.png){kind=icon}
Return
Improving 18F-FDG PET Quantification Through a Spatial Normalization Method
.png){kind=icon}
OA
AI
DOI：10.2967/jnumed.123.267360.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Quantification of F-18-FDG PET images is useful for accurate diagnosis and evaluation of various brain diseases, including brain tumors, epilepsy, dementia, and Parkinson disease. However, accurate quantification of F-18-FDG PET images requires matched 3-dimensional T-1 MRI scans of the same individuals to provide detailed information on brain anatomy. In this paper, we propose a transfer learning approach to adapt a pretrained deep neural network model from amyloid PET to spatially normalize F-18-FDG PET images without the need for 3-dimensional MRI. Methods: The proposed method is based on a deep learning model for automatic spatial normalization of F-18-FDG brain PET images, which was developed by fine-tuning a pretrained model for amyloid PET using only 103 F-18-FDG PET and MR images. After training, the algorithm was tested on 65 internal and 78 external test sets. All T-1 MR images with a 1-mm isotropic voxel size were processed with FreeSurfer software to provide cortical segmentation maps used to extract a ground-truth regional SUV ratio using cerebellar gray matter as a reference region. These values were compared with those from spatial normalization-based quantification methods using the proposed method and statistical parametric mapping software. Results: The proposed method showed superior spatial normalization compared with statistical parametric mapping, as evidenced by increased normalized mutual information and better size and shape matching in PET images. Quantitative evaluation revealed a consistently higher SUV ratio correlation and intraclass correlation coefficients for the proposed method across various brain regions in both internal and external datasets. The remarkably good correlation and intraclass correlation coefficient values of the proposed method for the external dataset are noteworthy, considering the dataset's different ethnic distribution and the use of different PET scanners and image reconstruction algorithms. Conclusion: This study successfully applied transfer learning to a deep neural network for F-18-FDG PET spatial normalization, demonstrating its resource efficiency and improved performance. This highlights the efficacy of transfer learning, which requires a smaller number of datasets than does the original network training, thus increasing the potential for broader use of deep learning-based brain PET spatial normalization techniques for various clinical and research radiotracers.
Keywords:
brain PET
quantification
spatial normalization
glucose
metabolism
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.1
Papers:
6.2K
Citations:
3.0W
Organization
Cited Papers
ShareSaveShareSaveShareSaveShareSaveInter-crystal scattering recovery of light-sharing PET detectors using convolutional neural networks
PREAI
ShareSaveAdaptive template generation for amyloid PET using a deep learning approach.png)
HUMAN BRAIN MAPPINGOAAI
HUMAN BRAIN MAPPINGIF3.3
OAAIShareSave
View more