Two novel and innovative segmentation algorithms are presented, for liver metastases and necrotic tissues in pre- and post-ablation, respectively. Both are based on Gaussian Mixture Model (GMM), adapted to include healthy liver knowledge and proximity information. Preliminary validation results on 20 patients and 42 lesions are discussed showing high accuracy versus manual segmentation gold standard outperforming simpler GMM and thresholding methods.

Pre and Post Liver Lesion Thermal ablation FDG-PET: background driven GMM segmentation

MOCCIA, SARA;SOFFIENTINI, CHIARA DOLORES;BASELLI, GIUSEPPE;
2015

Abstract

Two novel and innovative segmentation algorithms are presented, for liver metastases and necrotic tissues in pre- and post-ablation, respectively. Both are based on Gaussian Mixture Model (GMM), adapted to include healthy liver knowledge and proximity information. Preliminary validation results on 20 patients and 42 lesions are discussed showing high accuracy versus manual segmentation gold standard outperforming simpler GMM and thresholding methods.
File in questo prodotto:
File Dimensione Formato  
embc.pdf

accesso aperto

: Publisher’s version
Dimensione 92.47 kB
Formato Adobe PDF
92.47 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11311/964653
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact