Deep learning algorithm to evaluate cervical spondylotic myelopathy using lateral cervical spine radiograph

Efficacy Comparison of Osteopathic Muscle Energy Techniques and Cervical Mobilization on Pain, Disability, and Proprioception in Cervical Spondylosis Patients

BACKGROUND Cervical spondylosis (CS) is a degenerative disease of the cervical spine characterized by persistent neck pain. Cervical facet joint mobilization (CM) and the osteopathic muscle energy technique (MET) are effective manual procedures for the treatment of neck pain. In this study, we compared the efficacy of the MET and CM techniques on pain, disability, and proprioception in 76 patients with CS. MATERIAL AND METHODS A total of 96 participants with a diagnosis of CS were randomized into an electro-thermal therapy (ET) group (control group, n=32), ET+MET group (experiment I, n=32), and ET+CM group (experiment II, n=32). All patients received 3 treatment sessions per week for 4 consecutive weeks. Pain intensity, functional disability and cervical position sense were measured using the visual analog scale (VAS), Copenhagen Neck Functional Disability Scale (CNFDS), and cervical range of motion (CROM) device. RESULTS The study was completed by 76 participants. VAS and CNFDS scores decreased significantly after treatment in all 3 groups (P<0.001); however, there was no significant difference between the groups (P>0.05). Between-group analysis showed a significant difference in extension joint position error in favor of MET (P<0.001), while there was no significant difference between the groups in other movement directions (P>0.05). CONCLUSIONS MET and CM have similar effects on improving pain and disability in individuals with CS and chronic neck pain. However, the results of this study show that MET combined with ET is a more effective method for improving cervical position sense.

Long-Term Outcomes of One-Stage Combined Posteroanterior Procedure and Laminoplasty-Alone for Multilevel Degenerative Cervical Myelopathy With Concomitant Anterior and Posterior Compression: A Propensity Score Matching Analysis of 8-year Follow-Up

STUDY DESIGN

Retrospective cohort study.

OBJECTIVE

This study aimed to investigate the long-term outcomes of laminoplasty-alone (LP) and combined procedure (CP), consisting of laminoplasty and single-level anterior cervical discectomy and fusion, in comparable patients who had multilevel degenerative cervical myelopathy (MDCM) with concomitant anterior and posterior compression (CAPC).

METHODS

Consecutive MDCM patients with CAPC underwent LP or CP between 2012 and 2015 from a same surgical group were enrolled and followed up for a minimum of 8 years. Preoperative demographic, radiological, and clinical variables were collected. Propensity score matching (PSM) analysis was performed to match patients with comparable conditions. The outcomes were evaluated by postoperative Japanese Orthopedic Association (JOA) score improvement, JOA recovery rate (JOARR) and complications.

RESULTS

A total of 230 patients were included, of whom 146 underwent LP and 84 underwent CP. After PSM, 84 pairs of comparable patients were matched. The matched groups presented fair comparability in preoperative conditions. The CP group had significantly prolonged surgery time and greater blood loss. At the final follow-up, the postoperative JOA scores of LP and CP groups were 14.51 ± 1.79 and 15.47 ± 1.81 (P < 0.001) and the JOARR were 42.5% ± 53.3% and 68.5% ± 35.4%, respectively (P < 0.001). Three (3.6%) patients in the LP group underwent reoperations because of recurrent symptoms (P = 0.081).

CONCLUSION

Both LP and CP demonstrated considerable long-term neurological recovery in patients with CAPC. The CP showed a significantly higher JOA improvement and JOARR. The combined decompression might be a safe and effective alternative in treating MDCM with CAPC in experienced hands.

Detection of Cervical Foraminal Stenosis from Oblique Radiograph Using Convolutional Neural Network Algorithm

PURPOSE

This study was conducted to develop a convolutional neural network (CNN) algorithm that can diagnose cervical foraminal stenosis using oblique radiographs and evaluate its accuracy.

MATERIALS AND METHODS

A total of 997 patients who underwent cervical MRI and cervical oblique radiographs within a 3-month interval were included. Oblique radiographs were labeled as "foraminal stenosis" or "no foraminal stenosis" according to whether foraminal stenosis was present in the C2-T1 levels based on MRI evaluation as ground truth. The CNN model involved data augmentation, image preprocessing, and transfer learning using DenseNet161. Visualization of the location of the CNN model was performed using gradient-weight class activation mapping (Grad-CAM).

RESULTS

The area under the curve (AUC) of the receiver operating characteristic curve based on DenseNet161 was 0.889 (95% confidence interval, 0.851-0.927). The F1 score, accuracy, precision, and recall were 88.5%, 84.6%, 88.1%, and 88.5%, respectively. The accuracy of the proposed CNN model was significantly higher than that of two orthopedic surgeons (64.0%, p<0.001; 58.0%, p<0.001). Grad-CAM analysis demonstrated that the CNN model most frequently focused on the foramen location for the determination of foraminal stenosis, although disc space was also frequently taken into consideration.

CONCLUSION

A CNN algorithm that can detect neural foraminal stenosis in cervical oblique radiographs was developed. The AUC, F1 score, and accuracy were 0.889, 88.5%, and 84.6%, respectively. With the current CNN model, cervical oblique radiography could be a more effective screening tool for neural foraminal stenosis.

Deep learning-based detection of lumbar spinal canal stenosis using convolutional neural networks

BACKGROUND CONTEXT

Lumbar spinal canal stenosis (LSCS) is the most common spinal degenerative disorder in elderly people and usually first seen by primary care physicians or orthopedic surgeons who are not spine surgery specialists. Magnetic resonance imaging (MRI) is useful in the diagnosis of LSCS, but the equipment is often not available or difficult to read. LSCS patients with progressive neurologic deficits have difficulty with recovery if surgical treatment is delayed. So, early diagnosis and determination of appropriate surgical indications are crucial in the treatment of LSCS. Convolutional neural networks (CNNs), a type of deep learning, offers significant advantages for image recognition and classification, and work well with radiographs, which can be easily taken at any facility.

PURPOSE

Our purpose was to develop an algorithm to diagnose the presence or absence of LSCS requiring surgery from plain radiographs using CNNs.

STUDY DESIGN

Retrospective analysis of consecutive, nonrandomized series of patients at a single institution.

PATIENT SAMPLE

Data of 150 patients who underwent surgery for LSCS, including degenerative spondylolisthesis, at a single institution from January 2022 to August 2022, were collected. Additionally, 25 patients who underwent surgery at 2 other hospitals were included for extra external validation.

OUTCOME MEASURES

In annotation 1, the area under the curve (AUC) computed from the receiver operating characteristic (ROC) curve, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, positive likelihood ratio (PLR), and negative likelihood ratio (NLR) were calculated. In annotation 2, correlation coefficients were used.

METHODS

Four intervertebral levels from L1/2 to L4/5 were extracted as region of interest from lateral plain lumbar spine radiographs totaling 600 images were obtained. Based on the date of surgery, 500 images derived from the first 125 cases were used for internal validation, and 100 images from the subsequent 25 cases used for external validation. Additionally, 100 images from other hospitals were used for extra external validation. In annotation 1, binary classification of operative and nonoperative levels was used, and in annotation 2, the spinal canal area measured on axial MRI was labeled as the output layer. For internal validation, the 500 images were divided into each 5 dataset on per-patient basis and 5-fold cross-validation was performed. Five trained models were registered in the external validation prediction performance. Grad-CAM was used to visualize area with the high features extracted by CNNs.

RESULTS

In internal validation, the AUC and accuracy for annotation 1 ranged between 0.85-0.89 and 79-83%, respectively, and the correlation coefficients for annotation 2 ranged between 0.53 and 0.64 (all p<.01). In external validation, the AUC and accuracy for annotation 1 were 0.90 and 82%, respectively, and the correlation coefficient for annotation 2 was 0.69, using 5 trained CNN models. In the extra external validation, the AUC and accuracy for annotation 1 were 0.89 and 84%, respectively, and the correlation coefficient for annotation 2 was 0.56. Grad-CAM showed high feature density in the intervertebral joints and posterior intervertebral discs.

CONCLUSIONS

This technology automatically detects LSCS from plain lumbar spine radiographs, making it possible for medical facilities without MRI or nonspecialists to diagnose LSCS, suggesting the possibility of eliminating delays in the diagnosis and treatment of LSCS that require early treatment.

Would the one-stage combined approach lead to better long-term neurological outcomes than the posterior approach alone in multilevel degenerative cervical myelopathy patients with T2-Weighted increased signal intensity? An 8-year follow-up results and propensity score matching analysis

BACKGROUND

T2-weighted increased signal intensity (ISI) is commonly recognized as a sign of more severe spinal cord lesions, usually accompanied by worse neurological deficits and possibly worse postoperative neurological recovery. The combined approach could achieve better decompression and better neurological recovery for multilevel degenerative cervical myelopathy (MDCM). The choice of surgical approach for MDCM with intramedullary T2-weighted ISI remains disputed. This study aimed to compare the neurological outcomes of posterior and one-stage combined posteroanterior approaches for MDCM with T2-weighted ISI.

METHODS

A total of 83 consecutive MDCM patients with confirmed ISI with at least three intervertebral segments operated between 2012 and 2014 were retrospectively enrolled. Preoperative demographic, radiological and clinical condition variables were collected, and neurological conditions were evaluated by the Japanese Orthopedic Assessment score (JOA) and Neck Disability Index (NDI). Propensity score matching analysis was conducted to produce pairs of patients with comparable preoperative conditions from the posterior-alone and combined groups. Both short-term and mid-term surgical outcomes were evaluated, including the JOA recovery rate (JOARR), NDI improvements, complications, and reoperations.

RESULTS

A total of 83 patients were enrolled, of which 38 and 45 patients underwent posterior surgery alone and one-stage posteroanterior surgery, respectively. After propensity score matching, 38 pairs of comparable patients from the posterior and combined groups were matched. The matched groups presented similar preoperative clinical and radiological features and the mean follow-up duration were 111.6 ± 8.9 months. The preoperative JOA scores of the posterior and combined groups were 11.5 ± 2.2 and 11.1 ± 2.3, respectively (p = 0.613). The combined group presented with prolonged surgery duration(108.8 ± 28.0 and 186.1 ± 47.3 min, p = 0.028) and greater blood loss(276.3 ± 139.1 and 382.1 ± 283.1 ml, p<0.001). At short-term follow-up, the combined group presented a higher JOARR than the posterior group (posterior group: 50.7%±46.6%, combined group: 70.4%±20.3%, p = 0.024), while no significant difference in JOARR was observed between the groups at long-term follow-up (posterior group: 49.2%±48.5%, combined group: 59.6%±47.6%, p = 0.136). No significant difference was found in the overall complication and reoperation rates.

CONCLUSIONS

For MDCM patients with ISI, both posterior and one-stage posteroanterior approaches could achieve considerable neurological alleviations in short-term and long-term follow-up. With greater surgical trauma, the combined group presented better short-term JOARR but did not show higher efficacy in long-term neurological function preservation in patients with comparable preoperative conditions.

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.

Cervical Spondylosis Diagnosis Based on Convolutional Neural Network with X-ray Images

The increase in Cervical Spondylosis cases and the expansion of the affected demographic to younger patients have escalated the demand for X-ray screening. Challenges include variability in imaging technology, differences in equipment specifications, and the diverse experience levels of clinicians, which collectively hinder diagnostic accuracy. In response, a deep learning approach utilizing a ResNet-34 convolutional neural network has been developed. This model, trained on a comprehensive dataset of 1235 cervical spine X-ray images representing a wide range of projection angles, aims to mitigate these issues by providing a robust tool for diagnosis. Validation of the model was performed on an independent set of 136 X-ray images, also varied in projection angles, to ensure its efficacy across diverse clinical scenarios. The model achieved a classification accuracy of 89.7%, significantly outperforming the traditional manual diagnostic approach, which has an accuracy of 68.3%. This advancement demonstrates the viability of deep learning models to not only complement but enhance the diagnostic capabilities of clinicians in identifying Cervical Spondylosis, offering a promising avenue for improving diagnostic accuracy and efficiency in clinical settings.

Deep learning-based spinal canal segmentation of computed tomography image for disease diagnosis: A proposed system for spinal stenosis diagnosis

BACKGROUND

Lumbar disc herniation was regarded as an age-related degenerative disease. Nevertheless, emerging reports highlight a discernible shift, illustrating the prevalence of these conditions among younger individuals.

METHODS

This study introduces a novel deep learning methodology tailored for spinal canal segmentation and disease diagnosis, emphasizing image processing techniques that delve into essential image attributes such as gray levels, texture, and statistical structures to refine segmentation accuracy.

RESULTS

Analysis reveals a progressive increase in the size of vertebrae and intervertebral discs from the cervical to lumbar regions. Vertebrae, bearing weight and safeguarding the spinal cord and nerves, are interconnected by intervertebral discs, resilient structures that counteract spinal pressure. Experimental findings demonstrate a lack of pronounced anteroposterior bending during flexion and extension, maintaining displacement and rotation angles consistently approximating zero. This consistency maintains uniform anterior and posterior vertebrae heights, coupled with parallel intervertebral disc heights, aligning with theoretical expectations.

CONCLUSIONS

Accuracy assessment employs 2 methods: IoU and Dice, and the average accuracy of IoU is 88% and that of Dice is 96.4%. The proposed deep learning-based system showcases promising results in spinal canal segmentation, laying a foundation for precise stenosis diagnosis in computed tomography images. This contributes significantly to advancements in spinal pathology understanding and treatment.

Initial study on an expert system for spine diseases screening using inertial measurement unit

In recent times, widely understood spine diseases have advanced to one of the most urgetn problems where quick diagnosis and treatment are needed. To diagnose its specifics (e.g. to decide whether this is a scoliosis or sagittal imbalance) and assess its extend, various kind of imaging diagnostic methods (such as X-Ray, CT, MRI scan or ST) are used. However, despite their common use, some may be regarded as (to a level) invasive methods and there are cases where there are contraindications to using them. Besides, which is even more of a problem, these are very expensive methods and whilst their use for pure diagnostic purposes is absolutely valid, then due to their cost, they cannot rather be considered as tools which would be equally valid for bad posture screening programs purposes. This paper provides an initial evaluation of the alternative approach to the spine diseases diagnostic/screening using inertial measurement unit and we propose policy-based computing as the core for the inference systems. Although the methodology presented herein is potentially applicable to a variety of spine diseases, in the nearest future we will focus specifically on sagittal imbalance detection.

Deep Learning Algorithm for Identifying Cervical Cord Compression Due to Degenerative Canal Stenosis on Radiography

STUDY DESIGN

Cross-sectional study.

OBJECTIVE

Validate the diagnostic accuracy of a deep-learning algorithm for cervical cord compression due to degenerative canal stenosis on radiography.

SUMMARY OF BACKGROUND DATA

The diagnosis of degenerative cervical myelopathy is often delayed, resulting in improper management. Screening tools for suspected degenerative cervical myelopathy would help identify patients who require detailed physical evaluation.

MATERIALS AND METHODS

Data from 240 patients (120 with cervical stenosis on magnetic resonance imaging and 120 age and sex-matched controls) were randomly divided into training (n = 198) and test (n = 42) data sets. The deep-learning algorithm, designed to identify the suspected stenosis level on radiography, was constructed using a convolutional neural network model called EfficientNetB2, and radiography and magnetic resonance imaging data from the training data set. The accuracy and area under the curve of the receiver operating characteristic curve were calculated for the independent test data set. Finally, the number of correct diagnoses was compared between the algorithm and 10 physicians using the test cohort.

RESULTS

The diagnostic accuracy and area under the curve of the deep-learning algorithm were 0.81 and 0.81, respectively, in the independent test data set. The rate of correct responses in the test data set was significantly higher for the algorithm than for the physician's consensus (81.0% vs . 66.2%; P = 0.034). Furthermore, the accuracy of the algorithm was greater than that of each individual physician.

CONCLUSIONS

We developed a deep-learning algorithm capable of suggesting the presence of cervical spinal cord compression on cervical radiography and highlighting the suspected levels on radiographic imaging when cord compression is identified. The diagnostic accuracy of the algorithm was greater than that of spine physicians.

LEVEL OF EVIDENCE

Level IV.

Assessment of Fusion After Anterior Cervical Discectomy and Fusion Using Convolutional Neural Network Algorithm

BACKGROUND

A convolutional neural network (CNN) is a deep learning (DL) model specialized for image processing, analysis, and classification.

OBJECTIVE

In this study, we evaluated whether a CNN model using lateral cervical spine radiographs as input data can help assess fusion after anterior cervical discectomy and fusion (ACDF).

STUDY DESIGN

Diagnostic imaging study using DL.

PATIENT SAMPLE

We included 187 patients who underwent ACDF and fusion assessment with postoperative one-year computed tomography and neutral and dynamic lateral cervical spine radiographs.

OUTCOME MEASURES

The performance of the CNN-based DL algorithm was evaluated in terms of accuracy and area under the curve.

MATERIALS AND METHODS

Fusion or nonunion was confirmed by cervical spine computed tomography. Among the 187 patients, 69.5% (130 patients) were randomly selected as the training set, and the remaining 30.5% (57 patients) were assigned to the validation set to evaluate model performance. Radiographs of the cervical spine were used as input images to develop a CNN-based DL algorithm. The CNN algorithm used three radiographs (neutral, flexion, and extension) per patient and showed the diagnostic results as fusion (0) or nonunion (1) for each radiograph. By combining the results of the three radiographs, the final decision for a patient was determined to be fusion (fusion ≥2) or nonunion (fusion ≤1). By combining the results of the three radiographs, the final decision for a patient was determined as fusion (fusion ≥2) or nonunion (nonunion ≤1).

RESULTS

The CNN-based DL model demonstrated an accuracy of 89.5% and an area under the curve of 0.889 (95% confidence interval, 0.793-0.984).

CONCLUSION

The CNN algorithm for fusion assessment after ACDF trained using lateral cervical radiographs showed a relatively high diagnostic accuracy of 89.5% and is expected to be a useful aid in detecting pseudarthrosis.

A deep belief network-based clinical decision system for patients with osteosarcoma

Osteosarcoma was the most frequent type of malignant primary bone tumor with a poor survival rate mainly occurring in children and adolescents. For precision treatment, an accurate individualized prognosis for Osteosarcoma patients is highly desired. In recent years, many machine learning-based approaches have been used to predict distant metastasis and overall survival based on available individual information. In this study, we compared the performance of the deep belief networks (DBN) algorithm with six other machine learning algorithms, including Random Forest, XGBoost, Decision Tree, Gradient Boosting Machine, Logistic Regression, and Naive Bayes Classifier, to predict lung metastasis for Osteosarcoma patients. Therefore the DBN-based lung metastasis prediction model was integrated as a parameter into the Cox proportional hazards model to predict the overall survival of Osteosarcoma patients. The accuracy, precision, recall, and F1 score of the DBN algorithm were 0.917/0.888, 0.896/0.643, 0.956/0.900, and 0.925/0.750 in the training/validation sets, respectively, which were better than the other six machine-learning algorithms. For the performance of the DBN survival Cox model, the areas under the curve (AUCs) for the 1-, 3- and 5-year survival in the training set were 0.851, 0.806 and 0.793, respectively, indicating good discrimination, and the calibration curves showed good agreement between the prediction and actual observations. The DBN survival Cox model also demonstrated promising performance in the validation set. In addition, a nomogram integrating the DBN output was designed as a tool to aid clinical decision-making.