Crossing-preserving multi-scale vesselness

J. Hannink, R. Duits, E.J. Bekkers

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

11 Citations (Scopus)

Abstract

The multi–scale Frangi vesselness filter is an established tool in (retinal) vascular imaging. However, it cannot properly cope with crossings or bifurcations since it only looks for elongated structures. Therefore, we disentangle crossings/bifurcations via (multiple scale) invertible orientation scores and apply vesselness filters in this domain. This new method via scale–orientation scores performs considerably better at enhancing vessels throughout crossings and bifurcations than the Frangi version. Both methods are evaluated on a public dataset. Performance is measured by comparing ground truth data to the segmentation results obtained by basic thresholding and morphological component analysis of the filtered images. Keywords: Multi-scale vesselness filters; continuous wavelet transforms; line detection; gauge frames; retinal imaging
Original languageEnglish
Title of host publicationMedical Image Computing and Computer-Assisted Intervention – MICCAI 2014 (17th International Conference, Boston, MA, USA, September 14-18, 2014, Proceedings, Part II)
EditorsP. Golland, N. Hata, C. Barillot, J. Hornegger, R. Howe
Place of PublicationCham
PublisherSpringer
Pages603-610
ISBN (Print)978-3-319-10469-0
DOIs
Publication statusPublished - 2014
Event17th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2014), September 14-18, 2014, Boston, MA, USA - Boston, MA, United States
Duration: 14 Sep 201418 Sep 2014

Publication series

NameLecture Notes in Computer Science
Volume8674
ISSN (Print)0302-9743

Conference

Conference17th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2014), September 14-18, 2014, Boston, MA, USA
Abbreviated titleMICCAI 2014
CountryUnited States
CityBoston, MA
Period14/09/1418/09/14

    Fingerprint

Cite this

Hannink, J., Duits, R., & Bekkers, E. J. (2014). Crossing-preserving multi-scale vesselness. In P. Golland, N. Hata, C. Barillot, J. Hornegger, & R. Howe (Eds.), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014 (17th International Conference, Boston, MA, USA, September 14-18, 2014, Proceedings, Part II) (pp. 603-610). (Lecture Notes in Computer Science; Vol. 8674). Cham: Springer. https://doi.org/10.1007/978-3-319-10470-6_75