Tehran University of Medical Sciences

Science Communicator Platform

Stay connected! Follow us on X network (Twitter):
Share By
Pet Images Enhancement Using Deep Training of Reconstructed Images With Bayesian Penalized Likelihood Algorithm Publisher

Summary: Can AI enhance PET scans? Study finds ResNet model matches BPL image quality. #PETImaging #DeepLearning

Ghafari A2 ; Mofrad MS1 ; Kasraie N3 ; Ay MR1, 4 ; Seyyedi N5 ; Sheikhzadeh P1, 6
Authors

Source: Journal of Medical and Biological Engineering Published:2024


Abstract

Purpose: To adopt the merits of the Bayesian Penalized Likelihood (BPL) reconstruction algorithm (incl. improved contrast recovery), a deep learning ResNet model was trained to estimate BPL-like images using the non-attenuation, non-scatter corrected PET images (PET-nonAC) as inputs. Methods: Images of 112 patients were used for model training (79 patients), validation (13 patients) and testing (20 patients). The ResNet model used PET-nonAC images as input and predicted corresponding BPL-like images. The model performance regarding image quality was evaluated using metrics such as contrast-to-noise ratio (CNR). Results: The CNR of the reference BPL images was 2.40, while estimated BPL-like images using the deep learning model have a CNR value of 2.42 indicative of comparable performance. Conclusion: The estimated BPL-like images of the deep learning model offer comparable quality to the reference BPL images especially regarding the CNR metric. This deep learning model can be used to improve the image quality PET-nonAC by adopting the characteristics of the BPL images. © Taiwanese Society of Biomedical Engineering 2024.
Related Docs
View other Related Docs
1. Deep-Jasc: Joint Attenuation and Scatter Correction in Whole-Body 18F-Fdg Pet Using a Deep Residual Network, European Journal of Nuclear Medicine and Molecular Imaging (2020)
2. Leveraging Deep Neural Networks to Improve Numerical and Perceptual Image Quality in Low-Dose Preclinical Pet Imaging, Computerized Medical Imaging and Graphics (2021)
3. Deep Learning-Based Techniques for Estimating High-Quality Full-Dose Positron Emission Tomography Images From Low-Dose Scans: A Systematic Review, BMC Medical Imaging (2024)
Experts (# of related papers)
View all Related Experts
Mohammad Reza Ay (6)
Peyman Sheikhzadeh (5)
Pet Images Enhancement Using Deep Training of Reconstructed Images With Bayesian Penalized Likelihood Algorithm
Other Related Docs
4. Deep Adaptive Transfer Learning for Site-Specific Pet Attenuation and Scatter Correction From Multi-National/Institutional Datasets, 2022 IEEE NSS/MIC RTSD - IEEE Nuclear Science Symposium# Medical Imaging Conference and Room Temperature Semiconductor Detector Conference (2022)
5. Deep Learning-Based Partial Volume Correction in Standard and Low-Dose Positron Emission Tomography-Computed Tomography Imaging, Quantitative Imaging in Medicine and Surgery (2024)
6. Deep Active Learning Model for Adaptive Pet Attenuation and Scatter Correction in Multi-Centric Studies, 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record# NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors# RTSD 2022 (2021)
7. Impact of Time-Of-Flight and Point-Spread-Function for Respiratory Artifact Reduction in Pet/Ct Imaging: Focus on Standardized Uptake Value, Tanaffos (2017)
8. A Deep Neural Network to Recover Missing Data in Small Animal Pet Imaging: Comparison Between Sinogram-And Image-Domain Implementations, Proceedings - International Symposium on Biomedical Imaging (2021)
9. Automated Deep Identification of Radiopharmaceutical Type and Body Region From Pet Images, Iranian Journal of Nuclear Medicine (2024)
10. Accurate Automatic Glioma Segmentation in Brain Mri Images Based on Capsnet, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society# EMBS (2021)
11. Atb-Net: A Novel Attention-Based Convolutional Neural Network for Predicting Full-Dose From Low-Dose Pet Images, 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record# NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors# RTSD 2022 (2021)
12. Fusion Strategies for Deep Convolutional Neural Network Representations in Histopathological Image Classification, Journal of Supercomputing (2025)
13. Deep Learning-Based Automated Delineation of Head and Neck Malignant Lesions From Pet Images, 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference# NSS/MIC 2020 (2020)
14. Cultivating Diagnostic Clarity: The Importance of Reporting Artificial Intelligence Confidence Levels in Radiologic Diagnoses, Clinical Imaging (2025)
15. Lung Cancer Management: Revolutionizing Patient Outcomes Through Machine Learning and Artificial Intelligence, Cancer Reports (2025)
16. Fully Automated Gross Tumor Volume Delineation From Pet in Head and Neck Cancer Using Deep Learning Algorithms, Clinical Nuclear Medicine (2021)
17. Enhancing Radiomics Robustness Using Bayesian Penalized Likelihood Pet Reconstruction: Application to Phantom and Non-Small Cell Lung Cancer Patient Studies, BMC Medical Imaging (2025)
18. Application of Artificial Intelligence in Oncologic Molecular Pet-Imaging: A Narrative Review on Beyond [18F]F-Fdg Tracers - Part I. Psma, Choline, and Dota Radiotracers, Seminars in Nuclear Medicine (2024)
19. Classification of Ocular Surface Diseases: Deep Learning for Distinguishing Ocular Surface Squamous Neoplasia From Pterygium, Graefe's Archive for Clinical and Experimental Ophthalmology (2025)
20. Computer-Aided Detection (Cade) and Segmentation Methods for Breast Cancer Using Magnetic Resonance Imaging (Mri), Journal of Magnetic Resonance Imaging (2025)