In this paper we explore the application of anomaly detection techniques to tumor voxels segmentation. The developed algorithms work on 3-points dynamic FDG-PET acquisitions and leverage on the peculiar anaerobic metabolism that cancer cells experience over time. A few different global or local anomaly detectors are discussed, together with an investigation over two different algorithms aiming to estimate normal tissues' statistical distribution. Finally, all the proposed algorithms are tested on a dataset composed of 9 patients proving that anomaly detectors are able to outperform techniques in the state of the art.

Global and local anomaly detectors for tumor segmentation in dynamic pet acquisitions

VERDOJA, FRANCESCO;BONAFE', BARBARA;CAVAGNINO, Davide;GRANGETTO, Marco;
2016

Abstract

In this paper we explore the application of anomaly detection techniques to tumor voxels segmentation. The developed algorithms work on 3-points dynamic FDG-PET acquisitions and leverage on the peculiar anaerobic metabolism that cancer cells experience over time. A few different global or local anomaly detectors are discussed, together with an investigation over two different algorithms aiming to estimate normal tissues' statistical distribution. Finally, all the proposed algorithms are tested on a dataset composed of 9 patients proving that anomaly detectors are able to outperform techniques in the state of the art.
2016 IEEE International Conference on Image Processing (ICIP)
Phoenix, AZ
25-28 Sept. 2016
2016 IEEE International Conference on Image Processing (ICIP)
IEEE
4131
4135
978-1-4673-9961-6
978-1-4673-9961-6
Verdoja, F.; Bonafe, B.; Cavagnino, D.; Grangetto, M.; Bracco, C.; Varetto, T.; Racca, M.; Stasi, M.
File in questo prodotto:
File Dimensione Formato  
ArticleTumors2016_IRIS.pdf

Accesso riservato

Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 1.19 MB
Formato Adobe PDF
1.19 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Cavagnino_07533137.pdf

Accesso riservato

Tipo di file: PDF EDITORIALE
Dimensione 711.97 kB
Formato Adobe PDF
711.97 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

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: https://hdl.handle.net/2318/1610112
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact