. The deep learning-based diagnostic performance was evaluated by calculating mean intersection over union (IoU), accuracy, precision, sensitivity, specificity, F1 score, the area under the receiver operating characteristics curve (AUC), and intraclass correlation coefficient (ICC) with 95% confidence intervals (CIs).

Results

High detection consistency was obtained in the internal test dataset (mean IoU = 0.82, precision = 98.4%, sensitivity = 99.4%) and external test dataset (mean IoU = 0.70, precision = 96.3%, sensitivity = 97.8%). Overall accuracy for LDH classification was 87.70% (95% CI: 86.59%-88.86%) and 74.23% (95% CI: 71.83%-76.75%) in the internal and external test datasets, respectively. For internal testing, the proposed model achieved a high agreement in classification (ICC = 0.87, 95% CI: 0.86-0.88, P < 0.001), which was higher than that of external testing (ICC = 0.79, 95% CI: 0.76-0.81, P < 0.001). The AUC for model classification was 0.965 (95% CI: 0.962-0.968) and 0.916 (95% CI: 0.908-0.925) in the internal and external test datasets, respectively.

Conclusions

The automated diagnostic model achieved high performance in detecting and classifying LDH and exhibited considerable consistency with experts' classification.

Transtubular Endoscopic Neuronavigation-Assisted Approach for Extraforaminal Lumbar Disk Herniations: A New Trend for a Common Neurosurgical Disease

BACKGROUND

Extraforaminal lumbar disk herniations (ELDHs) are relatively rare and are, till today, diagnostic and therapeutic challenges. The transmuscular paramedian approach to the extraforaminal space is today the standard surgical approach. Nevertheless, controlling the correct trajectory to the extruded disk fragment continues to represent a challenge. The application of spinal navigation and spinal endoscopy seems to offer great advantages to ELDH treatment.

OBJECTIVE

The purpose of this study is to demonstrate the advantages of spinal navigation for ELDHs by taking a purely endoscopic transtubular approach, focusing on technical aspects and clinical outcomes.

METHODS

Nine consecutive patients who underwent a navigation-assisted, muscle-splitting, transtubular, purely endoscopic approach for ELDHs were retrospectively analyzed. Their clinical records were reviewed. Pain evaluations and neurological assessments were conducted.

RESULTS

We recorded a notable visual analog scale (VAS) score improvement in postoperative examinations. The mean operation time was 47.05 min. All patients were discharged on postoperative day 1.

CONCLUSION

The use of spinal navigation offers a great advantage to ELDH treatment. The aid of navigation allows for a patient-tailored approach and adequate surgical exploration even in face of complex lesion anatomies. The endoscopic transtubular navigated approach seems to offer a significant reduction in operative time, at least in the selected cases.

Automatic Grading of Disc Herniation, Central Canal Stenosis and Nerve Roots Compression in Lumbar Magnetic Resonance Image Diagnosis

AIM

Accurate severity grading of lumbar spine disease by magnetic resonance images (MRIs) plays an important role in selecting appropriate treatment for the disease. However, interpreting these complex MRIs is a repetitive and time-consuming workload for clinicians, especially radiologists. Here, we aim to develop a multi-task classification model based on artificial intelligence for automated grading of lumbar disc herniation (LDH), lumbar central canal stenosis (LCCS) and lumbar nerve roots compression (LNRC) at lumbar axial MRIs.

METHODS

Total 15254 lumbar axial T2W MRIs as the internal dataset obtained from the Fifth Affiliated Hospital of Sun Yat-sen University from January 2015 to May 2019 and 1273 axial T2W MRIs as the external test dataset obtained from the Third Affiliated Hospital of Southern Medical University from June 2016 to December 2017 were analyzed in this retrospective study. Two clinicians annotated and graded all MRIs using the three international classification systems. In agreement, these results served as the reference standard; In disagreement, outcomes were adjudicated by an expert surgeon to establish the reference standard. The internal dataset was randomly split into an internal training set (70%), validation set (15%) and test set (15%). The multi-task classification model based on ResNet-50 consists of a backbone network for feature extraction and three fully-connected (FC) networks for classification and performs the classification tasks of LDH, LCCS, and LNRC at lumbar MRIs. Precision, accuracy, sensitivity, specificity, F1 scores, confusion matrices, receiver-operating characteristics and interrater agreement (Gwet k) were utilized to assess the model's performance on the internal test dataset and external test datasets.

RESULTS

A total of 1115 patients, including 1015 patients from the internal dataset and 100 patients from the external test dataset [mean age, 49 years ± 15 (standard deviation); 543 women], were evaluated in this study. The overall accuracies of grading for LDH, LCCS and LNRC were 84.17% (74.16%), 86.99% (79.65%) and 81.21% (74.16%) respectively on the internal (external) test dataset. Internal and external testing of three spinal diseases showed substantial to the almost perfect agreement (k, 0.67 - 0.85) for the multi-task classification model.

CONCLUSION

The multi-task classification model has achieved promising performance in the automated grading of LDH, LCCS and LNRC at lumbar axial T2W MRIs.