Purpose: Focused ultrasound is an emerging technology for treating the brain locally in a noninvasive manner. In this study, we have investigated the influence of skull properties on simulating transcranial pressure field. Methods: A 3D computational model of transcranial focused ultrasound was constructed using female and male CT data to solve for intracranial pressure. For heterogeneous model, the acoustic properties were calculated from CT Hounsfield units based on a porosity. The homogeneous model assigned constant acoustic properties for the single-layered skull. Results: A computational model was validated against empirical data. The homogeneous models were then compared with the heterogeneous model, resulted in 10.87% and 7.19% differences in peak pressure for female and male models respectively. For the focal volume, homogeneous model demonstrated more than 94% overlap compared with the heterogeneous model. Conclusion: Homogeneous model can be constructed using MR images that are commonly used for the segmentation of the skull. We propose the possibility of the homogeneous model for the simulating transcranial pressure field owing to comparable focal volume between homogeneous model and heterogeneous model.

Brain-computer interface (BCI) is a technology that allows users with motor disturbance to control machines by brainwaves without a physical controller. Motor imagery (MI)-BCI is one of the popular BCI techniques, but it needs a long calibration time for users to perform a mental task that causes high fatigue to the users. MI is reported as showing a similar neural mechanism as motor execution (ME) and motor observation (MO). However, integrative investigations of these three tasks are rarely conducted. In this study, we propose a new paradigm that incorporates three tasks (MI, ME, and MO) and conducted a comparative analysis. For this study, we collected Electroencephalograms (EEG) of motor imagery/execution/observation from 28 healthy subjects and investigated alpha event-related (de)synchronization (ERD/ERS) and classification accuracy (left vs. right motor tasks). As result, we observed ERD and ERS in MI, MO and ME although the timing is different across tasks. In addition, the MI showed strong ERD on the contralateral hemisphere, while the MO showed strong ERD on the ipsilateral side. In the classification analysis using a Riemannian geometry-based classifier, we obtained classification accuracies as MO (66.34%), MI (60.06%) and ME (58.57%). We conclude that there are similarities and differences in fundamental neural mechanisms across the three motor tasks and that these results could be used to advance the current MI-BCI further by incorporating data from ME and MO.

In this study, the accuracy of the orthognathic surgical guides with single-stage split path was upgraded to realize orthognathic surgical guides with two-stage split path and simulated surgery was performed to verify its accuracy. As a result, the average error distance between the simulation model and the scan model was + 0.289 / - 0.468 mm (standard deviation 0.128), which was confirmed to be within ± 0.5 mm, which is a clinically acceptable level. Also, there was no significant difference compared with the average value of + 0.313 / - 0.456 mm (average standard deviation 0.106) of the conventional single-stage split path type device. It is judged that the use of this device can contribute to the reduction of surgical time and increase in accuracy since a separate finishing operation for bone preparation is unnecessary.

Ultrasound examination using ultrasound equipment is an ultrasound device that images human organs using sound waves and is used in various areas such as diagnosis, follow-up, and treatment of diseases. However, if the quality of ultrasound equipment is not guaranteed, the possibility of misdiagnosis increases, and the diagnosis rate decreases. Accordingly, The Korean Society of Radiology and Korea society of Ultrasound in Medicine presented guidelines for quality management of ultrasound equipment using ATS-539 phantom. The DenseNet201 classification algorithm shows 99.25% accuracy and 5.17% loss in the Dead Zone, 97.52% loss in Axial/Lateral Resolution, 96.98% accuracy and 20.64% loss in Sensitivity, 93.44% accuracy and 22.07% loss in the Gray scale and Dynamic Range. As a result, it is the best and is judged to be an algorithm that can be used for quantitative evaluation. Through this study, it can be seen that if quantitative evaluation using artificial intelligence is conducted in the qualitative evaluation item of ultrasonic equipment, the reliability of ultrasonic equipment can be increased with high accuracy.

Because arrhythmia occurs irregularly, it should be examined for at least 24 hours for accurate diagnosis. For this reason, this paper developed firmware software for arrhythmia detection and prevented consumption of temporal and human resources and enabled continuous management and early diagnosis. Prior to the experiment, the interval between the R peaks of the QRS Complex was calculated using the Pan-Tompkins algorithm. The developed firmware software designed and implemented an algorithm to detect arrhythmia such as tachycardia, bradycardia, ventricular tachycardia, persistent tachycardia, and non-persistent tachycardia, and a data transmission format to monitor the collected data based on BLE. As a result of the experiment, arrhythmia was found in real time according to the change in BPM as designed in this paper. And the data quality for BLE communication was verified by comparing the sensor's serial communication value with the Android application reception value. In the future, wearable devices for real-time arrhythmia detection will be lightweight and developed firmware software will be applied.

Since the detection of cervical intraepithelial neoplasia (CIN) is increasing due to regular cervical cancer screening, there is a high demand for simpler tools to diagnose and treat CIN in the clinic. In this study, we proposed an electric property of cervical tissue to verify treatment using a laser. At first, we observed the depth and width of ablated cervical tissues for 29 samples according to four different pulse energy of the fractional CO₂ laser to find enough pulse energy to reach the basement layer for initiated CIN. And then, the relative frequency differences in impedance spectrum before and after laser irradiation for ten non-CIN samples were collected using bioimpedance spectroscopy with a multi-electrode probe. As a result, the laser ablated the cervical tissues with a depth of more than 300 ㎛ at 100 mJ pulse energy. Also, we confirmed that the relative changes of electrical property for cervical tissue increased as the pulse energy of laser output increased, and the variation between samples decreased. Since the relative change in electrical properties of cervical tissue can be easily and quickly measured, the proposed technique paves the way for further verification and follow-up study of laser treatment for CIN.

The present study proposed a new interface system for capsule endoscopy by using head mounted display (HMD) device, which can control the orientation of the capsule endoscope with electromagnetic actuator (EMA) system. The orientation information of the HMD user was detected by the gyroscope sensor built into the device and then calculated to as an angle increment using Unity Engine compiler. The measured angle changes from the HMD were converted to the current values of the corresponding coils to be changed in the EMA system. Two experiments were designed to measure the accuracy and the intuitiveness of the HMD interface system. In the angle accuracy measurement, the capsule endoscope driven by HMD interface system showed the averaged errors of 0.68 degrees horizontally and 1.001 degrees vertically for given test angles. In the intuitiveness measurement, HMD interface system showed 1.33 times faster manipulation speed rather than the joystick interface system. In this respect, the HMD interface system for capsule endoscopy was expected to improve the overall diagnostic environment while maintaining comfort of patients and clinicians.

As the proportion of non-contact telemedicine increases and the number of electrocardiogram (ECG) data measured using portable ECG monitors increases, the demand for automatic algorithms that can precisely analyze vast amounts of ECG is increasing. Since the P, QRS, and T waves of the ECG have different shapes depending on the location of electrodes or individual characteristics and often have similar frequency components or amplitudes, it is difficult to distinguish P, QRS and T waves and measure each parameter. In order to measure the widths, intervals and areas of P, QRS, and T waves, a new algorithm that recognizes the start and end points of each wave and automatically measures the time differences and amplitudes between each point is required. In this study, the start and end points of the P, QRS, and T waves were measured using six Deep Neural Networks (DNN) that recognize the start and end points of each wave. Then, by synthesizing the results of all DNNs, 12 parameters for ECG characteristics for each heartbeat were obtained. In the ECG waveform of 10 subjects provided by Physionet, 12 parameters were measured for each of 660 heartbeats, and the 12 parameters measured for each heartbeat well represented the characteristics of the ECG, so it was possible to distinguish them from other subjects' parameters. When the ECG data of 10 subjects were combined into one file and analyzed with the suggested algorithm, 10 types of ECG waveform were observed, and two types of ECG waveform were simultaneously observed in 5 subjects, however, it was not observed that one person had more than two types.

Liver transplantation is a critical used treatment method for patients with end-stage liver disease. The number of cases of living donor liver transplantation is increasing due to the imbalance in needs and supplies for brain-dead organ donation. As a result, the importance of the accuracy of the donor's suitability evaluation is also increasing rapidly. To measure the donor's liver volume accurately is the most important, that is absolutely necessary for the recipient's postoperative progress and the donor's safety. Therefore, we propose liver segmentation in abdominal CT images from pre-operation, POD 7, and POD 63 with a two-dimensional U-Net. In addition, we introduce an algorithm to measure the volume of the segmented liver and measure the hepatectomy rate and regeneration rate of pre-operation, POD 7, and POD 63. The performance for the learning model shows the best results in the images from pre-operation. Each dataset from pre-operation, POD 7, and POD 63 has the DSC of 94.55 ± 9.24%, 88.40 ± 18.01%, and 90.64 ± 14.35%. The mean of the measured liver volumes by trained model are 1423.44 ± 270.17 ml in pre-operation, 842.99 ± 190.95 ml in POD 7, and 1048.32 ± 201.02 ml in POD 63. The donor's hepatectomy rate is an average of 39.68 ± 13.06%, and the regeneration rate in POD 63 is an average of 14.78 ± 14.07%.

In this paper, we propose a pill identification model using engraved text feature and image feature such as shape and color, and compare it with an identification model that does not use engraved text feature to verify the possibility of improving identification performance by improving recognition rate of the engraved text. The data consisted of 100 classes and used 10 images per class. The engraved text feature was acquired through Keras OCR based on deep learning and 1D CNN, and the image feature was acquired through 2D CNN. According to the identification results, the accuracy of the text recognition model was 90%. The accuracy of the comparative model and the proposed model was 91.9% and 97.6%. The accuracy, precision, recall, and F1-score of the proposed model were better than those of the comparative model in terms of statistical significance. As a result, we confirmed that the expansion of the range of feature improved the performance of the identification model.