Objective: This study evaluates the feasibility of direct scatter and attenuation correction of whole-body 68 Ga-PSMA PET images in the image domain using deep learning. Methods: Whole-body 68 Ga-PSMA PET images of 399 subjects were used to train a residual deep learning model, taking PET non-attenuation-corrected images (PET-nonAC) as input and CT-based attenuation-corrected PET images (PET-CTAC) as target (reference). Forty-six whole-body 68 Ga-PSMA PET images were used as an independent validation dataset. For validation, synthetic deep learning-based attenuation-corrected PET images were assessed considering the corresponding PET-CTAC images as reference. The evaluation metrics included the mean absolute error (MAE) of the SUV, peak signal-to-noise ratio, and structural similarity index (SSIM) in the whole body, as well as in different regions of the body, namely, head and neck, chest, and abdomen and pelvis. Results: The deep learning-guided direct attenuation and scatter correction produced images of comparable visual quality to PET-CTAC images. It achieved an MAE, relative error (RE%), SSIM, and peak signal-to-noise ratio of 0.91 ± 0.29 (SUV), −2.46% ± 10.10%, 0.973 ± 0.034, and 48.171 ± 2.964, respectively, within whole-body images of the independent external validation dataset. The largest RE% was observed in the head and neck region (−5.62% ± 11.73%), although this region exhibited the highest value of SSIM metric (0.982 ± 0.024). The MAE (SUV) and RE% within the different regions of the body were less than 2.0% and 6%, respectively, indicating acceptable performance of the deep learning model. Conclusions: This work demonstrated the feasibility of direct attenuation and scatter correction of whole-body 68 Ga-PSMA PET images in the image domain using deep learning with clinically tolerable errors. The technique has the potential of performing attenuation correction on stand-alone PET or PET/MRI systems.
Background: Single photon emission computed tomography (SPECT)-alone imaging using the Tc-99m radiopharmaceutical labeled with methylene diphosphonate or similar analogs is usually employed to diagnose metastatic bone and is typically followed by complementary magnetic resonance (MR) imaging for support in clinical decision-making. In this study, two attenuation map generation approaches from MR and SPECT non-attenuation corrected (SPECT-nonAC) images were evaluated in the context of quantitative SPECT imaging. Materials and Methods: The 2class-MR attenuation map was generated via segmenting an MR image into air and soft tissue. Likewise, SPECT-nonAC was segmented into background air and soft tissue to generate a 2class-SPECT attenuation map. The reference attenuation map was generated through manual bone segmentation from an MR image to develop a 3class-bone attenuation map. Standard uptake value (SUV) bias was calculated using the different attenuation maps on 50 vertebrae from normal patients and 16 vertebrae from metastatic patients. Results: The 2class-MR approach resulted in -16% and -8% SUV bias in normal and metastatic groups, respectively, while 2class-SPECT led to 33% and 26% SUV underestimation for the normal and metastatic patient groups, respectively. Conclusion: The 2class-SPECT approach led to a significant underestimation of SUV due to the uncertainty of body contour delineation. However, the 2class-MR approach resulted in less than -9% SUV bias in metastatic patients, demonstrating its potential to support quantitative SPECT imaging.
We investigate the accuracy of direct attenuation correction (AC) in the image domain for myocardial perfusion SPECT (single-photon emission computed tomography) imaging (MPI-SPECT) using residual (ResNet) and UNet deep convolutional neural networks. MPI-SPECT 99mTc-sestamibi images of 99 patients were retrospectively included. UNet and ResNet networks were trained using non-attenuation-corrected SPECT images as input, whereas CT-based attenuation-corrected (CT-AC) SPECT images served as reference. Chang’s calculated AC approach considering a uniform attenuation coefficient within the body contour was also implemented. Clinical and quantitative evaluations of the proposed methods were performed considering SPECT CT-AC images of 19 subjects (external validation set) as reference. Image-derived metrics, including the voxel-wise mean error (ME), mean absolute error, relative error, structural similarity index (SSI), and peak signal-to-noise ratio, as well as clinical relevant indices, such as total perfusion deficit (TPD), were utilized. Overall, AC SPECT images generated using the deep learning networks exhibited good agreement with SPECT CT-AC images, substantially outperforming Chang’s method. The ResNet and UNet models resulted in an ME of −6.99 ± 16.72 and −4.41 ± 11.8 and an SSI of 0.99 ± 0.04 and 0.98 ± 0.05, respectively. Chang’s approach led to ME and SSI of 25.52 ± 33.98 and 0.93 ± 0.09, respectively. Similarly, the clinical evaluation revealed a mean TPD of 12.78 ± 9.22% and 12.57 ± 8.93% for ResNet and UNet models, respectively, compared to 12.84 ± 8.63% obtained from SPECT CT-AC images. Conversely, Chang’s approach led to a mean TPD of 16.68 ± 11.24%. The deep learning AC methods have the potential to achieve reliable AC in MPI-SPECT imaging.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.