http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A deep learning based method for maxillofacial bone segmentation in CBCT images
Su Yang(양수),Se-Ryong Kang(강세룡),So-Young Chun(천소영),Ji-Yong Yoo(유지용),Jin Kim(김진),Da El Kim(김다엘),Won-Jin Yi(이원진) 대한전기학회 2021 대한전기학회 학술대회 논문집 Vol.2021 No.10
Cone-beam computed tomography (CBCT) images of the oral and maxillofacial region are commonly used in diagnosing and planning for surgical or orthodontic treatment to correct maxillofacial deformities. It is clinically essential to reconstruct a three dimensional model of maxillofacial structures for orthognathic surgery planning. However, this manual process is very tedious, challenging, and time-consuming. To resolve this problem, we proposed a deep learning based method for mandible and maxilla segmentation in CBCT images. Experimental results show that the proposed network achieves higher performance in all tasks than the baseline segmentation method.
딥러닝을 이용한 방사선학적 골 손실과 치주염 단계 분류의 자동적 진단 방법
이상정(Sang-Jeong Lee),강세룡(Se-Ryong Kang),양수(Su Yang),최민혁(Min-Hyuk Choi),김조은(Jo-Eun Kim),허경회(Kyung-Hoe Huh),이삼선(Sam-Sun Lee),허민석(Min-Suk Heo),이원진(Won-Jin Yi) 대한전기학회 2021 전기학회논문지 Vol.70 No.12
In this study, a deep learning hybrid framework was developed to automatically stage periodontitis in dental panoramic radiographs. The framework was proposed to automatically quantify the periodontal bone loss and classify periodontitis for each individual tooth into four stages according to the criteria that was proposed at the 2017 World Workshop. Radiographic bone level (or CEJ level) was detected using deep learning with a simple structure of the entire jaw in panoramic radiographs. Next, the percent ratio analysis of the radiographic bone loss combined the tooth long-axis with periodontal bone and CEJ levels. The percentage ratios can be used to automatically classify periodontal bone loss. Additionally, the number of missing teeth was quantified by detecting the position of the missing teeth in the panoramic radiographs. A multi-device study was also performed to verify the generality of the developed method. The mean absolute difference (MAD) between periodontitis stages by the automatic method and by the radiologists was 0.31 overall for all the teeth in the whole jaw. The MADs for the images from the multiple devices were 0.25, 0.34, and 0.35 for devices 1, 2, and 3, respectively. The developed method had a high accuracy, reliability, and generality when automatically diagnosing periodontal bone loss and the staging of periodontitis by the multi-device study.
증강현실 수술 내비게이션 시스템을 위한 단일 카메라 깊이 추정 기반 마커리스 정합
최민혁(Min-Hyuk Choi),최시은(Si-Eun Choi),강세룡(Se-Ryong Kang),유지용(Ji-Yong Yoo),양수(Su Yang),김조은(Jo-Eun Kim),허경회(Kyung-Hoe Huh),이삼선(Sam-Sun Lee),허민석(Min-Suk Heo),이원진(Won-Jin Yi) 대한전기학회 2021 전기학회논문지 Vol.70 No.12
In augmented reality(AR) surgical navigation system, the depth estimation using RGBD camera has limitation in obtaining the dense depth necessary to increase the registration accuracy. Recently, deep learning based monocular depth estimation has showed remarkable performance. In this study, we developed a markerless registration method using the monocular depth estimation, and applied it to AR surgical navigation system. The accuracy of our method of monocular depth estimation was 2.47 ± 1.15mm, while that of the method of the RGBD camera was 2.33 ± 1.24mm. There was no significant difference by paired T-test. Furthermore, the monocular depth estimation was able to acquire denser depth than the RGBD camera.
치아 크라운 질량 중심 및 각도 자동 예측을 위한 PointNet++ 기반 방법
천소영(Soyoung Chun),양수(Su Yang),유지용(Jiyong Yoo),최민혁(MinHyuk Choi),강세룡(Se-Ryong Kang),최시은(Sieun Choi),전보성(Bosoung Jeoun),김진(Jin Kim),이원진(Wonjin Yi) 대한전기학회 2021 대한전기학회 학술대회 논문집 Vol.2021 No.10
환자별 임플란트 크라운을 설계하기 위해서는 환자별 치아 위치, 치아 각도, 상악과 하악 사이의 교합 등을 고려해야 한다. 본 연구에서는 임플란트 크라운 설계를 위한 환자 임상치 크라운의 질량 중심과 각도 단위 벡터를 자동으로 예측하는 수정된 PointNet++를 제안하였다. 결과적으로 우리의 방법이 환자 맞춤형 임플란트 크라운의 자동 설계에 적용되기를 기대한다.