Segmentation semi-automatique de tumeurs du foie en TDM dynamique pour l'estimation du taux de nécrose

Abstract : Pre-operative locoregional treatments (PLT) delay the tumor progression by necrosis for patients with hepato-cellular carcinoma (HCC). To accurately assess the PLT response, we address the estimation of liver tumor necrosis (TN) from dynamic contrast-enhanced CT scans. To overcome inter-expert variability induced by visual qualitative assessment, we propose a semi-automatic method that requires weak interaction efforts to segment parenchyma, tumoral active and necrotic tissues. It applies random decision forests on semantic regions and involves robust multi-phase cluster-based features. Quantitative results confirms the benefits of exploiting dynamic cluster-based information.
Document type :
Conference papers
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01214068
Contributor : Pierre-Henri Conze <>
Submitted on : Friday, October 9, 2015 - 4:33:56 PM
Last modification on : Thursday, October 17, 2019 - 12:35:31 PM
Long-term archiving on : Sunday, January 10, 2016 - 10:34:15 AM

File

main_gretsi15.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01214068, version 1

Citation

Pierre-Henri Conze, François Rousseau, Vincent Noblet, Fabrice Heitz, Riccardo Memeo, et al.. Segmentation semi-automatique de tumeurs du foie en TDM dynamique pour l'estimation du taux de nécrose. Colloque GRETSI Traitement du Signal & des Images, GRETSI 2015, Sep 2015, Lyon, France. ⟨hal-01214068⟩

Share

Metrics

Record views

274

Files downloads

661