RELIABILITY OF THE MICHIGAN STATE UNIVERSITY (MSU) CLASSIFICATION OF LUMBAR DISC HERNIATION

Surgical Strategy for Lumbar Disc Herniation based on the MSU Classification: Percutaneous Endoscopic Lumbar Discectomy versus Transforaminal Lumbar Interbody Fusion: A 5-year Retrospective Study

OBJECTIVE

Currently, there is no established guideline on whether to opt for percutaneous endoscopic lumbar discectomy (PELD) or traditional transforaminal lumbar interbody fusion (TLIF) surgery based on specific types of lumbar disc herniation (LDH). Based on the Michigan State University (MSU) classification system, this study conducted a medium- to long-term follow-up analysis of two surgical methods over 5 years for the first time, aiming to provide empirical evidence to assist in making more informed decisions before surgery for LDH treatment.

METHODS

This was a retrospective study that included 273 patients with single-level LDH who underwent PELD or TLIF treatment at our hospital between January 1, 2016, and December 31, 2018. Detailed metrics included preoperative and postoperative visual analogue scale (VAS) scores and Oswestry disability index (ODI) at 1-day, 1-week, 1-year, and 5-year follow-ups. Complications, recurrences, and 5-year postoperative modified MacNab criteria scores were also recorded. Statistical methods included independent sample t-tests, repeated measures analysis of variance (ANOVA), and χ2 tests.

RESULTS

Classified into seven groups according to the MSU classification, it was found that there was an improvement in the VAS and ODI scores at four postoperative follow-ups (p < 0.001). PELD showed better results than TLIF in reducing pain and improving the ODI scores in the classifications of 3B, 2B, and 2C (p < 0.05). TLIF demonstrated consistent superiority over PELD in 2A, 2AB, 3A, and 3AB classifications (p < 0.05). The total recurrence rate in the PELD group (11.05%) within 5 years after surgery was higher (p < 0.05) than that in the TLIF group (3.96%). These were mainly concentrated in the 2A, 2AB, 3A, and 3AB types. Moreover, the rate of excellent and good outcomes in the PELD was higher than in the TLIF but no significant difference (χ2 = 1.0568, p = 0.5895).

CONCLUSION

This study suggests that PELD and TLIF may relieve LDH, but have advantages under different MSU classifications. The MSU classification has specific guiding significance and could aid in the surgical selection of PELD or TLIF to achieve optimal treatment outcomes for patients with lumbar disc herniation.

Transforaminal Endoscopic Discectomy for Thoracolumbar Disc Herniation: A Retrospective Study and Technical Note

BACKGROUND

Thoracolumbar disc herniation (TLDH) is a rare disorder with unique characteristics that can result in undesirable surgical outcomes after traditional discectomy. In view of the widespread use of transforaminal endoscopic discectomy for lower lumbar disc herniation, we investigated treatment of TLDH by this procedure. The purpose of this study was to evaluate the clinical efficacy of transforaminal endoscopic discectomy for treating TLDH and share our technical experience.

METHODS

We retrospectively evaluated the clinical data of 19 patients who had undergone transforaminal endoscopic discectomy for TLDH in our institution between April 2018 and July 2021. Operation time, follow-up time, blood loss, postoperative hospital stay, visual analog scale scores for low-back and leg pain, and Japanese Orthopedic Association (JOA) scores were evaluated.

RESULTS

The differences between preoperative and postoperative JOA and visual analog scale scores were significant (P < 0.05). According to the JOA scores, 14 of the 19 patients had excellent improvement, 3 had good improvement, and 2 had fair improvement; thus, the rate of satisfactory improvement was 89.5%.

CONCLUSIONS

Operation time, blood loss, postoperative hospital stay, and surgical outcomes were favorable. Transforaminal endoscopic discectomy is an ideal surgical procedure for treating TLDH.

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.

MRI-Based Medical Image Recognition: Identification and Diagnosis of LDH

To realize the automatic symptom recognition and classification of MR images and improve the accuracy and efficiency of the diagnosis of lumbar intervertebral disc herniation (LDH), a method for lumbar intervertebral disc recognition and disease classification is proposed in this paper. The method mainly includes three steps: preprocessing, target segmentation, and symptom classification. Preprocessing is performed by noise reduction and interference removal methods for blurred images. The contour poles are used to determine the four points of the tail vertebra in order to reduce the wrong segmentation of the tail vertebra. A classification method based on five judgment indicators is proposed, which effectively improves the stability of disease diagnosis. The example verifies that the algorithm can accurately complete the target segmentation and the accuracy of symptom classification reaches the standard of professional doctors, which proves that the method has good robustness.

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.