Quantitative evaluation of a deep learning-based framework to generate whole-body attenuation maps using LSO background radiation in long axial FOV PET scanners.
Publisher DOI
PubMed ID
35852557
Abstract
PURPOSE
Attenuation correction is a critically important step in data correction in positron emission tomography (PET) image formation. The current standard method involves conversion of Hounsfield units from a computed tomography (CT) image to construct attenuation maps (µ-maps) at 511 keV. In this work, the increased sensitivity of long axial field-of-view (LAFOV) PET scanners was exploited to develop and evaluate a deep learning (DL) and joint reconstruction-based method to generate µ-maps utilizing background radiation from lutetium-based (LSO) scintillators.
METHODS
Data from 18 subjects were used to train convolutional neural networks to enhance initial µ-maps generated using joint activity and attenuation reconstruction algorithm (MLACF) with transmission data from LSO background radiation acquired before and after the administration of <sup>18</sup>F-fluorodeoxyglucose (<sup>18</sup>F-FDG) (µ-map<sub>MLACF-PRE</sub> and µ-map<sub>MLACF-POST</sub> respectively). The deep learning-enhanced µ-maps (µ-map<sub>DL-MLACF-PRE</sub> and µ-map<sub>DL-MLACF-POST</sub>) were compared against MLACF-derived and CT-based maps (µ-map<sub>CT</sub>). The performance of the method was also evaluated by assessing PET images reconstructed using each µ-map and computing volume-of-interest based standard uptake value measurements and percentage relative mean error (rME) and relative mean absolute error (rMAE) relative to CT-based method.
RESULTS
No statistically significant difference was observed in rME values for µ-map<sub>DL-MLACF-PRE</sub> and µ-map<sub>DL-MLACF-POST</sub> both in fat-based and water-based soft tissue as well as bones, suggesting that presence of the radiopharmaceutical activity in the body had negligible effects on the resulting µ-maps. The rMAE values µ-map<sub>DL-MLACF-POST</sub> were reduced by a factor of 3.3 in average compared to the rMAE of µ-map<sub>MLACF-POST</sub>. Similarly, the average rMAE values of PET images reconstructed using µ-map<sub>DL-MLACF-POST</sub> (PET<sub>DL-MLACF-POST</sub>) were 2.6 times smaller than the average rMAE values of PET images reconstructed using µ-map<sub>MLACF-POST</sub>. The mean absolute errors in SUV values of PET<sub>DL-MLACF-POST</sub> compared to PET<sub>CT</sub> were less than 5% in healthy organs, less than 7% in brain grey matter and 4.3% for all tumours combined.
CONCLUSION
We describe a deep learning-based method to accurately generate µ-maps from PET emission data and LSO background radiation, enabling CT-free attenuation and scatter correction in LAFOV PET scanners.
Attenuation correction is a critically important step in data correction in positron emission tomography (PET) image formation. The current standard method involves conversion of Hounsfield units from a computed tomography (CT) image to construct attenuation maps (µ-maps) at 511 keV. In this work, the increased sensitivity of long axial field-of-view (LAFOV) PET scanners was exploited to develop and evaluate a deep learning (DL) and joint reconstruction-based method to generate µ-maps utilizing background radiation from lutetium-based (LSO) scintillators.
METHODS
Data from 18 subjects were used to train convolutional neural networks to enhance initial µ-maps generated using joint activity and attenuation reconstruction algorithm (MLACF) with transmission data from LSO background radiation acquired before and after the administration of <sup>18</sup>F-fluorodeoxyglucose (<sup>18</sup>F-FDG) (µ-map<sub>MLACF-PRE</sub> and µ-map<sub>MLACF-POST</sub> respectively). The deep learning-enhanced µ-maps (µ-map<sub>DL-MLACF-PRE</sub> and µ-map<sub>DL-MLACF-POST</sub>) were compared against MLACF-derived and CT-based maps (µ-map<sub>CT</sub>). The performance of the method was also evaluated by assessing PET images reconstructed using each µ-map and computing volume-of-interest based standard uptake value measurements and percentage relative mean error (rME) and relative mean absolute error (rMAE) relative to CT-based method.
RESULTS
No statistically significant difference was observed in rME values for µ-map<sub>DL-MLACF-PRE</sub> and µ-map<sub>DL-MLACF-POST</sub> both in fat-based and water-based soft tissue as well as bones, suggesting that presence of the radiopharmaceutical activity in the body had negligible effects on the resulting µ-maps. The rMAE values µ-map<sub>DL-MLACF-POST</sub> were reduced by a factor of 3.3 in average compared to the rMAE of µ-map<sub>MLACF-POST</sub>. Similarly, the average rMAE values of PET images reconstructed using µ-map<sub>DL-MLACF-POST</sub> (PET<sub>DL-MLACF-POST</sub>) were 2.6 times smaller than the average rMAE values of PET images reconstructed using µ-map<sub>MLACF-POST</sub>. The mean absolute errors in SUV values of PET<sub>DL-MLACF-POST</sub> compared to PET<sub>CT</sub> were less than 5% in healthy organs, less than 7% in brain grey matter and 4.3% for all tumours combined.
CONCLUSION
We describe a deep learning-based method to accurately generate µ-maps from PET emission data and LSO background radiation, enabling CT-free attenuation and scatter correction in LAFOV PET scanners.
Date Issued
2022-11
Publication Type
Article
Subject(s)
Subjects
Attenuation correction CT-less PET Deep learning LAFOV PET Simultaneous reconstruction
Language(s)
en
Author(s)
Sari, Hasan | |
Teimoorisichani, Mohammadreza | |
Panin, Vladimir | |
Bharkhada, Deepak | |
Conti, Maurizio |
Additional Credits
Journal
European journal of nuclear medicine and molecular imaging
Publisher
Springer
ISSN
1619-7089
Access(Rights)
open.access