Skip to Main content Skip to Navigation
Conference papers

Spectral Clustering of Time-Intensity Signals: Application to Dynamic Contrast-Enhanced MR Images Segmentation

Abstract : In this paper, we propose to apply a spectral clustering approach to analyse dynamic contrast-enhance magnetic resonance (DCE-MR) time-intensity signals. This graph theory-based method allows for grouping of signals after space transformation. Grouped signals are then used to segment their related voxels. The number of clusters is automatically selected by maximizing the normalized modularity criterion. We have performed experiments with simulated data generated via pharmacokinetic modelling in order to demonstrate the feasibility and applicability of this kind of unsupervised approach.
Document type :
Conference papers
Complete list of metadatas

https://www.hal.inserm.fr/inserm-01154783
Contributor : Frédérique Frouin <>
Submitted on : Saturday, May 23, 2015 - 11:56:11 AM
Last modification on : Tuesday, July 3, 2018 - 11:43:20 AM
Long-term archiving on: : Thursday, April 20, 2017 - 8:00:35 AM

File

ACTES-RITS2015-HAL-p116-7.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

  • HAL Id : inserm-01154783, version 1

Collections

Citation

Guillaume Tartare, Denis Hamad, Mustapha Azahaf, Philippe Puech, Nacim Betrouni. Spectral Clustering of Time-Intensity Signals: Application to Dynamic Contrast-Enhanced MR Images Segmentation. Journées RITS 2015, Mar 2015, Dourdan, France. pp 116-117. ⟨inserm-01154783⟩

Share

Metrics

Record views

154

Files downloads

95