Evaluation of manual and automated approaches for segmentation and extraction of quantitative indices from [18F]FDG PET-CT images
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Evaluation of manual and automated approaches for segmentation and extraction of quantitative indices from [18F]FDG PET-CT images. / Krokos, Georgios; Kotwal, Tejas; Malaih, Afnan; Barrington, Sally; Jackson, Price; Hicks, Rodney J.; Marsden, Paul K.; Fischer, Barbara Malene.
I: Biomedical physics & engineering express, Bind 10, Nr. 2, 025007, 2024.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Evaluation of manual and automated approaches for segmentation and extraction of quantitative indices from [18F]FDG PET-CT images
AU - Krokos, Georgios
AU - Kotwal, Tejas
AU - Malaih, Afnan
AU - Barrington, Sally
AU - Jackson, Price
AU - Hicks, Rodney J.
AU - Marsden, Paul K.
AU - Fischer, Barbara Malene
N1 - Publisher Copyright: Creative Commons Attribution license.
PY - 2024
Y1 - 2024
N2 - Utilisation of whole organ volumes to extract anatomical and functional information from computed tomography (CT) and positron emission tomography (PET) images may provide key information for the treatment and follow-up of cancer patients. However, manual organ segmentation, is laborious and time-consuming. In this study, a CT-based deep learning method and a multi-atlas method were evaluated for segmenting the liver and spleen on CT images to extract quantitative tracer information from Fluorine-18 fluorodeoxyglucose ([18F]FDG) PET images of 50 patients with advanced Hodgkin lymphoma (HL). Manual segmentation was used as the reference method. The two automatic methods were also compared with a manually defined volume of interest (VOI) within the organ, a technique commonly performed in clinical settings. Both automatic methods provided accurate CT segmentations, with the deep learning method outperforming the multi-atlas with a DICE coefficient of 0.93 ± 0.03 (mean ± standard deviation) in liver and 0.87 ± 0.17 in spleen compared to 0.87 ± 0.05 (liver) and 0.78 ± 0.11 (spleen) for the multi-atlas. Similarly, a mean relative error of -3.2% for the liver and -3.4% for the spleen across patients was found for the mean standardized uptake value (SUVmean) using the deep learning regions while the corresponding errors for the multi-atlas method were -4.7% and -9.2%, respectively. For the maximum SUV (SUVmax), both methods resulted in higher than 20% overestimation due to the extension of organ boundaries to include neighbouring, high-uptake regions. The conservative VOI method which did not extend into neighbouring tissues, provided a more accurate SUVmaxestimate. In conclusion, the automatic, and particularly the deep learning method could be used to rapidly extract information of the SUVmeanwithin the liver and spleen. However, activity from neighbouring organs and lesions can lead to high biases in SUVmaxand current practices of manually defining a volume of interest in the organ should be considered instead.
AB - Utilisation of whole organ volumes to extract anatomical and functional information from computed tomography (CT) and positron emission tomography (PET) images may provide key information for the treatment and follow-up of cancer patients. However, manual organ segmentation, is laborious and time-consuming. In this study, a CT-based deep learning method and a multi-atlas method were evaluated for segmenting the liver and spleen on CT images to extract quantitative tracer information from Fluorine-18 fluorodeoxyglucose ([18F]FDG) PET images of 50 patients with advanced Hodgkin lymphoma (HL). Manual segmentation was used as the reference method. The two automatic methods were also compared with a manually defined volume of interest (VOI) within the organ, a technique commonly performed in clinical settings. Both automatic methods provided accurate CT segmentations, with the deep learning method outperforming the multi-atlas with a DICE coefficient of 0.93 ± 0.03 (mean ± standard deviation) in liver and 0.87 ± 0.17 in spleen compared to 0.87 ± 0.05 (liver) and 0.78 ± 0.11 (spleen) for the multi-atlas. Similarly, a mean relative error of -3.2% for the liver and -3.4% for the spleen across patients was found for the mean standardized uptake value (SUVmean) using the deep learning regions while the corresponding errors for the multi-atlas method were -4.7% and -9.2%, respectively. For the maximum SUV (SUVmax), both methods resulted in higher than 20% overestimation due to the extension of organ boundaries to include neighbouring, high-uptake regions. The conservative VOI method which did not extend into neighbouring tissues, provided a more accurate SUVmaxestimate. In conclusion, the automatic, and particularly the deep learning method could be used to rapidly extract information of the SUVmeanwithin the liver and spleen. However, activity from neighbouring organs and lesions can lead to high biases in SUVmaxand current practices of manually defining a volume of interest in the organ should be considered instead.
KW - atlas
KW - CT
KW - deep learning
KW - organ segmentation
KW - PET
U2 - 10.1088/2057-1976/ad160e
DO - 10.1088/2057-1976/ad160e
M3 - Journal article
C2 - 38100790
AN - SCOPUS:85181776977
VL - 10
JO - Biomedical physics & engineering express
JF - Biomedical physics & engineering express
SN - 2057-1976
IS - 2
M1 - 025007
ER -
ID: 379653275