Use of residual neural network for the detection of ossification of the posterior longitudinal ligament on plain cervical radiography.

Ossification of the posterior longitudinal ligament (OPLL) causes serious problems, such as myelopathy and acute spinal cord injury. The early and accurate diagnosis of OPLL would hence prevent the miserable prognoses. Plain lateral radiography is an essential method for the evaluation of OPLL. Therefore, minimizing the diagnostic errors of OPLL on radiography is crucial. Image identification based on a residual neural network (RNN) has been recognized to be potentially effective as a diagnostic strategy for orthopedic diseases; however, the accuracy of detecting OPLL using RNN has remained unclear. An RNN was trained with plain lateral cervical radiography images of 2,318 images from 672 patients (535 images from 304 patients with OPLL and 1,773 images from 368 patients of Negative). The accuracy, sensitivity, specificity, false positive rate, and false negative rate of diagnosis of the RNN were calculated. The mean accuracy, sensitivity, specificity, false positive rate, and false negative rate of the model were 98.9%, 97.0%, 99.4%, 2.2%, and 1.0%, respectively. The model achieved an overall area under the curve of 0.99 (95% confidence interval, 0.97-1.00) in which AUC in each fold estimated was 0.99, 0.99, 0.98, 0.98, and 0.99, respectively. An algorithm trained by an RNN could make binary classification of OPLL on cervical lateral X-ray images. RNN may hence be useful as a screening tool to assist physicians in identifying patients with OPLL in future setting. To achieve accurate identification of OPLL patients clinically, RNN has to be trained with other cause of myelopathy.

Long-Term Outcomes Following Lumbar Microendoscopic Decompression for Lumbar Spinal Stenosis with and without Degenerative Spondylolisthesis: Minimum 10-Year Follow-Up.

OBJECTIVE: To determine whether preoperative presence of degenerative lumbar spondylolisthesis (DS) worsens the minimum 10-year outcome of patients undergoing microendoscopic decompression (MED) for lumbar spinal stenosis (SS). METHODS: Eighty patients undergoing MED were classified into 2 groups: DS group (34 SS with DS patients) and SS group (46 SS without DS patients). The degrees of improvement (DOIs) by the Japanese Orthopaedic Association Back Pain Evaluation Questionnaire (JOABPEQ) and intensities of improvement (IOIs) by Visual Analog Scale (VAS) at 120-159 (mean, 138.4) months after MED of the DS and SS groups were statistically compared. Patients with DS were classified into 2 groups based on the effectiveness by VAS or JOABPEQ: effective group (E group: IOI or DOI ≥20) and ineffective group (I group). All preoperative radiologic measurements were statistically compared between the E and I groups. RESULTS: Significant decreases in low back pain, leg pain, and numbness, as measured by VAS, were noted at follow-up in the DS and SS groups. The effectiveness rates of pain-related disorders, lumbar spine dysfunction, and gait disturbance by JOABPEQ were almost equally high in the DS and SS groups. Statistical comparisons of the DOIs in all 5 functional scores and IOIs in low back pain, leg pain, and numbness showed no significant differences between the DS and SS groups. No significant differences were confirmed between the E and I groups concerning preoperative spondylolisthesis and instability. CONCLUSIONS: Our study indicated that preoperative DS did not worsen the outcome of patients with SS undergoing MED.

Artificial intelligence for the detection of vertebral fractures on plain spinal radiography.

Vertebral fractures (VFs) cause serious problems, such as substantial functional loss and a high mortality rate, and a delayed diagnosis may further worsen the prognosis. Plain thoracolumbar radiography (PTLR) is an essential method for the evaluation of VFs. Therefore, minimizing the diagnostic errors of VFs on PTLR is crucial. Image identification based on a deep convolutional neural network (DCNN) has been recognized to be potentially effective as a diagnostic strategy; however, the accuracy for detecting VFs has not been fully investigated. A DCNN was trained with PTLR images of 300 patients (150 patients with and 150 without VFs). The accuracy, sensitivity, and specificity of diagnosis of the model were calculated and compared with those of orthopedic residents, orthopedic surgeons, and spine surgeons. The DCNN achieved accuracy, sensitivity, and specificity rates of 86.0% [95% confidence interval (CI) 82.0-90.0%], 84.7% (95% CI 78.8-90.5%), and 87.3% (95% CI 81.9-92.7%), respectively. Both the accuracy and sensitivity of the model were suggested to be noninferior to those of orthopedic surgeons. The DCNN can assist clinicians in the early identification of VFs and in managing patients, to prevent further invasive interventions and a decreased quality of life.