한국정보처리학회:학술대회논문집 (Proceedings of the Korea Information Processing Society Conference)
- 한국정보처리학회 2020년도 추계학술발표대회
- /
- Pages.1036-1038
- /
- 2020
- /
- 2005-0011(pISSN)
- /
- 2671-7298(eISSN)
DOI QR Code
다중 확장된 컨볼루션 U-Net 을 사용한 간 영역 분할
Liver Segmentation using Multi-dilated U-Net
- 신하 쉬르티카 (전북대학교 컴퓨터공학부) ;
- 오강한 (전북대학교 컴퓨터공학부) ;
- 파티마 보드 (전북대학교 의과대학 핵의학교실 및 전북대학교병원 핵의학과) ;
- 정환정 (전북대학교 의과대학 핵의학교실 및 전북대학교병원 핵의학과) ;
- 오일석 (전북대학교 컴퓨터공학부)
- Sinha, Shrutika (Dept. of Computer Science and Engineering, Jeonbuk National University) ;
- Oh, Kanghan (Dept. of Computer Science and Engineering, Jeonbuk National University) ;
- Boud, Fatima (Department of Nuclear Medicine, Molecular Imaging & Therapeutic Medicine Research Center, Biomedical Research Institute, Jeonbuk National University Medical School and Hospital) ;
- Jeong, Hwan-Jeong (Department of Nuclear Medicine, Molecular Imaging & Therapeutic Medicine Research Center, Biomedical Research Institute, Jeonbuk National University Medical School and Hospital) ;
- Oh, Il-Seok (Dept. of Computer Science and Engineering, Jeonbuk National University)
- 발행 : 2020.11.05
초록
This paper proposes a novel automated liver segmentation using Multi-Dilated U-Nets. The proposed multidilation segmentation model has the advantage of considering both local and global shapes of the liver image. We use the CT images subject-wise, every 2D image is concatenated to 3D to calculate the IOU score and DICE score. The experimental results on Jeonbuk National University hospital dataset achieves better performance than the conventional U-Net.
키워드