Choline PET/CT features to predict survival outcome in high-risk prostate cancer restaging: a preliminary machine-learning radiomics study.
Journal
The quarterly journal of nuclear medicine and molecular imaging : official publication of the Italian Association of Nuclear Medicine (AIMN) [and] the International Association of Radiopharmacology (IAR), [and] Section of the Society of...
ISSN: 1827-1936
Titre abrégé: Q J Nucl Med Mol Imaging
Pays: Italy
ID NLM: 101213861
Informations de publication
Date de publication:
Dec 2022
Dec 2022
Historique:
pubmed:
17
6
2020
medline:
18
11
2022
entrez:
17
6
2020
Statut:
ppublish
Résumé
Radiomic features are increasingly utilized to evaluate tumor heterogeneity in PET imaging but to date its role has not been investigated for Cho-PET in prostate cancer. The potential application of radiomics features analysis using a machine-learning radiomics algorithm was evaluated to select We retrospectively analyzed high-risk PCa patients who underwent restaging One hundred and six imaging features were extracted for 46 lesions for a total of 4876 features analyzed. No significant differences between the training and validating sets in terms of age, sex, PSA values, lesion location and size (P>0.05) were demonstrated by the machine-learning model. Thirteen features were able to discriminate FU disease status after NCA selection. Best performance in DA classification was obtained using the combination of the 13 selected features (sensitivity 74%, specificity 58% and accuracy 66%) compared to the use of all features (sensitivity 40%, specificity 52%, and accuracy 51%). Per-site performance of the 13 selected features in DA classification were as follows: T = sensitivity 63%, specificity 83%, accuracy 71%; N = sensitivity 87%, specificity 91% of and accuracy 90%; bone-M = sensitivity 33%, specificity 77% and accuracy 66%. An artificial intelligence model demonstrated to be feasible and able to select a panel of
Sections du résumé
BACKGROUND
BACKGROUND
Radiomic features are increasingly utilized to evaluate tumor heterogeneity in PET imaging but to date its role has not been investigated for Cho-PET in prostate cancer. The potential application of radiomics features analysis using a machine-learning radiomics algorithm was evaluated to select
METHODS
METHODS
We retrospectively analyzed high-risk PCa patients who underwent restaging
RESULTS
RESULTS
One hundred and six imaging features were extracted for 46 lesions for a total of 4876 features analyzed. No significant differences between the training and validating sets in terms of age, sex, PSA values, lesion location and size (P>0.05) were demonstrated by the machine-learning model. Thirteen features were able to discriminate FU disease status after NCA selection. Best performance in DA classification was obtained using the combination of the 13 selected features (sensitivity 74%, specificity 58% and accuracy 66%) compared to the use of all features (sensitivity 40%, specificity 52%, and accuracy 51%). Per-site performance of the 13 selected features in DA classification were as follows: T = sensitivity 63%, specificity 83%, accuracy 71%; N = sensitivity 87%, specificity 91% of and accuracy 90%; bone-M = sensitivity 33%, specificity 77% and accuracy 66%.
CONCLUSIONS
CONCLUSIONS
An artificial intelligence model demonstrated to be feasible and able to select a panel of
Identifiants
pubmed: 32543166
pii: S1824-4785.20.03227-6
doi: 10.23736/S1824-4785.20.03227-6
doi:
Substances chimiques
Choline
N91BDP6H0X
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM