共 49 条
Deep-learning-derived input function in dynamic [18F]FDG PET imaging of mice
被引:1
作者:
Kuttner, Samuel
[1
,2
,3
]
Luppino, Luigi T.
[2
]
Convert, Laurence
[4
,5
]
Sarrhini, Otman
[4
,5
]
Lecomte, Roger
[4
,5
,6
]
Kampffmeyer, Michael C.
[2
]
Sundset, Rune
[1
,3
]
Jenssen, Robert
[2
]
机构:
[1] Univ Hosp North Norway, PET Imaging Ctr, Tromso, Norway
[2] UiT Arctic Univ Norway, Dept Phys & Technol, UiT Machine Learning Grp, Tromso, Norway
[3] UiT Arctic Univ Norway, Dept Clin Med, Nucl Med & Radiat Biol Res Grp, Tromso, Norway
[4] Univ Sherbrooke, Sherbrooke Mol Imaging Ctr CRCHUS, Sherbrooke, PQ, Canada
[5] Univ Sherbrooke, Dept Nucl Med & Radiobiol, Sherbrooke, PQ, Canada
[6] Imaging Res & Technol Inc, Sherbrooke, PQ, Canada
来源:
FRONTIERS IN NUCLEAR MEDICINE
|
2024年
/
4卷
关键词:
dynamic positron emission tomography (PET);
small-animal PET 18F-FDG PET/CT;
Patlak analysis;
arterial input function estimation;
glucose metabolism;
deep learning;
prediction model;
SMALL-ANIMAL PET;
PARTIAL-VOLUME CORRECTION;
BRAIN TRANSFER CONSTANTS;
GLUCOSE-METABOLISM;
F-18-FDG PET;
GRAPHICAL EVALUATION;
BLOOD;
ARTERIAL;
QUANTIFICATION;
D O I:
10.3389/fnume.2024.1372379
中图分类号:
R8 [特种医学];
R445 [影像诊断学];
学科分类号:
1002 ;
100207 ;
1009 ;
摘要:
Dynamic positron emission tomography and kinetic modeling play a critical role in tracer development research using small animals. Kinetic modeling from dynamic PET imaging requires accurate knowledge of an input function, ideally determined through arterial blood sampling. Arterial cannulation in mice, however, requires complex, time-consuming and terminal surgery, meaning that longitudinal studies are impossible. The aim of the current work was to develop and evaluate a non-invasive, deep-learning-based prediction model (DLIF) that directly takes the PET data as input to predict a usable input function. We first trained and evaluated the DLIF model on 68 [18F]Fluorodeoxyglucose mouse scans with image-derived targets using cross validation. Subsequently, we evaluated the performance of a trained DLIF model on an external dataset consisting of 8 mouse scans where the input function was measured by continuous arterial blood sampling. The results showed that the predicted DLIF and image-derived targets were similar, and the net influx rate constants following from Patlak modeling using DLIF as input function were strongly correlated to the corresponding values obtained using the image-derived input function. There were somewhat larger discrepancies when evaluating the model on the external dataset, which could be attributed to systematic differences in the experimental setup between the two datasets. In conclusion, our non-invasive DLIF prediction method may be a viable alternative to arterial blood sampling in small animal [18F]FDG imaging. With further validation, DLIF could overcome the need for arterial cannulation and allow fully quantitative and longitudinal experiments in PET imaging studies of mice.
引用
收藏
页数:11
相关论文