Deep Learning-Based Delayed PET Image Synthesis from Corresponding Early Scanned PET for Dosimetry Uptake Estimation
The acquisition of in vivo radiopharmaceutical distribution through imaging is time-consuming due to dosimetry, which requires the subject to be scanned at several time points post-injection. This study aimed to generate delayed positron emission tomography images from early images using a deep-lear...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/19/3045 |
| _version_ | 1797576055854202880 |
|---|---|
| author | Kangsan Kim Byung Hyun Byun Ilhan Lim Sang Moo Lim Sang-Keun Woo |
| author_facet | Kangsan Kim Byung Hyun Byun Ilhan Lim Sang Moo Lim Sang-Keun Woo |
| author_sort | Kangsan Kim |
| collection | DOAJ |
| description | The acquisition of in vivo radiopharmaceutical distribution through imaging is time-consuming due to dosimetry, which requires the subject to be scanned at several time points post-injection. This study aimed to generate delayed positron emission tomography images from early images using a deep-learning-based image generation model to mitigate the time cost and inconvenience. Eighteen healthy participants were recruited and injected with [<sup>18</sup>F]Fluorodeoxyglucose. A paired image-to-image translation model, based on a generative adversarial network (GAN), was used as the generation model. The standardized uptake value (SUV) mean of the generated image of each organ was compared with that of the ground-truth. The least square GAN and perceptual loss combinations displayed the best performance. As the uptake time of the early image became closer to that of the ground-truth image, the translation performance improved. The SUV mean values of the nominated organs were estimated reasonably accurately for the muscle, heart, liver, and spleen. The results demonstrate that the image-to-image translation deep learning model is applicable for the generation of a functional image from another functional image acquired from normal subjects, including predictions of organ-wise activity for specific normal organs. |
| first_indexed | 2024-03-10T21:47:06Z |
| format | Article |
| id | doaj.art-d3fb68aeceaf46d98ae07ecb8c5dcbdd |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T21:47:06Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-d3fb68aeceaf46d98ae07ecb8c5dcbdd2023-11-19T14:13:59ZengMDPI AGDiagnostics2075-44182023-09-011319304510.3390/diagnostics13193045Deep Learning-Based Delayed PET Image Synthesis from Corresponding Early Scanned PET for Dosimetry Uptake EstimationKangsan Kim0Byung Hyun Byun1Ilhan Lim2Sang Moo Lim3Sang-Keun Woo4Division of Applied RI, Korea Institute of Radiological and Medical Sciences, Seoul 01812, Republic of KoreaDepartment of Nuclear Medicine, Korea Institute of Radiological and Medical Sciences, Seoul 01812, Republic of KoreaDepartment of Nuclear Medicine, Korea Institute of Radiological and Medical Sciences, Seoul 01812, Republic of KoreaDepartment of Nuclear Medicine, Korea Institute of Radiological and Medical Sciences, Seoul 01812, Republic of KoreaDivision of Applied RI, Korea Institute of Radiological and Medical Sciences, Seoul 01812, Republic of KoreaThe acquisition of in vivo radiopharmaceutical distribution through imaging is time-consuming due to dosimetry, which requires the subject to be scanned at several time points post-injection. This study aimed to generate delayed positron emission tomography images from early images using a deep-learning-based image generation model to mitigate the time cost and inconvenience. Eighteen healthy participants were recruited and injected with [<sup>18</sup>F]Fluorodeoxyglucose. A paired image-to-image translation model, based on a generative adversarial network (GAN), was used as the generation model. The standardized uptake value (SUV) mean of the generated image of each organ was compared with that of the ground-truth. The least square GAN and perceptual loss combinations displayed the best performance. As the uptake time of the early image became closer to that of the ground-truth image, the translation performance improved. The SUV mean values of the nominated organs were estimated reasonably accurately for the muscle, heart, liver, and spleen. The results demonstrate that the image-to-image translation deep learning model is applicable for the generation of a functional image from another functional image acquired from normal subjects, including predictions of organ-wise activity for specific normal organs.https://www.mdpi.com/2075-4418/13/19/3045functional imaging<sup>18</sup>F-FDGdiagnostic radiopharmaceuticalpositron emission tomographystandardized uptake valueinternal dosimetry |
| spellingShingle | Kangsan Kim Byung Hyun Byun Ilhan Lim Sang Moo Lim Sang-Keun Woo Deep Learning-Based Delayed PET Image Synthesis from Corresponding Early Scanned PET for Dosimetry Uptake Estimation Diagnostics functional imaging <sup>18</sup>F-FDG diagnostic radiopharmaceutical positron emission tomography standardized uptake value internal dosimetry |
| title | Deep Learning-Based Delayed PET Image Synthesis from Corresponding Early Scanned PET for Dosimetry Uptake Estimation |
| title_full | Deep Learning-Based Delayed PET Image Synthesis from Corresponding Early Scanned PET for Dosimetry Uptake Estimation |
| title_fullStr | Deep Learning-Based Delayed PET Image Synthesis from Corresponding Early Scanned PET for Dosimetry Uptake Estimation |
| title_full_unstemmed | Deep Learning-Based Delayed PET Image Synthesis from Corresponding Early Scanned PET for Dosimetry Uptake Estimation |
| title_short | Deep Learning-Based Delayed PET Image Synthesis from Corresponding Early Scanned PET for Dosimetry Uptake Estimation |
| title_sort | deep learning based delayed pet image synthesis from corresponding early scanned pet for dosimetry uptake estimation |
| topic | functional imaging <sup>18</sup>F-FDG diagnostic radiopharmaceutical positron emission tomography standardized uptake value internal dosimetry |
| url | https://www.mdpi.com/2075-4418/13/19/3045 |
| work_keys_str_mv | AT kangsankim deeplearningbaseddelayedpetimagesynthesisfromcorrespondingearlyscannedpetfordosimetryuptakeestimation AT byunghyunbyun deeplearningbaseddelayedpetimagesynthesisfromcorrespondingearlyscannedpetfordosimetryuptakeestimation AT ilhanlim deeplearningbaseddelayedpetimagesynthesisfromcorrespondingearlyscannedpetfordosimetryuptakeestimation AT sangmoolim deeplearningbaseddelayedpetimagesynthesisfromcorrespondingearlyscannedpetfordosimetryuptakeestimation AT sangkeunwoo deeplearningbaseddelayedpetimagesynthesisfromcorrespondingearlyscannedpetfordosimetryuptakeestimation |