Objective Bone mineral density (BMD) is an important consideration during fusion surgery. Although dual X-ray absorptiometry is considered as the gold standard for assessing BMD, quantitative computed tomography (QCT) provides more accurate data in spine osteoporosis. However, QCT has the disadvantage of additional radiation hazard and cost. The present study was to demonstrate the utility of artificial intelligence and machine learning algorithm for assessing osteoporosis using Hounsfield units (HU) of preoperative lumbar CT coupling with data of QCT. Methods We reviewed 70 patients undergoing both QCT and conventional lumbar CT for spine surgery. The T-scores of 198 lumbar vertebra was assessed in QCT and the HU of vertebral body at the same level were measured in conventional CT by the picture archiving and communication system (PACS) system. A multiple regression algorithm was applied to predict the T-score using three independent variables (age, sex, and HU of vertebral body on conventional CT) coupling with T-score of QCT. Next, a logistic regression algorithm was applied to predict osteoporotic or non-osteoporotic vertebra. The Tensor flow and Python were used as the machine learning tools. The Tensor flow user interface developed in our institute was used for easy code generation. Results The predictive model with multiple regression algorithm estimated similar T-scores with data of QCT. HU demonstrates the similar results as QCT without the discordance in only one non-osteoporotic vertebra that indicated osteoporosis. From the training set, the predictive model classified the lumbar vertebra into two groups (osteoporotic vs. non-osteoporotic spine) with 88.0% accuracy. In a test set of 40 vertebrae, classification accuracy was 92.5% when the learning rate was 0.0001 (precision, 0.939; recall, 0.969; F1 score, 0.954; area under the curve, 0.900). Conclusion This study is a simple machine learning model applicable in the spine research field. The machine learning model can predict the T-score and osteoporotic vertebrae solely by measuring the HU of conventional CT, and this would help spine surgeons not to under-estimate the osteoporotic spine preoperatively. If applied to a bigger data set, we believe the predictive accuracy of our model will further increase. We propose that machine learning is an important modality of the medical research field.

AbstractObjectiveBone mineral density (BMD) is a very important factor in spinal fusion surgery using instrumentation. Our aim was to investigate the utility of Hounsfield units (HU) obtained from preoperative lumbar computed tomography (CT) to predict osteoporosis coupling with data of quantitative computed tomography (QCT) and dual X-ray absorptiometry (DEXA).MethodsWe reviewed 180 patients that underwent both QCT and lumbar CT for spine surgery. HU was retrospectively calculated on the lumbar CT of 503 lumbar vertebrae from L1 to L3. Femur DEXA was performed in all patients and spine DEXA was tested in 120 patients (331 vertebrae). BMD was grouped as osteoporosis (QCT<80mg/cm3, DEXA T score≤-2.5) and non-osteoporosis (QCT≥80mg/cm3, DEXA T score>-2.5) for comparison of HU value.ResultsHU value and BMD showed significant correlations. The optima cut-off value based on QCT was higher than that of DEXA scans which had the best correlation for predicting osteoporosis. ROC curve analysis demonstrated that HU value with QCT of 146 has a sensitivity of 94.3% and a specificity of 87.5% for osteoporosis.ConclusionsSignificant correlation was found between HU measurement and BMD value. These findings provide evidence that HU measurement can be established as a means for predicting osteoporosis before spine fusion surgery with reduced radiation hazard.

No abstract

This study indicates that no significant differences were observed in the clinical outcome between coil embolization and surgical clipping techniques in the treatment of aneurysms causing ONP. Coil embolization seems to be more feasible and safe treatment modality for the relief and recovery of oculomotor nerve palsy.

Recent interest in medical artificial intelligence (AI) has increased with onset of the fourth industrial revolution. Real-time monitoring of patients is an important research area of medical AI. The medical AI is very closely related to the Internet of Things (IoT), a core element of the fourth industrial revolution. Attempts to diagnose and treat patients using IoT have been already applied to patients with chronic disease such as hypertension and arrhythmia. However, in the spine, research on IoT and digital biomarkers are still in the early stages. The digital biomarker obtained by IoT devices is objective and could represent real-time, real-world, and abundant data. Based on its characteristics, IoT and digital biomarkers can also be useful in the spine. Currently, research on real-time monitoring of physical activity or spinal posture is ongoing. Therefore, the authors introduce the basic concepts of IoT and digital biomarkers, their relationship to AI, and recent trends. Current and future perspectives of IoT and digital biomarker in spine are also discussed. In the future, it is expected that IoT, digital biomarkers, and AI will lead to a paradigm shift in the diagnosis and treatment of spinal diseases.

A 47-year-old woman visited with lumbago and severe left leg pain that had been presented for 1 week. The patient complained of severe radiating pain on left L3 sensory dermatome area and reported aggravation of leg pain at 20 degrees of hip flexion by straight leg raising test (SLRT). However, there was no motor weakness on neurological examination. Magnetic resonance imaging (MRI) demonstrated contrast enhancing spinal extradural mass at L2-3 level that was iso-signal intensity (SI) on T1-weighted images (WI), hypo-SI on T2WI. She was not able to walk and sleep due to incapacitating pain. Thus, surgical removal was performed via left partial laminectomy. Postoperatively, the radiating pain was relieved completely. Histopathologic examination revealed that the tumor consisted of chondroma, which had mature hyaline cartilage with nests of benign-appearing cells and calcium deposits in lacunae.

This study suggests that internal trapping is a stable and effective treatment for acute VAD. Reconstructive treatment using stent and coils could also be a feasible alternative modality for hemorrhagic type VAD. However, serial DSA follow-up is essential.

ObjectiveCervical pedicle screw (CPS) placement is very challenging due to high risk of neurovascular complications. We devised a new technique (medial funnel technique) to improve the accuracy and feasibility of CPS placement.MethodsWe reviewed 28 consecutive patients undergoing CPS instrumentation using the medial funnel technique. Their mean age was 51.4 years (range, 30–81 years). Preoperative diagnosis included degenerative disease (n=5), trauma (n=22), and infection (n=1). Screw perforations were graded with the following criteria: grade 0 having no perforation, grade 1 having <25%, grade 2 having 25%–50% and grade 3 having >50% of screw diameter. Grades 0 and 1 were considered as correct position. The degree of perforation was determined by 2 junior neurosurgeons and 1 senior neurosurgeon.ResultsA total of 88 CPSs were inserted. The rate of correct placement was 94.3%; grade 0, 54 screws; grade 1, 29 screws; grade 2, 4 screws; and grade 3, 1 screw. No neurovascular complications or failure of instrumentation occurred. In perforated screws (34 screws), lateral perforations were 4 and medial perforations were 30.ConclusionWe performed CPS insertion using medial funnel technique and achieved 94.3% (83 of 88) of correct placement. And it can decrease lateral perforation.