공현중 교수

As the number of robotic surgery procedures has increased, so has the importance of evaluating surgical skills in these techniques. It is difficult, however, to automatically and quantitatively evaluate surgical skills during robotic surgery, as these skills are primarily associated with the movement of surgical instruments. This study proposes a deep learning-based surgical instrument tracking algorithm to evaluate surgeons' skills in performing procedures by robotic surgery. This method overca

We demonstrated that the performance of federated learning using decentralized data was comparable to that of conventional deep learning using pooled data. Federated learning might be potentially useful for analyzing medical images while protecting patients' personal information.

The findings indicate that prolonged exercise is superior to multiple short sessions for improving the risk of metabolic syndrome and the atherogenic index in middle-aged obese women. However, multiple short sessions can be recommended as an alternative to prolonged exercise when the goal is to decrease blood glucose or waist circumference.

Introducing IoT-based technology to clinical sites, including medical institutions, will enhance the quality of medical services, increase patient safety, improve management efficiency, and promote patient-centered medical services. Moreover, the IoT is expected to play an active role in the five major tasks of facility hygiene in medical fields, which are all required to deal with the COVID-19 pandemic: social distancing, contact tracking, bed occupancy control, and air quality management. Ulti

Thus far, there have been no reported specific rules for systematically determining the appropriate augmented sample size to optimize model performance when conducting data augmentation. In this paper, we report on the feasibility of synthetic data augmentation using generative adversarial networks (GAN) by proposing an automation pipeline to find the optimal multiple of data augmentation to achieve the best deep learning-based diagnostic performance in a limited dataset. We used Waters' view ra

The potential for remote health care can be increased by simplifying the AD screening process. Furthermore, by facilitating remote health care, the proposed method can enhance the accessibility of AD screening and increase the rate of early AD detection.

Stereo disc photograph was analyzed and reconstructed as 3 dimensional contour image to evaluate the status of the optic nerve head for the early detection of glaucoma and the evaluation of the efficacy of treatment. Stepwise preprocessing was introduced to detect the edge of the optic nerve head and retinal vessels and reduce noises. Paired images were registered by power cepstrum method and zero-mean normalized cross-correlation. After Gaussian blurring, median filter application and disparity

Although there are some limitations to our study, these results may prove useful for detecting teeth with impaired vitality and non-invasively differentiating between necrotic and vital pulp.

We demonstrate that a surface-emitting hybrid light source can be realized by a combination of organic and inorganic light-emitting devices (LEDs). To this end, a blue inorganic LED bar is deployed at one side of a transparent light guide plate (LGP), and a yellow organic LED (OLED) is in contact with the rear surface of the LGP. In such a configuration, it is found that the overall luminance is almost equivalent to the sum of the luminances measured from each light source, and the overall lumin

Flow rate differences between pressure flow studies and free uroflowmetry are not due to mechanical obstruction by the catheter but to other factors, such as the bladder filling method. Objective parameters on the natural fill telemetric pressure flow study correlated with standard pressure flow study findings. The natural fill telemetric pressure flow study shortened the time needed for the test and may decrease the discomfort of the standard pressure flow study.