Diagnosis of osteoarthritic changes, loss of cervical lordosis, and disc space narrowing on cervical radiographs with deep learning methods.

OBJECTIVES: In this study, we aimed to differentiate normal cervical graphs and graphs of diseases that cause mechanical neck pain by using deep convolutional neural networks (DCNN) technology. MATERIALS AND METHODS: In this retrospective study, the convolutional neural networks were used and transfer learning method was applied with the pre-trained VGG-16, VGG-19, Resnet-101, and DenseNet-201 networks. Our data set consisted of 161 normal lateral cervical radiographs and 170 lateral cervical radiographs with osteoarthritis and cervical degenerative disc disease. RESULTS: We compared the performances of the classification models in terms of performance metrics such as accuracy, sensitivity, specificity, and precision metrics. Pre-trained VGG-16 network outperformed other models in terms of accuracy (93.9%), sensitivity (95.8%), specificity (92.0%), and precision (92.0%) results. CONCLUSION: The results of this study suggest that the deep learning methods are promising support tool in automated control of cervical graphs using the DCNN and the exclusion of normal graphs. Such a supportive tool may reduce the diagnosis time and provide radiologists or clinicians to have more time to interpret abnormal graphs.

Insights From Pupil Size to Mental Workload of Surgical Residents: Feasibility of an Educational Computer-Based Surgical Simulation Environment (ECE) Considering the Hand Condition.

The advantage of simulation environments is that they present various insights into real situations, where experimental research opportunities are very limited-for example, in endoscopic surgery. These operations require simultaneous use of both hands. For this reason, surgical residents need to develop several motor skills, such as eye-hand coordination and left-right hand coordination. While performing these tasks, the hand condition (dominant, nondominant, both hands) creates different degrees of mental workload, which can be assessed through mental physiological measures-namely, pupil size. Studies show that pupil size grows in direct proportion to mental workload. However, in the literature, there are very limited studies exploring this workload through the pupil sizes of the surgical residents under different hand conditions. Therefore, in this study, we present a computer-based simulation of a surgical task using eye-tracking technology to better understand the influence of the hand condition on the performance of skill-based surgical tasks in a computer-based simulated environment. The results show that under the both-hand condition, the pupil size of the surgical residents is larger than the one under the dominant and nondominant hand conditions. This indicates that when the computer-simulated surgical task is performed with both hands, it is considered more difficult than in the dominant and nondominant hand conditions. In conclusion, this study shows that pupil size measurements are sufficiently feasible to estimate the mental workload of the participants while performing surgical tasks. The results of this study can be used as a guide by instructional system designers of skill-based training programs.