Optimizing Attenuation Correction in <sup>68</sup>Ga-PSMA PET Imaging Using Deep Learning and Artifact-Free Dataset Refinement
<b>Background/Objectives:</b> Attenuation correction (AC) is essential for achieving quantitatively accurate PET imaging. In <sup>68</sup>Ga-PSMA PET, however, artifacts such as respiratory motion, halo effects, and truncation errors in CT-based AC (CT-AC) images compromise i...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/11/1400 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850129378896248832 |
|---|---|
| author | Masoumeh Dorri Giv Guluzar Ozbolat Hossein Arabi Somayeh Malmir Shahrokh Naseri Vahid Roshan Ravan Hossein Akbari-Lalimi Raheleh Tabari Juybari Ghasem Ali Divband Nasrin Raeisi Vahid Reza Dabbagh Kakhki Emran Askari Sara Harsini |
| author_facet | Masoumeh Dorri Giv Guluzar Ozbolat Hossein Arabi Somayeh Malmir Shahrokh Naseri Vahid Roshan Ravan Hossein Akbari-Lalimi Raheleh Tabari Juybari Ghasem Ali Divband Nasrin Raeisi Vahid Reza Dabbagh Kakhki Emran Askari Sara Harsini |
| author_sort | Masoumeh Dorri Giv |
| collection | DOAJ |
| description | <b>Background/Objectives:</b> Attenuation correction (AC) is essential for achieving quantitatively accurate PET imaging. In <sup>68</sup>Ga-PSMA PET, however, artifacts such as respiratory motion, halo effects, and truncation errors in CT-based AC (CT-AC) images compromise image quality and impair model training for deep learning-based AC. This study proposes a novel artifact-refinement framework that filters out corrupted PET-CT images to create a clean dataset for training an image-domain AC model, eliminating the need for anatomical reference scans. <b>Methods:</b> A residual neural network (ResNet) was trained using paired PET non-AC and PET CT-AC images from a dataset of 828 whole-body <sup>68</sup>Ga-PSMA PET-CT scans. An initial model was trained using all data and employed to identify artifact-affected samples via voxel-level error metrics. These outliers were excluded, and the refined dataset was used to retrain the model with an L2 loss function. Performance was evaluated using metrics including mean error (ME), mean absolute error (MAE), relative error (RE%), RMSE, and SSIM on both internal and external test datasets. <b>Results:</b> The model trained with the artifact-free dataset demonstrated significantly improved performance: ME = −0.009 ± 0.43 SUV, MAE = 0.09 ± 0.41 SUV, and SSIM = 0.96 ± 0.03. Compared to the model trained on unfiltered data, the purified data model showed enhanced quantitative accuracy and robustness in external validation. <b>Conclusions:</b> The proposed data purification framework significantly enhances the performance of deep learning-based AC for <sup>68</sup>Ga-PSMA PET by mitigating artifact-induced errors. This approach facilitates reliable PET imaging in the absence of anatomical references, advancing clinical applicability and image fidelity. |
| format | Article |
| id | doaj-art-437215e00c644353adaaeb7be89e1fe9 |
| institution | OA Journals |
| issn | 2075-4418 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-437215e00c644353adaaeb7be89e1fe92025-08-20T02:33:01ZengMDPI AGDiagnostics2075-44182025-05-011511140010.3390/diagnostics15111400Optimizing Attenuation Correction in <sup>68</sup>Ga-PSMA PET Imaging Using Deep Learning and Artifact-Free Dataset RefinementMasoumeh Dorri Giv0Guluzar Ozbolat1Hossein Arabi2Somayeh Malmir3Shahrokh Naseri4Vahid Roshan Ravan5Hossein Akbari-Lalimi6Raheleh Tabari Juybari7Ghasem Ali Divband8Nasrin Raeisi9Vahid Reza Dabbagh Kakhki10Emran Askari11Sara Harsini12Nuclear Medicine Research Center, Department of Nuclear Medicine, Ghaem Hospital, Mashhad University of Medical Science, Mashhad 6541747187, IranFaculty of Health Science, Sinop University, Sinop 57000, TurkeyDivision of Nuclear Medicine and Molecular Imaging, Department of Medical Imaging, Geneva University Hospital, CH-1211 Geneva, SwitzerlandDepartment of Physics, Payame Noor University, Tehran 193954697, IranDepartment of Medical Physics, Faculty of Medicine, Mashhad University of Medical Science, Mashhad 9177948564, IranNuclear Medicine Research Center, Department of Nuclear Medicine, Ghaem Hospital, Mashhad University of Medical Science, Mashhad 6541747187, IranDepartment of Medical Physics and Radiology, School of Allied Medical Sciences, Gonabad University of Medical Sciences, Gonabad 8317785741, IranDepartment of Radiology Technology, Behbahan Faculty of Medical Science, Behbahan 6361796819, IranDepartment of Nuclear Medicine, Jam Hospital, Tehran 1588657915, IranNuclear Medicine Research Center, Department of Nuclear Medicine, Ghaem Hospital, Mashhad University of Medical Science, Mashhad 6541747187, IranNuclear Medicine Research Center, Department of Nuclear Medicine, Ghaem Hospital, Mashhad University of Medical Science, Mashhad 6541747187, IranNuclear Medicine Research Center, Department of Nuclear Medicine, Ghaem Hospital, Mashhad University of Medical Science, Mashhad 6541747187, IranDepartment of Molecular Imaging and Therapy, BC Cancer Research Institute, Vancouver, BC V5Z 1L3, Canada<b>Background/Objectives:</b> Attenuation correction (AC) is essential for achieving quantitatively accurate PET imaging. In <sup>68</sup>Ga-PSMA PET, however, artifacts such as respiratory motion, halo effects, and truncation errors in CT-based AC (CT-AC) images compromise image quality and impair model training for deep learning-based AC. This study proposes a novel artifact-refinement framework that filters out corrupted PET-CT images to create a clean dataset for training an image-domain AC model, eliminating the need for anatomical reference scans. <b>Methods:</b> A residual neural network (ResNet) was trained using paired PET non-AC and PET CT-AC images from a dataset of 828 whole-body <sup>68</sup>Ga-PSMA PET-CT scans. An initial model was trained using all data and employed to identify artifact-affected samples via voxel-level error metrics. These outliers were excluded, and the refined dataset was used to retrain the model with an L2 loss function. Performance was evaluated using metrics including mean error (ME), mean absolute error (MAE), relative error (RE%), RMSE, and SSIM on both internal and external test datasets. <b>Results:</b> The model trained with the artifact-free dataset demonstrated significantly improved performance: ME = −0.009 ± 0.43 SUV, MAE = 0.09 ± 0.41 SUV, and SSIM = 0.96 ± 0.03. Compared to the model trained on unfiltered data, the purified data model showed enhanced quantitative accuracy and robustness in external validation. <b>Conclusions:</b> The proposed data purification framework significantly enhances the performance of deep learning-based AC for <sup>68</sup>Ga-PSMA PET by mitigating artifact-induced errors. This approach facilitates reliable PET imaging in the absence of anatomical references, advancing clinical applicability and image fidelity.https://www.mdpi.com/2075-4418/15/11/1400attenuation correctionpositron emission tomography computed tomographydeep learningimage artifactsneural networks |
| spellingShingle | Masoumeh Dorri Giv Guluzar Ozbolat Hossein Arabi Somayeh Malmir Shahrokh Naseri Vahid Roshan Ravan Hossein Akbari-Lalimi Raheleh Tabari Juybari Ghasem Ali Divband Nasrin Raeisi Vahid Reza Dabbagh Kakhki Emran Askari Sara Harsini Optimizing Attenuation Correction in <sup>68</sup>Ga-PSMA PET Imaging Using Deep Learning and Artifact-Free Dataset Refinement Diagnostics attenuation correction positron emission tomography computed tomography deep learning image artifacts neural networks |
| title | Optimizing Attenuation Correction in <sup>68</sup>Ga-PSMA PET Imaging Using Deep Learning and Artifact-Free Dataset Refinement |
| title_full | Optimizing Attenuation Correction in <sup>68</sup>Ga-PSMA PET Imaging Using Deep Learning and Artifact-Free Dataset Refinement |
| title_fullStr | Optimizing Attenuation Correction in <sup>68</sup>Ga-PSMA PET Imaging Using Deep Learning and Artifact-Free Dataset Refinement |
| title_full_unstemmed | Optimizing Attenuation Correction in <sup>68</sup>Ga-PSMA PET Imaging Using Deep Learning and Artifact-Free Dataset Refinement |
| title_short | Optimizing Attenuation Correction in <sup>68</sup>Ga-PSMA PET Imaging Using Deep Learning and Artifact-Free Dataset Refinement |
| title_sort | optimizing attenuation correction in sup 68 sup ga psma pet imaging using deep learning and artifact free dataset refinement |
| topic | attenuation correction positron emission tomography computed tomography deep learning image artifacts neural networks |
| url | https://www.mdpi.com/2075-4418/15/11/1400 |
| work_keys_str_mv | AT masoumehdorrigiv optimizingattenuationcorrectioninsup68supgapsmapetimagingusingdeeplearningandartifactfreedatasetrefinement AT guluzarozbolat optimizingattenuationcorrectioninsup68supgapsmapetimagingusingdeeplearningandartifactfreedatasetrefinement AT hosseinarabi optimizingattenuationcorrectioninsup68supgapsmapetimagingusingdeeplearningandartifactfreedatasetrefinement AT somayehmalmir optimizingattenuationcorrectioninsup68supgapsmapetimagingusingdeeplearningandartifactfreedatasetrefinement AT shahrokhnaseri optimizingattenuationcorrectioninsup68supgapsmapetimagingusingdeeplearningandartifactfreedatasetrefinement AT vahidroshanravan optimizingattenuationcorrectioninsup68supgapsmapetimagingusingdeeplearningandartifactfreedatasetrefinement AT hosseinakbarilalimi optimizingattenuationcorrectioninsup68supgapsmapetimagingusingdeeplearningandartifactfreedatasetrefinement AT rahelehtabarijuybari optimizingattenuationcorrectioninsup68supgapsmapetimagingusingdeeplearningandartifactfreedatasetrefinement AT ghasemalidivband optimizingattenuationcorrectioninsup68supgapsmapetimagingusingdeeplearningandartifactfreedatasetrefinement AT nasrinraeisi optimizingattenuationcorrectioninsup68supgapsmapetimagingusingdeeplearningandartifactfreedatasetrefinement AT vahidrezadabbaghkakhki optimizingattenuationcorrectioninsup68supgapsmapetimagingusingdeeplearningandartifactfreedatasetrefinement AT emranaskari optimizingattenuationcorrectioninsup68supgapsmapetimagingusingdeeplearningandartifactfreedatasetrefinement AT saraharsini optimizingattenuationcorrectioninsup68supgapsmapetimagingusingdeeplearningandartifactfreedatasetrefinement |