An effective CNN approach for vertebrae segmentation from 3D CT images

Chan Pang Kuok, Jin Yuan Hsue, Ting Li Shen, Bing Feng Huang, Chi Yeh Chen, Yung Nien Sun

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

1 Citation (Scopus)

Abstract

Spine surgery is risky when treating spinal diseases or injuries. In order to decrease the damage of tissue and accelerate the recovery, minimally invasive surgery is strongly desired. Because of this, the preoperative planning and intraoperative guidance become very important. A 3D vertebrae model of the surgical site will be built for these purposes from the computer tomography (CT) images. The segmentation methods of vertebrae from the CT images for modeling are widely concerned. The conventional methods were satisfactory but they usually required prior knowledge of the vertebrae. Recently, the deep learning convolutional neural network (CNN) showed an outstanding performance on the end-to-end semantic image segmentation. Benefit from this, we propose an effective and simple convolution neural network based approach for vertebrae segmentation. Different from training and testing on large 3D data, the axial view images are used effectively in this study. A sequence of simple image processing steps are applied for the intervertebral plane detection. Five CT cases are used on this study and the segmentation results are highly accurate with average dice similarity coefficient over 0.95.

Original languageEnglish
Title of host publicationProceedings of the 2018 Pacific Neighborhood Consortium Annual Conference and Joint Meetings
Subtitle of host publicationHuman Rights in Cyberspace, PNC 2018
EditorsShih-Lung Shaw, Ta-Chien Chan, Ling-Jyh Chen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages7-12
Number of pages6
ISBN (Electronic)9789869531719
DOIs
Publication statusPublished - 2018 Dec 14
Event2018 Pacific Neighborhood Consortium Annual Conference and Joint Meetings, PNC 2018 - San Francisco, United States
Duration: 2018 Oct 272018 Oct 30

Other

Other2018 Pacific Neighborhood Consortium Annual Conference and Joint Meetings, PNC 2018
CountryUnited States
CitySan Francisco
Period18-10-2718-10-30

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Information Systems and Management
  • Archaeology
  • Computer Networks and Communications
  • Sociology and Political Science
  • Public Administration

Fingerprint Dive into the research topics of 'An effective CNN approach for vertebrae segmentation from 3D CT images'. Together they form a unique fingerprint.

Cite this