메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술대회자료
저자정보
Dong Hyun Shin (Gachon Gil Hospital) Joon Hyop Lee (Gachon Gil Hospital) Yoo Seung Jung (Gachon Gil Hospital)
저널정보
대한외과학회 대한외과학회 학술대회 초록집 2021년 대한외과학회 춘계학술대회
발행연도
2021.5
수록면
239 - 239 (1page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
Purpose
Thyroidectomy is the most common cause of hypoparathyroidism. reserving the parathyroid during thyroidectomy is extremely important. However, the parathyroid glands are not easy to distinguish from the surrounding fat tissue or even lymph node for the inexperienced eye. The purpose of this study was to develop a real time-parathyroid detection algorithm based on deep learning technology that could aid endocrine surgeons in identifying the parathyroid gland during thyroidectomy and thus reduce post-operative hypoparathyroidism

Method
In this study, surgical video clips of 152 patients who underwent thyroid surgery at our institution were used. Both upper and lower parathyroids were filmed using a commercial camera and a 10mm 30 degrees’ endoscope after which intraoperative fine needle aspiration was performed to confirm the parathyroids. Still cut images of confirmed parathyroids were preprocessed for deep learning and region of interest (ROI) was identified by the surgeon as gold standard.
Key-frame images were extracted from each clips and their quality was evaluated according to the BRISQUE’s score system. Each image was geometrically, photometrically and Generative Adversarial Network-wise (GAN) transformed to augment the training set.
True object detection condition was defined as intersection over union (area of overlap/area of Union) ≥ 0.1 and probability ≥ 0.05. This alg ... 전체 초록 보기

목차

등록된 정보가 없습니다.

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

최근 본 자료

전체보기

댓글(0)

0