Abstract
Segmentation of organs at risk in CT volumes is a prerequisite for radiotherapy treatment planning. In this paper we focus on esophagus segmentation, a challenging problem since the walls of the esophagus have a very low contrast in CT images. Making use of Fully Convolutional Networks (FCN), we present several extensions that improve the performance, including a new architecture that allows to use low level features with high level information, effectively combining local and global information for improving the localization accuracy. Experiments demonstrate competitive performance on a dataset of 30 CT scans.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 2017 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2017 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 503-506 |
| Number of pages | 4 |
| ISBN (Electronic) | 9781509055593 |
| DOIs | |
| Publication status | Published - 2017 Jan 1 |
| Externally published | Yes |
| Event | 5th IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2017 - Kuching, Sarawak, Malaysia Duration: 2017 Sep 12 → 2017 Sep 14 |
Other
| Other | 5th IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2017 |
|---|---|
| Country | Malaysia |
| City | Kuching, Sarawak |
| Period | 17/9/12 → 17/9/14 |
Fingerprint
ASJC Scopus subject areas
- Computer Science Applications
- Computer Vision and Pattern Recognition
- Signal Processing
Cite this
Fully automated esophagus segmentation with a hierarchical deep learning approach. / Trullo, Roger; Petitjean, Caroline; Nie, Dong; Shen, Dinggang; Ruan, Su.
Proceedings of the 2017 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 503-506.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Fully automated esophagus segmentation with a hierarchical deep learning approach
AU - Trullo, Roger
AU - Petitjean, Caroline
AU - Nie, Dong
AU - Shen, Dinggang
AU - Ruan, Su
PY - 2017/1/1
Y1 - 2017/1/1
N2 - Segmentation of organs at risk in CT volumes is a prerequisite for radiotherapy treatment planning. In this paper we focus on esophagus segmentation, a challenging problem since the walls of the esophagus have a very low contrast in CT images. Making use of Fully Convolutional Networks (FCN), we present several extensions that improve the performance, including a new architecture that allows to use low level features with high level information, effectively combining local and global information for improving the localization accuracy. Experiments demonstrate competitive performance on a dataset of 30 CT scans.
AB - Segmentation of organs at risk in CT volumes is a prerequisite for radiotherapy treatment planning. In this paper we focus on esophagus segmentation, a challenging problem since the walls of the esophagus have a very low contrast in CT images. Making use of Fully Convolutional Networks (FCN), we present several extensions that improve the performance, including a new architecture that allows to use low level features with high level information, effectively combining local and global information for improving the localization accuracy. Experiments demonstrate competitive performance on a dataset of 30 CT scans.
UR - http://www.scopus.com/inward/record.url?scp=85041387177&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85041387177&partnerID=8YFLogxK
U2 - 10.1109/ICSIPA.2017.8120664
DO - 10.1109/ICSIPA.2017.8120664
M3 - Conference contribution
AN - SCOPUS:85041387177
SP - 503
EP - 506
BT - Proceedings of the 2017 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2017
PB - Institute of Electrical and Electronics Engineers Inc.
ER -