Optimization-Based Image Reconstruction From Low-Count, List-Mode TOF-PET Data

Zheng, Zhang; Rose, Sean; Ye, Jinghan; Perkins, Amy E.; Chen, Buxin; Kao, Chien-Min; Sidky, Emil Y.; Tung, Chi-hua; Pan, Xiaochuan

doi:10.1109/tbme.2018.2802947

Cited by 14 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly to other authors (Karp et al 2008, Conti et al 2013, Westerwoudt et al 2014, Suljic et al 2015, Surti 2015, Zhang et al 2018, we demonstrated that when using TOF, CRC converges faster. Comparison between different timing resolutions showed that the convergence speed is further improved when the scanner has better timing resolution.…”

Section: Discussionsupporting

confidence: 86%

Implementation and validation of time-of-flight PET image reconstruction module for listmode and sinogram projection data in the STIR library

et al. 2019

View full text Add to dashboard Cite

In this paper, we describe the implementation of support for time-of-flight (TOF) positron emission tomography (PET) for both listmode and sinogram data in the open source software for tomographic image reconstruction (STIR). We provide validation and performance characterization using simulated data from the open source GATE Monte Carlo toolbox, with TOF configurations spanning from 81.2 to 209.6 ps. The coincidence detector resolution was corrected for the timing resolution deterioration due to the contribution of the crystal length. Comparison between the reconstruction of listmode and sinogram data demonstrated good agreement in both TOF and non-TOF cases in terms of relative absolute error. To reduce the reconstruction time, we assessed the truncation of the TOF kernel along lines-of-response (LOR). Rejection of LOR elements beyond four times the TOF standard deviation provides significant acceleration of without compromising the image quality. Further narrowing of the kernel can provide extra time reduction but with the gradual introduction of error in the reconstructed images. As expected, TOF reconstruction performs better than non-TOF in terms of both contrast-recovery-coefficient (CRC) and signal-to-noise ratio (SNR). CRC achieves convergence faster with TOF, at lower noise levels. SNR with TOF was superior for early iterations, but with quick deterioration. Higher timing resolution further improved reconstruction performance, while TOF bin mashing was shown to have only a small impact on reconstructed images.

show abstract

Section: Discussionsupporting

confidence: 86%

Implementation and validation of time-of-flight PET image reconstruction module for listmode and sinogram projection data in the STIR library

et al. 2019

View full text Add to dashboard Cite

show abstract

“…List-mode reconstructions allow existing data and their associated annotations to be retrospectively reconstructed with numerous variations to better match differences in other unseen dataset properties. Changing the reconstruction parameters can simulate different out-of-domain properties [ 15 , 16 , 17 ]. Thus, using existing datasets and their associated annotations with list-mode reconstructions may dramatically reduce the cost and effort to generate these better matching datasets.…”

Section: Introductionmentioning

confidence: 99%

Improving Generalizability of PET DL Algorithms: List-Mode Reconstructions Improve DOTATATE PET Hepatic Lesion Detection Performance

Yang,

Silosky,

Wehrend

et al. 2024

Bioengineering

View full text Add to dashboard Cite

Deep learning (DL) algorithms used for DOTATATE PET lesion detection typically require large, well-annotated training datasets. These are difficult to obtain due to low incidence of gastroenteropancreatic neuroendocrine tumors (GEP-NETs) and the high cost of manual annotation. Furthermore, networks trained and tested with data acquired from site specific PET/CT instrumentation, acquisition and processing protocols have reduced performance when tested with offsite data. This lack of generalizability requires even larger, more diverse training datasets. The objective of this study is to investigate the feasibility of improving DL algorithm performance by better matching the background noise in training datasets to higher noise, out-of-domain testing datasets. 68Ga-DOTATATE PET/CT datasets were obtained from two scanners: Scanner1, a state-of-the-art digital PET/CT (GE DMI PET/CT; n = 83 subjects), and Scanner2, an older-generation analog PET/CT (GE STE; n = 123 subjects). Set1, the data set from Scanner1, was reconstructed with standard clinical parameters (5 min; Q.Clear) and list-mode reconstructions (VPFXS 2, 3, 4, and 5-min). Set2, data from Scanner2 representing out-of-domain clinical scans, used standard iterative reconstruction (5 min; OSEM). A deep neural network was trained with each dataset: Network1 for Scanner1 and Network2 for Scanner2. DL performance (Network1) was tested with out-of-domain test data (Set2). To evaluate the effect of training sample size, we tested DL model performance using a fraction (25%, 50% and 75%) of Set1 for training. Scanner1, list-mode 2-min reconstructed data demonstrated the most similar noise level compared that of Set2, resulting in the best performance (F1 = 0.713). This was not significantly different compared to the highest performance, upper-bound limit using in-domain training for Network2 (F1 = 0.755; p-value = 0.103). Regarding sample size, the F1 score significantly increased from 25% training data (F1 = 0.478) to 100% training data (F1 = 0.713; p < 0.001). List-mode data from modern PET scanners can be reconstructed to better match the noise properties of older scanners. Using existing data and their associated annotations dramatically reduces the cost and effort in generating these datasets and significantly improves the performance of existing DL algorithms. List-mode reconstructions can provide an efficient, low-cost method to improve DL algorithm generalizability.

show abstract

Optimizing time-of-flight of PET/CT image quality via penalty β value in Bayesian penalized likelihood reconstruction algorithm

Murat,

Zulkifli,

Said

et al. 2025

Radiography

View full text Add to dashboard Cite

Optimization-Based Image Reconstruction From Low-Count, List-Mode TOF-PET Data

Abstract: The optimization-based reconstruction approach can be exploited for yielding insights into potential quality upper bound of reconstructed images in, and design of scanning protocols of, TOF-PET imaging of practical significance.

Cited by 14 publications

References 33 publications

Implementation and validation of time-of-flight PET image reconstruction module for listmode and sinogram projection data in the STIR library

Implementation and validation of time-of-flight PET image reconstruction module for listmode and sinogram projection data in the STIR library

Improving Generalizability of PET DL Algorithms: List-Mode Reconstructions Improve DOTATATE PET Hepatic Lesion Detection Performance

Optimizing time-of-flight of PET/CT image quality via penalty β value in Bayesian penalized likelihood reconstruction algorithm

Contact Info

Product

Resources

About