Automated quantification of reference levels in liver and mediastinal blood pool for the Deauville therapy response classification using FDG-PET/CT in Hodgkin and non-Hodgkin lymphomas.
Adolescent
Adult
Aged
Aged, 80 and over
Automation
Female
Fluorodeoxyglucose F18
/ administration & dosage
Hodgkin Disease
/ diagnostic imaging
Humans
Image Interpretation, Computer-Assisted
/ methods
Liver
/ diagnostic imaging
Lymphoma, Non-Hodgkin
/ diagnostic imaging
Male
Mediastinum
/ blood supply
Middle Aged
Neural Networks, Computer
Positron Emission Tomography Computed Tomography
/ standards
Predictive Value of Tests
Radiopharmaceuticals
/ administration & dosage
Reproducibility of Results
Retrospective Studies
Treatment Outcome
Young Adult
artificial intelligence
convolutional neural network
objective
segmentation
Journal
Clinical physiology and functional imaging
ISSN: 1475-097X
Titre abrégé: Clin Physiol Funct Imaging
Pays: England
ID NLM: 101137604
Informations de publication
Date de publication:
Jan 2019
Jan 2019
Historique:
received:
24
05
2018
accepted:
11
09
2018
pubmed:
5
10
2018
medline:
10
4
2019
entrez:
5
10
2018
Statut:
ppublish
Résumé
18F-FDG-PET/CT has become a standard for assessing treatment response in patients with lymphoma. A subjective interpretation of the scan based on the Deauville 5-point scale has been widely adopted. However, inter-observer variability due to the subjectivity of the interpretation is a limitation. Our main goal is to develop an objective and automated method for evaluating response. The first step is to develop and validate an artificial intelligence (AI)-based method, for the automated quantification of reference levels in the liver and mediastinal blood pool in patients with lymphoma. The AI-based method was trained to segment the liver and the mediastinal blood pool in CT images from 80 lymphoma patients, who had undergone 18F-FDG-PET/CT, and apply this to a validation group of six lymphoma patients. CT segmentations were transferred to the PET images to obtain automatic standardized uptake values (SUV). The AI-based analysis was compared to corresponding manual segmentations performed by two radiologists. The mean difference for the comparison between the AI-based liver SUV quantifications and those of the two radiologists in the validation group was 0·02 and 0·02, respectively, and 0·02 and 0·02 for mediastinal blood pool respectively. An AI-based method for the automated quantification of reference levels in the liver and mediastinal blood pool shows good agreement with results obtained by experienced radiologists who had manually segmented the CT images. This is a first, promising step towards objective treatment response evaluation in patients with lymphoma based on 18F-FDG-PET/CT.
Sections du résumé
BACKGROUND
BACKGROUND
18F-FDG-PET/CT has become a standard for assessing treatment response in patients with lymphoma. A subjective interpretation of the scan based on the Deauville 5-point scale has been widely adopted. However, inter-observer variability due to the subjectivity of the interpretation is a limitation. Our main goal is to develop an objective and automated method for evaluating response. The first step is to develop and validate an artificial intelligence (AI)-based method, for the automated quantification of reference levels in the liver and mediastinal blood pool in patients with lymphoma.
METHODS
METHODS
The AI-based method was trained to segment the liver and the mediastinal blood pool in CT images from 80 lymphoma patients, who had undergone 18F-FDG-PET/CT, and apply this to a validation group of six lymphoma patients. CT segmentations were transferred to the PET images to obtain automatic standardized uptake values (SUV). The AI-based analysis was compared to corresponding manual segmentations performed by two radiologists.
RESULTS
RESULTS
The mean difference for the comparison between the AI-based liver SUV quantifications and those of the two radiologists in the validation group was 0·02 and 0·02, respectively, and 0·02 and 0·02 for mediastinal blood pool respectively.
CONCLUSIONS
CONCLUSIONS
An AI-based method for the automated quantification of reference levels in the liver and mediastinal blood pool shows good agreement with results obtained by experienced radiologists who had manually segmented the CT images. This is a first, promising step towards objective treatment response evaluation in patients with lymphoma based on 18F-FDG-PET/CT.
Substances chimiques
Radiopharmaceuticals
0
Fluorodeoxyglucose F18
0Z5B2CJX4D
Types de publication
Comparative Study
Journal Article
Validation Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
78-84Subventions
Organisme : Gothenburg University (Medical Faculty ALF Grants) Sweden
Informations de copyright
© 2018 Scandinavian Society of Clinical Physiology and Nuclear Medicine. Published by John Wiley & Sons Ltd.