• Investigative Magnetic Resonance Imaging
• /
• 제25권3호
• /
• pp.156-163
• /
• 2021

Recently, neuromelanin and nigrosome imaging techniques have been developed to evaluate the substantia nigra in Parkinson's disease. Previous studies have shown potential benefits of quantitative analysis of neuromelanin and nigrosome images in the substantia nigra, although visual assessments have been performed to evaluate structures in most studies. In this study, we investigate the potential of using deep learning based automatic region segmentation techniques for quantitative analysis of the substantia nigra. The deep convolutional neural network was trained to automatically segment substantia nigra regions on 3D nigrosome and neuromelanin sensitive MR images obtained from 30 subjects. With a 5-fold cross-validation, the mean calculated dice similarity coefficient between manual and deep learning was 0.70 ± 0.11. Although calculated dice similarity coefficients were relatively low due to empirically drawn margins, selected slices were overlapped for more than two slices of all subjects. Our results demonstrate that deep convolutional neural network-based method could provide reliable localization of substantia nigra regions on neuromelanin and nigrosome sensitive MR images.

• 대한의용생체공학회:의공학회지
• /
• 제39권1호
• /
• pp.43-47
• /
• 2018

Traditional electroencephalography (EEG)-based authentication systems generally use external stimuli that require user attention and relatively long time for authentication. The aim of this study is to investigate the feasibility of biometric authentication based on EEG without using any external stimuli. Seventeen subjects took part in the experiment and their EEGs were measured while repetitively closing and opening their eyes. For identifying each subject, we calculated inter- and intra-subject cross-correlation using changes in alpha activity (8-13 Hz) during eyes closed as compared to eyes open. In order to optimize the number of recording electrodes, we calculated authentication accuracy by progressively reducing the number of electrodes used in the analysis. Significant increase in alpha activity was observed for all subjects during eyes closed, focusing on occipital areas, and spatial patterns of changed alpha activity were considerably different between the subjects. A mean authentication accuracy of 92.45% was obtained, which was retained over 75% when using only 8 electrodes placed around occipital areas. Our results could demonstrate the feasibility of the proposed novel authentication method based on resting state EEGs.

• 한국융합학회논문지
• /
• 제5권1호
• /
• pp.35-41
• /
• 2014

An automatic speech recognition system is one of the popular research problems. There are many research groups working in this field for different language including Japanese. Japanese vowel recognition is one of important parts in the Japanese speech recognition system. The vowel classification system with the Mamdani fuzzy inference system was developed in this research. We tested our system on the blind test data set collected from one male native Japanese speaker and four male non-native Japanese speakers. All subjects in the blind test data set were not the same subjects in the training data set. We found out that the classification rate from the training data set is 95.0 %. In the speaker-independent experiments, the classification rate from the native speaker is around 70.0 %, whereas that from the non-native speakers is around 80.5 %.

• 대한의생명과학회지
• /
• 제25권1호
• /
• pp.99-106
• /
• 2019

Amyloid positron emission tomography (PET) allows early and accurate diagnosis in suspected cases of Alzheimer's disease (AD) and contributes to future treatment plans. In the present study, a method of implementing a diagnostic system to distinguish ${\beta}$-Amyloid ($A{\beta}$) positive from $A{\beta}$ negative with objectiveness and accuracy was proposed using a machine learning approach, such as the Principal Component Analysis (PCA) and Support Vector Machine (SVM). $^{18}F$-Florbetaben (FBB) brain PET images were arranged in control and patients (total n = 176) with mild cognitive impairment and AD. An SVM was used to classify the slices of registered PET image using PET template, and a system was created to diagnose patients comprehensively from the output of the trained model. To compare the per-slice classification, the PCA-SVM model observing the whole brain (WB) region showed the highest performance (accuracy 92.38, specificity 92.87, sensitivity 92.87), followed by SVM with gray matter masking (GMM) (accuracy 92.22, specificity 92.13, sensitivity 92.28) for $A{\beta}$ positivity. To compare according to per-subject classification, the PCA-SVM with WB also showed the highest performance (accuracy 89.21, specificity 71.67, sensitivity 98.28), followed by PCA-SVM with GMM (accuracy 85.80, specificity 61.67, sensitivity 98.28) for $A{\beta}$ positivity. When comparing the area under curve (AUC), PCA-SVM with WB was the highest for per-slice classifiers (0.992), and the models except for SVM with WM were highest for the per-subject classifier (1.000). We can classify $^{18}F$-Florbetaben amyloid brain PET image for $A{\beta}$ positivity using PCA-SVM model, with no additional effects on GMM.

• 대한의생명과학회지
• /
• 제24권4호
• /
• pp.418-425
• /
• 2018

Amyloid brain positron emission tomography (PET) images are visually and subjectively analyzed by the physician with a lot of time and effort to determine the ${\beta}$-Amyloid ($A{\beta}$) deposition. We designed a convolutional neural network (CNN) model that predicts the $A{\beta}$-positive and $A{\beta}$-negative status. We performed 18F-florbetaben (FBB) brain PET on controls and patients (n=176) with mild cognitive impairment and Alzheimer's Disease (AD). We classified brain PET images visually as per the on the brain amyloid plaque load score. We designed the visual geometry group (VGG16) model for the visual assessment of slice-based samples. To evaluate only the gray matter and not the white matter, gray matter masking (GMM) was applied to the slice-based standard samples. All the performance metrics were higher with GMM than without GMM (accuracy 92.39 vs. 89.60, sensitivity 87.93 vs. 85.76, and specificity 98.94 vs. 95.32). For the patient-based standard, all the performance metrics were almost the same (accuracy 89.78 vs. 89.21), lower (sensitivity 93.97 vs. 99.14), and higher (specificity 81.67 vs. 70.00). The area under curve with the VGG16 model that observed the gray matter region only was slightly higher than the model that observed the whole brain for both slice-based and patient-based decision processes. Amyloid brain PET images can be appropriately analyzed using the CNN model for predicting the $A{\beta}$-positive and $A{\beta}$-negative status.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2024년도 춘계학술발표대회
• /
• pp.447-449
• /
• 2024

본 논문에서 다양한 환경적 요인에서 촬영한 이미지 데이터를 활용하여 신호등 위치의 정확한 탐지 및 신호등의 색상 인식을 통해 교통 신호를 판별하는데 사용되는 컴퓨터 비전 기반의 신호등 인식 시스템 알고리즘을 제안하였다. 이를 통해 기존에 신호를 인식하던 LiDAR 및 RADAR 센서를 대신해 카메라를 사용함으로써 자율주행 차의 제작비용 감소를 기대할 수 있다. 또한 다양한 환경의 이미지 데이터를 통해 실험을 진행하였고 이러한 실험결과를 분석하고 적용함으로써 악천후에서의 효과적인 신호등 인식 시스템을 구축하는데 기여하고자 한다.

• 한국안광학회지
• /
• 제5권1호
• /
• pp.101-105
• /
• 2000

본 연구는 한국인을 대상으로 주시점의 위치에 따른 시 표적이 뇌파에 미치는 영향을 조사한 것이다. 시유발 전위 장치는 BIO-Pag를 이용하였으며, 검사 결과는 586 컴퓨터에 입력하여 분석하였다. 조도는 500lux이여 시표는 직경이 3 cm인 붉은 광점을 사용하였다. 수렴과 개산에 따른 결과는 다음과 같다. 1. 시자극에 관계하는 시피질의 뇌파의 출현 빈도는 델타파, 베타파, 세타파, 그리고 알파파의 순으로 나타났다. 2. 수렴 상태는 개산에 비해서 속파 성분이 많이 출현되었다. 3. 수렴은 개산에 비해서 베타파와 알파파가 많아 나타났다. 4. 수렴과 개산에서 진폭에 대한 히스토 그램은 비가우시안 모양이다. 5. 뇌파의 진폭에 대한 위상 분석은 거의 선상을 나타내었다.

• 대한의용생체공학회:의공학회지
• /
• 제17권3호
• /
• pp.347-354
• /
• 1996

This paper presents digital hearing aids signal processing system in WT(wavelet transform) domain. For implementation of hearing aids in WT domain, the gain in frequency domain is approximated in WT domain. We also present the gain selection algorithm to deal with the change of input signal power. Most transform methods produce blocking effect, and this effect degrades the convergence rate of feedback canceller. As a solution, we proposed wavelet transform bascd feedback canceller. To evaluate the performance, we compared it with LOT (lapped orthogonal transform) method in the frequency domain. This system has not shown the blocking effect, and improves convergence rate as compared with the LOT based feedback canceller.

• Nuclear Engineering and Technology
• /
• 제55권11호
• /
• pp.4019-4025
• /
• 2023

Recently, a new monkey computational phantom, called Visible Monkey, was developed for non-ionizing radiation studies in animal research. In this study, we extended its applications to ionizing radiation studies by implementing the voxel model of the Visible Monkey into three general-purpose Monte Carlo (MC) codes: MCNP6, PHITS, and Geant4. The implementation work for MCNP and PHITS was conducted using the LATTICE, UNIVERSE, and FILL cards. The G4VNestedParameterisation class was used for Geant4. Then, organ dose coefficients (DCs) for idealized photon beams in the antero-posterior direction were calculated using the three codes and compared, showing excellent agreement (differences <3%). Additionally, organ DCs in other directions (postero-anterior, left-lateral, and right-lateral) were calculated and compared with those of the newborn and 1-year-old reference phantoms. Significant differences were observed (e.g., the stomach DC of the monkey was 5-fold greater than that of the 1-year-old phantom at 0.03 MeV) while the differences tended to decrease with increasing energy (mostly <20% at 10 MeV). The results of this study allows conducting MC simulations using the Visible Monkey to estimate organ-level doses, which should be valuable to support/improve monkey experiments involving ionizing radiation exposures.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1992년도 춘계학술대회
• /
• pp.79-81
• /
• 1992

This paper describes the design of an adaptive closed circuit anesthesia controller based on a multiplexed mass spectrometer system. The controller deals with measurement deterioration caused by measurement delay and rise time through a tong catheter as well as long sampling times due to the multiplexed measurements. Measurement data is extrapolated between sampling periods to increase the estimation convergence rate. A multiple-step-ahead predictive control algorithm is used to calculate intermediatc control inputs between sampling intervals. Simulations are used to validate the designed controller.