A cascaded two-step approach for segmentation of thoracic organs

S. Kim, Y. Jang, K. Han, H. Shim, H. J. Chang

Research output: Contribution to journalConference articlepeer-review

7 Citations (Scopus)


Segmentation of thoracic organ is a challenging task as demonstrated by the SegTHOR challenge. In this paper, we present an efficient yet simple framework for automatic thoracic organ segmentation. Two steps are included: first, we designed a simple network to define the ROI of the input volume. Second, we propose a network based on the encoder and decoder model. Three orthogonal views are fed into the network, respectively. To do the final segmentation, we used ensemble by majority voting. The experiments show that our approach is comparable with other segmentation networks.

Original languageEnglish
JournalCEUR Workshop Proceedings
Publication statusPublished - 2019
Event2019 SegTHOR Challenge: Segmentation of THoracic Organs at Risk in CT Images, SegTHOR 2019 - Venice, Italy
Duration: 2019 Apr 10 → …

Bibliographical note

Publisher Copyright:
© 2019 CEUR-WS. All rights reserved.

All Science Journal Classification (ASJC) codes

  • Computer Science(all)


Dive into the research topics of 'A cascaded two-step approach for segmentation of thoracic organs'. Together they form a unique fingerprint.

Cite this