Vascular network segmentation: an unsupervised approach

Abstract : Micro-tomography produces high resolution images of bio- logical structures such as vascular networks. In this paper, we present a new approach for segmenting vascular network into pathological and normal regions from considering their micro-vessel 3D structure only. We consider a partition of the volume obtained by a watershed algorithm based on the dis- tance from the nearest vessel. Each territory is characterized by its volume and the local vascular density. The volume and density maps are first regularized by minimizing the total vari- ation. Then, a new approach is proposed to segment the vol- ume from the two previous restored images based on hypoth- esis testing. Results are presented on 3D micro-tomographic images of the brain micro-vascular network.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/hal-00668140
Contributor : Xavier Descombes <>
Submitted on : Thursday, February 9, 2012 - 10:53:48 AM
Last modification on : Monday, November 4, 2019 - 5:52:05 PM

Identifiers

Citation

Xavier Descombes, Franck Plouraboué, A. El Boustani, Caroline Fonta, Geraldine Le Duc, et al.. Vascular network segmentation: an unsupervised approach. ISBI - International Symposium on Biomedical Imaging, May 2012, Barcelona, Spain. ⟨10.1109/ISBI.2012.6235788⟩. ⟨hal-00668140⟩

Share

Metrics

Record views

498