Fully automated esophagus segmentation with a hierarchical deep learning approach

Roger Trullo, Caroline Petitjean, Dong Nie, Dinggang Shen, Su Ruan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

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 languageEnglish
Title of host publicationProceedings of the 2017 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages503-506
Number of pages4
ISBN (Electronic)9781509055593
DOIs
Publication statusPublished - 2017 Jan 1
Externally publishedYes
Event5th IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2017 - Kuching, Sarawak, Malaysia
Duration: 2017 Sep 122017 Sep 14

Other

Other5th IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2017
CountryMalaysia
CityKuching, Sarawak
Period17/9/1217/9/14

Fingerprint

Computerized tomography
Radiotherapy
Planning
Experiments
Deep learning

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Trullo, R., Petitjean, C., Nie, D., Shen, D., & Ruan, S. (2017). Fully automated esophagus segmentation with a hierarchical deep learning approach. In Proceedings of the 2017 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2017 (pp. 503-506). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSIPA.2017.8120664

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 proceedingConference contribution

Trullo, R, Petitjean, C, Nie, D, Shen, D & Ruan, S 2017, Fully automated esophagus segmentation with a hierarchical deep learning approach. in Proceedings of the 2017 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2017. Institute of Electrical and Electronics Engineers Inc., pp. 503-506, 5th IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2017, Kuching, Sarawak, Malaysia, 17/9/12. https://doi.org/10.1109/ICSIPA.2017.8120664
Trullo R, Petitjean C, Nie D, Shen D, Ruan S. Fully automated esophagus segmentation with a hierarchical deep learning approach. In 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 https://doi.org/10.1109/ICSIPA.2017.8120664
Trullo, Roger ; Petitjean, Caroline ; Nie, Dong ; Shen, Dinggang ; Ruan, Su. / Fully automated esophagus segmentation with a hierarchical deep learning approach. Proceedings of the 2017 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 503-506
@inproceedings{8fca2f4d09314462855d7c35a666dd7b,
title = "Fully automated esophagus segmentation with a hierarchical deep learning approach",
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.",
author = "Roger Trullo and Caroline Petitjean and Dong Nie and Dinggang Shen and Su Ruan",
year = "2017",
month = "1",
day = "1",
doi = "10.1109/ICSIPA.2017.8120664",
language = "English",
pages = "503--506",
booktitle = "Proceedings of the 2017 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

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 -