Active contour algorithm with discriminant analysis for delineating tumors in positron emission tomography

Stefano Barone, Albert Comelli, Maria Gabriella Sabini, Anthony Yezzi, Alessandro Stefano, Giorgio Russo, Massimo Ippolito, Samuel Bignardi, Albert Comelli

Risultato della ricerca: Article

1 Citazione (Scopus)

Abstract

In the context of cancer delineation using positron emission tomography datasets, we present an innovative approach which purpose is to tackle the real-time, three-dimensional segmentation task in a full, or at least nearly full automatized way. The approach comprises a preliminary initialization phase where the user highlights a region of interest around the cancer on just one slice of the tomographic dataset. The algorithm takes care of identifying an optimal and user-independent region of interest around the anomalous tissue and located on the slice containing the highest standardized uptake value so to start the successive segmentation task. The three-dimensional volume is then reconstructed using a slice-by-slice marching approach until a suitable automatic stop condition is met. On each slice, the segmentation is performed using an enhanced local active contour based on the minimization of a novel energy functional which combines the information provided by a machine learning component, the discriminant analysis in the present study. As a result, the whole algorithm is almost completely automatic and the output segmentation is independent from the input provided by the user. Phantom experiments comprising spheres and zeolites, and clinical cases comprising various body districts (lung, brain, and head and neck), and two different radio-tracers (18 F-fluoro-2-deoxy-D-glucose, and 11C-labeled Methionine) were used to assess the algorithm performances. Phantom experiments with spheres and with zeolites showed a dice similarity coefficient above 90% and 80%, respectively. Clinical cases showed high agreement with the gold standard (R2 = 0.98). These results indicate that the proposed method can be efficiently applied in the clinical routine with potential benefit for the treatment response assessment, and targeting in radiotherapy.
Lingua originaleEnglish
pagine (da-a)67-78
Numero di pagine12
RivistaArtificial Intelligence in Medicine
Volume94
Stato di pubblicazionePublished - 2019

All Science Journal Classification (ASJC) codes

  • Medicine (miscellaneous)
  • Artificial Intelligence

Cita questo

Active contour algorithm with discriminant analysis for delineating tumors in positron emission tomography. / Barone, Stefano; Comelli, Albert; Sabini, Maria Gabriella; Yezzi, Anthony; Stefano, Alessandro; Russo, Giorgio; Ippolito, Massimo; Bignardi, Samuel; Comelli, Albert.

In: Artificial Intelligence in Medicine, Vol. 94, 2019, pag. 67-78.

Risultato della ricerca: Article

Barone, S, Comelli, A, Sabini, MG, Yezzi, A, Stefano, A, Russo, G, Ippolito, M, Bignardi, S & Comelli, A 2019, 'Active contour algorithm with discriminant analysis for delineating tumors in positron emission tomography' Artificial Intelligence in Medicine, vol. 94, pagg. 67-78.
Barone, Stefano ; Comelli, Albert ; Sabini, Maria Gabriella ; Yezzi, Anthony ; Stefano, Alessandro ; Russo, Giorgio ; Ippolito, Massimo ; Bignardi, Samuel ; Comelli, Albert. / Active contour algorithm with discriminant analysis for delineating tumors in positron emission tomography. In: Artificial Intelligence in Medicine. 2019 ; Vol. 94. pagg. 67-78.
@article{abb75d12da5e43a09d5ea6c294d4b42f,
title = "Active contour algorithm with discriminant analysis for delineating tumors in positron emission tomography",
abstract = "In the context of cancer delineation using positron emission tomography datasets, we present an innovative approach which purpose is to tackle the real-time, three-dimensional segmentation task in a full, or at least nearly full automatized way. The approach comprises a preliminary initialization phase where the user highlights a region of interest around the cancer on just one slice of the tomographic dataset. The algorithm takes care of identifying an optimal and user-independent region of interest around the anomalous tissue and located on the slice containing the highest standardized uptake value so to start the successive segmentation task. The three-dimensional volume is then reconstructed using a slice-by-slice marching approach until a suitable automatic stop condition is met. On each slice, the segmentation is performed using an enhanced local active contour based on the minimization of a novel energy functional which combines the information provided by a machine learning component, the discriminant analysis in the present study. As a result, the whole algorithm is almost completely automatic and the output segmentation is independent from the input provided by the user. Phantom experiments comprising spheres and zeolites, and clinical cases comprising various body districts (lung, brain, and head and neck), and two different radio-tracers (18 F-fluoro-2-deoxy-D-glucose, and 11C-labeled Methionine) were used to assess the algorithm performances. Phantom experiments with spheres and with zeolites showed a dice similarity coefficient above 90{\%} and 80{\%}, respectively. Clinical cases showed high agreement with the gold standard (R2 = 0.98). These results indicate that the proposed method can be efficiently applied in the clinical routine with potential benefit for the treatment response assessment, and targeting in radiotherapy.",
keywords = "Active contour algorithm; Biological target volume segmentation; Discriminant analysis; Positron emission tomography; Medicine (miscellaneous); Artificial Intelligence",
author = "Stefano Barone and Albert Comelli",
year = "2019",
language = "English",
volume = "94",
pages = "67--78",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",

}

TY - JOUR

T1 - Active contour algorithm with discriminant analysis for delineating tumors in positron emission tomography

AU - Barone, Stefano

AU - Comelli, Albert

AU - Sabini, Maria Gabriella

AU - Yezzi, Anthony

AU - Stefano, Alessandro

AU - Russo, Giorgio

AU - Ippolito, Massimo

AU - Bignardi, Samuel

AU - Comelli, Albert

PY - 2019

Y1 - 2019

N2 - In the context of cancer delineation using positron emission tomography datasets, we present an innovative approach which purpose is to tackle the real-time, three-dimensional segmentation task in a full, or at least nearly full automatized way. The approach comprises a preliminary initialization phase where the user highlights a region of interest around the cancer on just one slice of the tomographic dataset. The algorithm takes care of identifying an optimal and user-independent region of interest around the anomalous tissue and located on the slice containing the highest standardized uptake value so to start the successive segmentation task. The three-dimensional volume is then reconstructed using a slice-by-slice marching approach until a suitable automatic stop condition is met. On each slice, the segmentation is performed using an enhanced local active contour based on the minimization of a novel energy functional which combines the information provided by a machine learning component, the discriminant analysis in the present study. As a result, the whole algorithm is almost completely automatic and the output segmentation is independent from the input provided by the user. Phantom experiments comprising spheres and zeolites, and clinical cases comprising various body districts (lung, brain, and head and neck), and two different radio-tracers (18 F-fluoro-2-deoxy-D-glucose, and 11C-labeled Methionine) were used to assess the algorithm performances. Phantom experiments with spheres and with zeolites showed a dice similarity coefficient above 90% and 80%, respectively. Clinical cases showed high agreement with the gold standard (R2 = 0.98). These results indicate that the proposed method can be efficiently applied in the clinical routine with potential benefit for the treatment response assessment, and targeting in radiotherapy.

AB - In the context of cancer delineation using positron emission tomography datasets, we present an innovative approach which purpose is to tackle the real-time, three-dimensional segmentation task in a full, or at least nearly full automatized way. The approach comprises a preliminary initialization phase where the user highlights a region of interest around the cancer on just one slice of the tomographic dataset. The algorithm takes care of identifying an optimal and user-independent region of interest around the anomalous tissue and located on the slice containing the highest standardized uptake value so to start the successive segmentation task. The three-dimensional volume is then reconstructed using a slice-by-slice marching approach until a suitable automatic stop condition is met. On each slice, the segmentation is performed using an enhanced local active contour based on the minimization of a novel energy functional which combines the information provided by a machine learning component, the discriminant analysis in the present study. As a result, the whole algorithm is almost completely automatic and the output segmentation is independent from the input provided by the user. Phantom experiments comprising spheres and zeolites, and clinical cases comprising various body districts (lung, brain, and head and neck), and two different radio-tracers (18 F-fluoro-2-deoxy-D-glucose, and 11C-labeled Methionine) were used to assess the algorithm performances. Phantom experiments with spheres and with zeolites showed a dice similarity coefficient above 90% and 80%, respectively. Clinical cases showed high agreement with the gold standard (R2 = 0.98). These results indicate that the proposed method can be efficiently applied in the clinical routine with potential benefit for the treatment response assessment, and targeting in radiotherapy.

KW - Active contour algorithm; Biological target volume segmentation; Discriminant analysis; Positron emission tomography; Medicine (miscellaneous); Artificial Intelligence

UR - http://hdl.handle.net/10447/339184

UR - http://www.elsevier.com/locate/artmed

M3 - Article

VL - 94

SP - 67

EP - 78

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

ER -