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
안영샘 (인하대학교) 권장우 (인하대학교)
저널정보
한국재활복지공학회 한국재활복지공학회 학술대회 논문집 2018 한국재활복지공학회 춘계학술심포지엄
발행연도
2018.4
수록면
103 - 106 (4page)

이용수

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

초록· 키워드

오류제보하기
In this paper, there are more than 10 million people with cerebrovascular diseases worldwide, and this trend is steadily increasing. Especially in developed countries, patients with cerebrovascular disease are the leading cause of death rate, along with cancer and heart disease. Cerebrovascular disease requires ongoing management because the after-effect remains chronic, and the patient`s condition as well as condition on surface must be followed up with a radiological device. Since there is no way to see inside the skull with an X-ray, we need to check the patient`s condition using CT or MRI device. Even though the same Dicom file is the output, the resolution for each of the MRI and CT and the FOV is different, so it is necessary to manually adjust the size and to set it in order to compare at a glance.
Therefore, even if doctors directly shoot with CT and MRI devices, there is a probability of making mistakes if they manually adjust the image, adjust to the image. Moreover, it would require a lot of work.
To solve this problem, GAN (Generative Adversarial Networks) has been used to modulate MRI into CT through Deep Learning, which is one of the artificial intelligence technologies that has developed as the symbol of fourth industrial revolution era, giving the world a ripple effect. The same resolution and the same environment are assumed in this process. In order to create such DataSet, a pre-processing has to be done manually by a person, so that work can be performed.
We conducted research to replace the uncertainly matched tasks by using the CT and MRI registration software with the existing CT and MRI images without conversion or by registering them after the output operation. Experimental results confirmed that the initial values of CT and MRI cannot be accurately registered for various reasons, and this software was proved necessary.
In the future, this software can be applied to application image processing such as registration through Canny Edge Detection, Blur, Sift, and SURF image processing, mathematical algorithm, automatic image registration through machine learning and deep running. I will study further to make it more convenient.

목차

ABSTRACT
1. 서론
2. 제안하는 내용
3. 실험결과
4. 결론
REFERENCES

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

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

이 논문의 저자 정보

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-ECN-0101-2018-512-002052128