A preliminary PET radiomics study of brain metastases using a fully automatic segmentation method

Abstract Background Positron Emission Tomography (PET) is increasingly utilized in radiomics studies for treatment evaluation purposes. Nevertheless, lesion volume identification in PET images is a critical and still challenging step in the process of radiomics, due to the low spatial resolution and...

Full description

Bibliographic Details
Main Authors: Alessandro Stefano, Albert Comelli, Valentina Bravatà, Stefano Barone, Igor Daskalovski, Gaetano Savoca, Maria Gabriella Sabini, Massimo Ippolito, Giorgio Russo
Format: Article
Language:English
Published: BMC 2020-09-01
Series:BMC Bioinformatics
Subjects:
Online Access:http://link.springer.com/article/10.1186/s12859-020-03647-7
id doaj-3c0c25b5466040a4ad51374a75d9eb8d
record_format Article
spelling doaj-3c0c25b5466040a4ad51374a75d9eb8d2020-11-25T03:55:01ZengBMCBMC Bioinformatics1471-21052020-09-0121S811410.1186/s12859-020-03647-7A preliminary PET radiomics study of brain metastases using a fully automatic segmentation methodAlessandro Stefano0Albert Comelli1Valentina Bravatà2Stefano Barone3Igor Daskalovski4Gaetano Savoca5Maria Gabriella Sabini6Massimo Ippolito7Giorgio Russo8Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR)Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR)Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR)University of PalermoDepartment of Physics and Astronomy, University of CataniaInstitute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR)Medical Physics Unit, Cannizzaro HospitalNuclear Medicine Department, Cannizzaro HospitalInstitute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR)Abstract Background Positron Emission Tomography (PET) is increasingly utilized in radiomics studies for treatment evaluation purposes. Nevertheless, lesion volume identification in PET images is a critical and still challenging step in the process of radiomics, due to the low spatial resolution and high noise level of PET images. Currently, the biological target volume (BTV) is manually contoured by nuclear physicians, with a time expensive and operator-dependent procedure. This study aims to obtain BTVs from cerebral metastases in patients who underwent L-[11C]methionine (11C-MET) PET, using a fully automatic procedure and to use these BTVs to extract radiomics features to stratify between patients who respond to treatment or not. For these purposes, 31 brain metastases, for predictive evaluation, and 25 ones, for follow-up evaluation after treatment, were delineated using the proposed method. Successively, 11C-MET PET studies and related volumetric segmentations were used to extract 108 features to investigate the potential application of radiomics analysis in patients with brain metastases. A novel statistical system has been implemented for feature reduction and selection, while discriminant analysis was used as a method for feature classification. Results For predictive evaluation, 3 features (asphericity, low-intensity run emphasis, and complexity) were able to discriminate between responder and non-responder patients, after feature reduction and selection. Best performance in patient discrimination was obtained using the combination of the three selected features (sensitivity 81.23%, specificity 73.97%, and accuracy 78.27%) compared to the use of all features. Secondly, for follow-up evaluation, 8 features (SUVmean, SULpeak, SUVmin, SULpeak prod-surface-area, SUVmean prod-sphericity, surface mean SUV 3, SULpeak prod-sphericity, and second angular moment) were selected with optimal performance in discriminant analysis classification (sensitivity 86.28%, specificity 87.75%, and accuracy 86.57%) outperforming the use of all features. Conclusions The proposed system is able i) to extract 108 features for each automatically segmented lesion and ii) to select a sub-panel of 11C-MET PET features (3 and 8 in the case of predictive and follow-up evaluation), with valuable association with patient outcome. We believe that our model can be useful to improve treatment response and prognosis evaluation, potentially allowing the personalization of cancer treatment plans.http://link.springer.com/article/10.1186/s12859-020-03647-7CancerActive contourPositron emission tomographyBiological target volumeRadiomics
collection DOAJ
language English
format Article
sources DOAJ
author Alessandro Stefano
Albert Comelli
Valentina Bravatà
Stefano Barone
Igor Daskalovski
Gaetano Savoca
Maria Gabriella Sabini
Massimo Ippolito
Giorgio Russo
spellingShingle Alessandro Stefano
Albert Comelli
Valentina Bravatà
Stefano Barone
Igor Daskalovski
Gaetano Savoca
Maria Gabriella Sabini
Massimo Ippolito
Giorgio Russo
A preliminary PET radiomics study of brain metastases using a fully automatic segmentation method
BMC Bioinformatics
Cancer
Active contour
Positron emission tomography
Biological target volume
Radiomics
author_facet Alessandro Stefano
Albert Comelli
Valentina Bravatà
Stefano Barone
Igor Daskalovski
Gaetano Savoca
Maria Gabriella Sabini
Massimo Ippolito
Giorgio Russo
author_sort Alessandro Stefano
title A preliminary PET radiomics study of brain metastases using a fully automatic segmentation method
title_short A preliminary PET radiomics study of brain metastases using a fully automatic segmentation method
title_full A preliminary PET radiomics study of brain metastases using a fully automatic segmentation method
title_fullStr A preliminary PET radiomics study of brain metastases using a fully automatic segmentation method
title_full_unstemmed A preliminary PET radiomics study of brain metastases using a fully automatic segmentation method
title_sort preliminary pet radiomics study of brain metastases using a fully automatic segmentation method
publisher BMC
series BMC Bioinformatics
issn 1471-2105
publishDate 2020-09-01
description Abstract Background Positron Emission Tomography (PET) is increasingly utilized in radiomics studies for treatment evaluation purposes. Nevertheless, lesion volume identification in PET images is a critical and still challenging step in the process of radiomics, due to the low spatial resolution and high noise level of PET images. Currently, the biological target volume (BTV) is manually contoured by nuclear physicians, with a time expensive and operator-dependent procedure. This study aims to obtain BTVs from cerebral metastases in patients who underwent L-[11C]methionine (11C-MET) PET, using a fully automatic procedure and to use these BTVs to extract radiomics features to stratify between patients who respond to treatment or not. For these purposes, 31 brain metastases, for predictive evaluation, and 25 ones, for follow-up evaluation after treatment, were delineated using the proposed method. Successively, 11C-MET PET studies and related volumetric segmentations were used to extract 108 features to investigate the potential application of radiomics analysis in patients with brain metastases. A novel statistical system has been implemented for feature reduction and selection, while discriminant analysis was used as a method for feature classification. Results For predictive evaluation, 3 features (asphericity, low-intensity run emphasis, and complexity) were able to discriminate between responder and non-responder patients, after feature reduction and selection. Best performance in patient discrimination was obtained using the combination of the three selected features (sensitivity 81.23%, specificity 73.97%, and accuracy 78.27%) compared to the use of all features. Secondly, for follow-up evaluation, 8 features (SUVmean, SULpeak, SUVmin, SULpeak prod-surface-area, SUVmean prod-sphericity, surface mean SUV 3, SULpeak prod-sphericity, and second angular moment) were selected with optimal performance in discriminant analysis classification (sensitivity 86.28%, specificity 87.75%, and accuracy 86.57%) outperforming the use of all features. Conclusions The proposed system is able i) to extract 108 features for each automatically segmented lesion and ii) to select a sub-panel of 11C-MET PET features (3 and 8 in the case of predictive and follow-up evaluation), with valuable association with patient outcome. We believe that our model can be useful to improve treatment response and prognosis evaluation, potentially allowing the personalization of cancer treatment plans.
topic Cancer
Active contour
Positron emission tomography
Biological target volume
Radiomics
url http://link.springer.com/article/10.1186/s12859-020-03647-7
work_keys_str_mv AT alessandrostefano apreliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT albertcomelli apreliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT valentinabravata apreliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT stefanobarone apreliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT igordaskalovski apreliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT gaetanosavoca apreliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT mariagabriellasabini apreliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT massimoippolito apreliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT giorgiorusso apreliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT alessandrostefano preliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT albertcomelli preliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT valentinabravata preliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT stefanobarone preliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT igordaskalovski preliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT gaetanosavoca preliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT mariagabriellasabini preliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT massimoippolito preliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
AT giorgiorusso preliminarypetradiomicsstudyofbrainmetastasesusingafullyautomaticsegmentationmethod
_version_ 1724471213149913088