Multicriteria 3D PET image segmentation

Francisco Javier Alvarez Padilla; Eloïse Grossiord; Barbara Romaniuk; Benoît Naegel; Camille Kurtz; Hugues Talbot; Laurent Najman; Romain Guillemot; Dimitri Papathanassiou; Nicolas Passat

doi:10.1109/IPTA.2015.7367162

Multicriteria 3D PET image segmentation

Francisco Javier Alvarez Padilla ^{1, 2} Eloïse Grossiord ^{3, 4} Barbara Romaniuk ¹ Benoît Naegel ² Camille Kurtz ⁵ Hugues Talbot ³ Laurent Najman ³ Romain Guillemot ¹ Dimitri Papathanassiou ^{1, 6} Nicolas Passat ¹

1 CRESTIC - Centre de Recherche en Sciences et Technologies de l'Information et de la Communication - EA 3804

2 ICube - Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie

3 LIGM - Laboratoire d'Informatique Gaspard-Monge

4 Keosys

5 LIPADE - EA 2517 - Laboratoire d'Informatique Paris Descartes

6 Institut Jean Godinot

Abstract : The analysis of images acquired with Positron Emission Tomography (PET) is challenging. In particular, there is no consensus on the best criterion to quantify the metabolic activity for lesion detection and segmentation purposes. Based on this consideration, we propose a versatile knowledge-based segmen-tation methodology for 3D PET imaging. In contrast to previous methods, an arbitrary number of quantitative criteria can be involved and the experts behaviour learned and reproduced in order to guide the segmentation process. The classification part of the scheme relies on example-based learning strategies, allowing interactive example definition and more generally incremental refinement. The image processing part relies on hierarchical segmentation, allowing vectorial attribute handling. Preliminary results on synthetic and real images confirm the relevance of this methodology, both as a segmentation approach and as an experimental framework for criteria evaluation.

Keywords : knowledge-based system example-based learning hierarchical segmentation Positron Emission Tomography

Document type :

Conference papers

Domain :

Computer Science [cs] / Image Processing

Computer Science [cs] / Medical Imaging

Liste complète des métadonnées

Cited literature [20 references] Display Hide Download

https://hal.archives-ouvertes.fr/hal-01616446
Contributor : Laurent Najman <>
Submitted on : Monday, October 16, 2017 - 9:11:08 PM
Last modification on : Thursday, April 11, 2019 - 4:02:18 PM
Document(s) archivé(s) le : Wednesday, January 17, 2018 - 12:19:11 PM

Alvarez Padilla IPTA 2015_VFin...

Files produced by the author(s)

Multicriteria 3D PET image segmentation

File

Identifiers

Collections

Citation

Export

Metrics

372

48

Contact

Multicriteria 3D PET image segmentation

File

Identifiers

Collections

Citation

Export

Share

Metrics

372

48

Contact