Automatic method for tumor segmentation from 3-points dynamic PET acquisitions

Francesco Verdoja; Marco Grangetto; Christian Bracco; Teresio Varetto; Manuela Racca; Michele Stasi

doi:10.1109/ICIP.2014.7025188

Automatic method for tumor segmentation from 3-points dynamic PET acquisitions

Francesco Verdoja, Marco Grangetto, Christian Bracco, Teresio Varetto, Manuela Racca, Michele Stasi

Istituto Oncologico Candiolo

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper a novel technique to segment tumor voxels in dynamic positron emission tomography (PET) scans is proposed. An innovative anomaly detection tool tailored for 3-points dynamic PET scans is designed. The algorithm allows the identification of tumoral cells in dynamic FDG-PET scans thanks to their peculiar anaerobic metabolism experienced over time. The proposed tool is preliminarily tested on a small dataset showing promising performance as compared to the state of the art in terms of both accuracy and classification errors.

Original language	English
Title of host publication	2014 IEEE International Conference on Image Processing, ICIP 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	937-941
Number of pages	5
ISBN (Print)	9781479957514
DOIs	https://doi.org/10.1109/ICIP.2014.7025188
Publication status	Published - Jan 28 2014

Keywords

anomaly detection
image segmentation
Medical diagnostic imaging
positron emission tomography
tumors

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Access to Document

10.1109/ICIP.2014.7025188

Cite this

Automatic method for tumor segmentation from 3-points dynamic PET acquisitions. / Verdoja, Francesco; Grangetto, Marco; Bracco, Christian; Varetto, Teresio; Racca, Manuela; Stasi, Michele.

2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 937-941 7025188.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

@inproceedings{bd35ea0b40324a9d9efedc6fef52f4b0,

title = "Automatic method for tumor segmentation from 3-points dynamic PET acquisitions",

abstract = "In this paper a novel technique to segment tumor voxels in dynamic positron emission tomography (PET) scans is proposed. An innovative anomaly detection tool tailored for 3-points dynamic PET scans is designed. The algorithm allows the identification of tumoral cells in dynamic FDG-PET scans thanks to their peculiar anaerobic metabolism experienced over time. The proposed tool is preliminarily tested on a small dataset showing promising performance as compared to the state of the art in terms of both accuracy and classification errors.",

keywords = "anomaly detection, image segmentation, Medical diagnostic imaging, positron emission tomography, tumors",

author = "Francesco Verdoja and Marco Grangetto and Christian Bracco and Teresio Varetto and Manuela Racca and Michele Stasi",

year = "2014",

month = jan,

day = "28",

doi = "10.1109/ICIP.2014.7025188",

language = "English",

isbn = "9781479957514",

pages = "937--941",

booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Automatic method for tumor segmentation from 3-points dynamic PET acquisitions

AU - Verdoja, Francesco

AU - Grangetto, Marco

AU - Bracco, Christian

AU - Varetto, Teresio

AU - Racca, Manuela

AU - Stasi, Michele

PY - 2014/1/28

Y1 - 2014/1/28

N2 - In this paper a novel technique to segment tumor voxels in dynamic positron emission tomography (PET) scans is proposed. An innovative anomaly detection tool tailored for 3-points dynamic PET scans is designed. The algorithm allows the identification of tumoral cells in dynamic FDG-PET scans thanks to their peculiar anaerobic metabolism experienced over time. The proposed tool is preliminarily tested on a small dataset showing promising performance as compared to the state of the art in terms of both accuracy and classification errors.

AB - In this paper a novel technique to segment tumor voxels in dynamic positron emission tomography (PET) scans is proposed. An innovative anomaly detection tool tailored for 3-points dynamic PET scans is designed. The algorithm allows the identification of tumoral cells in dynamic FDG-PET scans thanks to their peculiar anaerobic metabolism experienced over time. The proposed tool is preliminarily tested on a small dataset showing promising performance as compared to the state of the art in terms of both accuracy and classification errors.

KW - anomaly detection

KW - image segmentation

KW - Medical diagnostic imaging

KW - positron emission tomography

KW - tumors

UR - http://www.scopus.com/inward/record.url?scp=84949926795&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949926795&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2014.7025188

DO - 10.1109/ICIP.2014.7025188

M3 - Conference contribution

AN - SCOPUS:84949926795

SN - 9781479957514

SP - 937

EP - 941

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Automatic method for tumor segmentation from 3-points dynamic PET acquisitions

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this