Download PDFOpen PDF in browser

FCN Based Approach for the Automatic Segmentation of Bone Surfaces in Ultrasound Images

4 pagesPublished: July 12, 2018

Abstract

In CAOS, ultrasound imaging has been proposed as a solution for obtaining the specific bone morphology of the patient, avoiding limitations of existing technologies. However, this imaging modality presents different drawbacks that make difficult the automatic bone segmentation. A new algorithm, based on Fully Convolutional Networks (FCN), is proposed. The aim of this paper is to compare and validate this method with (1) a manual segmentation that was performed by three independent experts, and (2) a state of the art method called Confidence in Phase Symmetry (CPS). The FCN based approach outperforms the CPS algorithm and the RMSE is close to the manual segmentation variability.

Keyphrases: bone, computer assisted orthopedic surgery., fully conventional network, segmentation, ultrasound

In: Wei Tian and Ferdinando Rodriguez Y Baena (editors). CAOS 2018. The 18th Annual Meeting of the International Society for Computer Assisted Orthopaedic Surgery, vol 2, pages 227-230.

BibTeX entry
@inproceedings{CAOS2018:FCN_Based_Approach_Automatic,
  author    = {Mateo Villa and Guillaume Dardenne and Maged Nasan and Hoel Letissier and Chafiaa Hamitouche and Eric Stindel},
  title     = {FCN Based Approach for the Automatic Segmentation of Bone Surfaces in Ultrasound Images},
  booktitle = {CAOS 2018. The 18th Annual Meeting of the International Society for Computer Assisted Orthopaedic Surgery},
  editor    = {Wei Tian and Ferdinando Rodriguez Y Baena},
  series    = {EPiC Series in Health Sciences},
  volume    = {2},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-5305},
  url       = {/publications/paper/3kLg},
  doi       = {10.29007/bncb},
  pages     = {227-230},
  year      = {2018}}
Download PDFOpen PDF in browser