MRI-based detection of cervical ossification of the posterior longitudinal ligament using a novel automated machine learning diagnostic tool.

OBJECTIVE: Currently, CT is considered the gold standard for the diagnosis of ossification of the posterior longitudinal ligament (OPLL). The objective of this study was to develop artificial intelligence (AI) software and a validated model for the identification and representation of cervical OPLL (C-OPLL) on MRI, obviating the need for spine CT. METHODS: A retrospective evaluation was performed of consecutive imaging studies of all adult patients who underwent both cervical CT and MRI for any clinical indication within a span of 36 months (between January 2017 and July 2020) in a single tertiary-care referral hospital. C-OPLL was identified by a panel of neurosurgeons and a neuroradiologist. MATLAB software was then used to create an AI tool for the diagnosis of C-OPLL by using a convolutional neural network method to identify features on MR images. A reader study was performed to compare the performance of the AI model to that of the diagnostic panel using standard test performance metrics. Interobserver variability was assessed using Cohen's kappa score. RESULTS: Nine hundred consecutive patients were found to be eligible for radiological evaluation, yielding 65 identified C-OPLL carriers. The AI model, utilizing MR images, was able to accurately segment the vertebral bodies, PLL, and discoligamentous complex, and detect C-OPLL carriers. The AI model identified 5 additional C-OPLL patients who were not initially detected. The performance of the MRI-based AI model resulted in a sensitivity of 85%, specificity of 98%, negative predictive value of 98%, and positive predictive value of 85%. The overall accuracy of the model was 98%, with a kappa score of 0.917. CONCLUSIONS: The novel AI software developed in this study was highly specific for identifying C-OPLL on MRI, without the use of CT. This model may obviate the need for CT scans while maintaining adequate diagnostic accuracy. With further development, this MRI-based AI model has the potential to aid in the diagnosis of various spinal disorders and its automated layers may lay the foundation for MRI-specific diagnostic criteria for C-OPLL.

Vicarious growth among social work students: What makes the difference?

This study examined the contribution of background variables, personal factors (professional commitment) and environmental factors (peer support and supervision) to social work students' vicarious growth as an implication of their field practicums with trauma victims. Special emphasis was placed on examining the role of secondary traumatisation in the growth process. The sample consisted of 259 social work students at three social work schools in Israel. All students conducted their field practicums in social services and worked with trauma victims. The findings indicated that the mean level of growth was moderate and significant contribution was made by the student's year of study. Specifically, students in their third year of social work school showed more growth than did students in their first year. In addition, a positive contribution was made by the students' supervision satisfaction, professional commitment and secondary traumatisation. The findings thus highlight the possibility of students' growth during their field practicums. In addition, the study emphasises the significant role played by supervisors in these practicums, in terms of both helping students grow as well as dealing with the distress they may feel during this part of their social work training.