- Subscribe
- My alerts
- Log in
- My Cart
Advanced Search
- Home
- Content
- Current
- Ahead of print
- Past Issues
- JNM Supplement
- SNMMI Annual Meeting Abstracts
- JNM Podcasts
- Continuing Education
- Subscriptions
- Subscribers
- Institutional and Non-member
- Rates
- Journal Claims
- Authors
- Submit to JNM
- Information for Authors
- Assignment of Copyright
- AQARA requirements
- Info
- Reviewers
- Permissions
- Advertisers
- About
- About Us
- Editorial Board
- Contact Information
- More
- Alerts
- Feedback
- Help
- SNMMI Journals
- Visit JNM on Facebook
- Join JNM on LinkedIn
- Follow JNM on Twitter
- Subscribe to our RSS feeds
Meeting ReportGeneral Clinical Specialties - Pediatrics
Chenyang Han, Andrew Trout, Joseph MacLean, Jieyuhan Zhu and Jing Tang
Journal of Nuclear Medicine June 2024, 65 (supplement 2) 242529;
- Article
Abstract
242529
Introduction: Deep learning (DL)-based PET attenuation and scatter correction (ASC) has received attention as an alternative to the standard CT-based ASC method. This development toward achieving CT-free PET imaging has the potential to reduce patient radiation dose which would be particularly beneficial to children. In this study, we compare two convolutional neural network (CNN)-based ASC approaches using emission-only PET data, with the goal of achieving quantitative accuracy comparable to CT-based ASC.
Methods: We retrospectively processed data of 83 whole-body PET/CT scans from 58 pediatric patients under 12 years of age (6.1 ± 0.6 years, weight 23.1 ± 12.9 kg) without gross misregistration between PET and CT. All patients underwent 18F-FDG (0.11 ± 0.01 mCi/kg administered activity) examinations on a GE Discovery MI Gen 2 PET/CT scanner using a standard-of-care acquisition protocol. For each scan, the PET data were reconstructed using the manufacturer standard reconstruction (Q.Clear, regularization parameter = 700) with no ASC (NASC) and with ASC based on the CT generated μ-map, the latter serving as the reference for evaluation.
We developed two DL methods, with method A training a CNN to predict an ASC PET image (λ-CNN PET) directly from the NASC PET image out of which method B predicts a μ-map. In method B, to focus the CNN on predicting a μ-map corresponding to the patient body, we divided the CT-generated μ-map into two parts: patient body and everything (equipment/bedding) outside of the body. The CNN predicted only the μ-map for the patient body and objects outside of the body were added back to the CNN-generated pseudo μ-map before Q.Clear reconstruction was performed (μ-CNN PET). Out of the 83 scans, data from 63 were used for training and 20 were used for performance analysis. Random rotation of the training input and label was used to increase the robustness of the model and prevent overfitting. Ninety-one thousand training data pairs were generated for each model which used an ADAM optimizer with a learning rate of 0.0001 and L2 loss. To quantitatively evaluate the λ-CNN PET and μ-CNN PET results against the CT-based ASC PET as the reference, standardized uptake values (SUVs) were measured in the liver (3-cm diameter region of interest [ROI]) and in up to five of the most-avid lesions (if lesions were present). Twenty-seven total lesions from 15 scans were included. Dunn’s test was used to compare SUVmean and SUVmax between reconstruction results with p < 0.05 considered significant. The structural similarity index measure (SSIM) was employed to compare the similarity between λ-CNN PET or μ-CNN PET and the reference CT-based ASC PET.
Results: Results from both DL methods exhibited no significant differences in liver SUV values when compared with the reference PET (p = 0.74 and 0.84 for SUVmax, p = 0.87 and 0.94 for liver SUVmean for λ-CNN PET and μ-CNN PET, respectively). Method A with SSIM= 0.964 ± 0.009, had a negative bias over the whole brain of test scans as well as noticeable blur throughout the body, leading to reduced lesion SUVs. Specifically, significant differences were found in lesion SUVmax (p = 0.018) but not in lesion SUVmean (p = 0.35). In method B, CNN-predicted μ-maps had poorly rendered bone structures, overestimated μ-values in the lungs, and artifacts above the patient’s head in some cases. These discrepancies had minimal influence on ASC, resulting in higher similarity (SSIM = 0.984 ± 0.012) between λ-CNN PET and the reference PET and no significant difference in lesion SUVs (p = 0.63 and 0.83 for SUVmax and SUVmean).
Conclusions: In conclusion, for pediatric patients imaged on a state-of-the-art digital PET/CT system, ASC can be achieved using a CNN-predicted attenuation map without the use of CT. Resultant PET images show no significantly difference from CT-based ASC PET images in SUV measures.
- Download figure
- Open in new tab
- Download powerpoint
Previous
Back to top
In this issue
Journal of Nuclear Medicine
Vol. 65, Issue supplement 2
June 1, 2024
- Table of Contents
- Index by author
Article Alerts
Email Article
Citation Tools
- Facebook Like
- Google Plus One
Bookmark this article
Jump to section
- Article
Related Articles
No related articles found.
- Google Scholar
Cited By...
No citing articles found.
- Google Scholar
More in this TOC Section
General Clinical Specialties - Pediatrics
Diuresis Effectiveness of Furosemide is Confounded by Propofol Sedation During Pediatric Renography.
Sedation-free pediatric [18F]FDG imaging on total-body PET/CT with the assistance of artificial intelligence
Show more General Clinical Specialties - Pediatrics
Deep learningâbased CT-free attenuation and scatter correction for pediatric whole-body PET imaging
Diuresis Effectiveness of Furosemide is Confounded by Propofol Sedation During Pediatric Renography.
Sedation-free pediatric [18F]FDG imaging on total-body PET/CT with the assistance of artificial intelligence
Deep learningâbased CT-free attenuation and scatter correction for pediatric whole-body PET imaging
Show more Deep learningâbased CT-free attenuation and scatter correction for pediatric whole-body PET imaging