Quantitative evaluation of a deep learning-based framework to generate whole-body attenuation maps using LSO background radiation in long axial FOV PET scanners

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 (18)F-fluorodeoxyglucose ((18)F-FDG) (µ-map(MLACF-PRE) and µ-map(MLACF-POST) respectively). The deep learning-enhanced µ-maps (µ-map(DL-MLACF-PRE) and µ-map(DL-MLACF-POST)) were compared against MLACF-derived and CT-based maps (µ-map(CT)). 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(DL-MLACF-PRE) and µ-map(DL-MLACF-POST) 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(DL-MLACF-POST) were reduced by a factor of 3.3 in average compared to the rMAE of µ-map(MLACF-POST). Similarly, the average rMAE values of PET images reconstructed using µ-map(DL-MLACF-POST) (PET(DL-MLACF-POST)) were 2.6 times smaller than the average rMAE values of PET images reconstructed using µ-map(MLACF-POST). The mean absolute errors in SUV values of PET(DL-MLACF-POST) compared to PET(CT) 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. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s00259-022-05909-3.