메뉴 건너뛰기

추천
검색
질문

논문 기본 정보

자료유형
학술대회자료
저자정보
(Chosun University) (Chosun University) (Chosun University) (Chosun University)
저널정보
한국통신학회 한국통신학회 학술대회논문집 2019년도 한국통신학회 추계종합학술발표회 논문집
발행연도
수록면
58 - 61 (4page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
이 논문의 연구방법이 궁금하신가요?
🏆
연구결과
이 논문의 연구결과가 궁금하신가요?
AI에게 요청하기
추천
검색
질문

초록· 키워드

Recently, several high dimensional classification methods have been proposed to automatically discriminate between patients with Alzheimer"s disease (AD) and elderly controls (CN) based on T1-weighted MRI images. Moreover, many works have validated that multiple neuroimaging tools and biological biomarkers contain complementary information for early prognosis of AD. In this paper, we proposed an automatic classification by using multiple neuroimaging tools and finally combining them to classify AD vs HC. In total 180 subjects were downloaded from Open Access Series of Imaging Studies (OASIS) homepage, form which 90 subjects belong to AD and 90 subjects belong to (HC). We have used three types of feature extraction process which are NiftyReg, Freesurfer (6) and MALPEM (Multi-Atlas Labeled Propagation with EM refinement). For each image, we have extracted 246 Region of interest (ROI) using Brainnetome atlas using NiftyReg, 138 Region of Interest (ROI) using multi-labeled atlas in MALPEM and 68 regions using Freesurfer Destrieux atlas. According to KNN classifier result, multimodal feature achieved a good result for binary classification problem (AD and HC). Result, AUC of ROC for each of neuroimaging tools are 71%, 80%, 84% (NiftyReg, Freesurfer, MALPEM) and our method achieved 90% (AD and HC). Moreover, we have compared our result with the latest published state-of-the-art multimodal method.
상세정보 수정요청해당 페이지 내 제목·저자·목차·페이지
정보가 잘못된 경우 알려주세요!

목차

  1. Abstract
  2. I. INTRODUCTION
  3. II. MATERIAL AND METHOD
  4. III. EXPERIMENT RESULT
  5. IV. CONCLUSION
  6. REFERENCE

참고문헌

참고문헌 신청

최근 본 자료

전체보기
UCI(KEPA) : I410-ECN-0101-2020-567-000084819