Dual-Tracer PET Image Separation by Deep Learning: A Simulation Study
Source abstract
Abstract
Multiplexed positron emission tomography (PET) imaging provides perfectly registered simultaneous functional and molecular imaging of more than one biomarker. However, the separation of the multiplexed PET signals within a single PET scan is challenging due to the fact that all PET tracers emit positrons, which, after annihilating with a nearby electron, give rise to 511 keV photon pairs that are detected in coincidence. Compartment modelling can separate single-tracer PET signals from multiplexed signals based on the differences in bio-distribution kinetics and radioactive decay. However, the compartment-modelling-based method requires staggered injections and assumes that each tracer’s input function is known. In this paper, we propose a deep-learning-based method to simultaneously separate dual-tracer PET signals without explicitly knowing the input functions. We evaluate the proposed deep-learning-based separation method on dual-tracer [18F]FDG and [11C]MET PET simulations and compare its separation performance to that of the compartment-modelling-based method, assessing performance dependence on the time interval between tracer injections as well as on the amount of training data. It is shown that the proposed method implicitly denoises the separated images and offers reduced variance in the separated images compared to compartment modelling.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Medical Imaging Techniques and Applications · Advanced MRI Techniques and Applications · Advanced Radiotherapy Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Biomedical Engineering and Imaging Sciences, Department of Biomedical Engineering, King’s College London, St. Thomas’ Hospital, London SE1 7EH, UK
Funding
EPSRC programme for Next Generation Molecular Imaging and Therapy with Radionuclides · Wellcome/EPSRC Centre for Medical Engineering
References (63)
Show source-provided references
1. Cardiac positron emission tomography imaging10.1053/j.semnuclmed.2004.09.002 ↗
2. Quantitative imaging of protein targets in the human brain with PET10.1088/0031-9155/60/22/R363 ↗
3. A combined PET/CT scanner for clinical oncology
4. Normal variants, artefacts and interpretative pitfalls in PET imaging with 18-fluoro-2-deoxyglucose and carbon-11 methionine10.1007/s002590050597 ↗
5. Usefulness of 11C-methionine PET in the evaluation of brain lesions that are hypo-or isometabolic on 18F-FDG PET10.1007/s00259-001-0690-4 ↗
6. Feasibility of simultaneous and sequentially administered dual tracer protocols for measurement of regional cerebral haematocrit using positron emission tomography10.1088/0031-9155/35/2/005 ↗
7. Dual-tracer PET/CT imaging in evaluation of metastatic hepatocellular carcinoma10.2967/jnumed.106.036673 ↗
8. Early astrocytosis in autosomal dominant Alzheimer’s disease measured in vivo by multi-tracer positron emission tomography10.1038/srep16404 ↗
9. Mapelli, P., Partelli, S., Salgarello, M., Doraku, J., Muffatti, F., Schiavo Lena, M., Pasetto, S., Bezzi, C., Bettinardi, V., and Andreasi, V. (2021). Dual tracer 68Ga-DOTATOC and 18F-FDG PET improve preoperative evaluation of aggressiveness in resectable pancreatic neuroendocrine neoplasms. Diagnostics, 11.10.3390/diagnostics11020192 ↗
10. 18F-alfatide II and 18F-FDG dual-tracer dynamic PET for parametric, early prediction of tumor response to therapy10.2967/jnumed.113.122069 ↗
11. An investigation of a double-tracer technique for positron computerized tomography
12. Koeppe, R.A., Ficaro, E.P., Raffel, D.M., Minoshima, S., and Kilbourn, M.R. (1998). Quantitative Functional Brain Imaging with Positron Emission Tomography, Academic Press.
13. Rapid dual-injection single-scan 13N-ammonia PET for quantification of rest and stress myocardial blood flows10.1088/0031-9155/51/20/018 ↗
14. Methodology for quantitative rapid multi-tracer PET tumor characterizations10.7150/thno.5201 ↗
15. Simultaneous dual-tracer PET imaging of the rat brain and its application in the study of cerebral ischemia10.1007/s11307-010-0370-5 ↗
16. Verhaeghe, J., D’Asseler, Y., Staelens, S., and Lemahieu, I. (2005, January 23–29). Noise properties of simultaneous dual tracer PET imaging. Proceedings of the IEEE Nuclear Science Symposium Conference Record, 2005, Fajardo, PR, USA.
17. Dual-[11C]tracer single-acquisition positron emission tomography studies10.1097/00004647-200112000-00013 ↗
18. Simultaneous quantification of two brain functions with dual tracer injection in PET dynamic study10.1016/j.ics.2004.04.015 ↗
19. Feasibility of rapid multitracer PET tumor imaging10.1109/TNS.2005.858230 ↗
20. Rapid dual-tracer PTSM + ATSM PET imaging of tumour blood flow and hypoxia: A simulation study10.1088/0031-9155/51/1/005 ↗
21. Signal separation and parameter estimation in noninvasive dual-tracer PET scans using reference-region approaches10.1038/jcbfm.2009.53 ↗
22. Single-scan dual-tracer FLT + FDG PET tumor characterization10.1088/0031-9155/58/3/429 ↗
23. PET Measurement of rCBF in the presence of a neurochemical tracer10.1016/j.jneumeth.2003.09.006 ↗
24. Evaluation of rapid dual-tracer 62Cu-PTSM + 62Cu-ATSM PET in dogs with spontaneously occurring tumors10.1088/0031-9155/53/1/015 ↗
25. Rapid Multi-Tracer PET Tumor Imaging with 18F-FDG and Secondary Shorter-Lived Tracers10.1109/TNS.2009.2026417 ↗
26. Generalized separable parameter space techniques for fitting 1K–5K serial compartment models10.1118/1.4810937 ↗
27. Application of separable parameter space techniques to multi-tracer PET compartment modeling10.1088/0031-9155/61/3/1238 ↗
28. Direct parametric image reconstruction in reduced parameter space for rapid multi-tracer PET imaging10.1109/TMI.2015.2403300 ↗
29. Gao, F., Liu, H., Jian, Y., and Shi, P. (2009, January 5–10). Dynamic dual-tracer PET reconstruction. Proceedings of the Information Processing in Medical Imaging: 21st International Conference, IPMI 2009, Williamsburg, VA, USA.
30. Accelerated PET water activation acquisition with signal separation methodology10.1118/1.4789483 ↗
31. Simultaneous water activation and glucose metabolic rate imaging with PET10.1088/0031-9155/58/3/393 ↗
32. Reader, A.J., Matthews, J.C., Sureau, F.C., Comtat, C., Trébossen, R., and Buvat, I. (November, January 26). Fully 4D image reconstruction by estimation of an input function and spectral coefficients. Proceedings of the 2007 IEEE Nuclear Science Symposium Conference Record, Honolulu, HI, USA.10.1109/NSSMIC.2007.4436834 ↗
33. Dual-tracer PET using generalized factor analysis of dynamic sequences10.1007/s11307-013-0631-1 ↗
34. Design and utilisation of protocols to characterise dynamic PET uptake of two tracers using basis pursuit10.1088/1361-6560/aa6b44 ↗
35. Machine Learning-Based Noninvasive Quantification of Single-Imaging Session Dual-Tracer 18F-FDG and 68Ga-DOTATATE Dynamic PET-CT in Oncology10.1109/TMI.2021.3112783 ↗
36. Chen, T., and Guestrin, C. (2016, January 13–17). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
37. Separation of a mixture of simultaneous dual-tracer PET signals: A data-driven approach10.1109/TNS.2017.2736644 ↗
38. Deep-learning-based separation of a mixture of dual-tracer single-acquisition PET signals with equal half-Lives: A simulation study10.1109/TRPMS.2019.2897120 ↗
39. Separation of dual-tracer PET signals using a deep stacking network10.1016/j.nima.2021.165681 ↗
40. Luo, Y., and Mesgarani, N. (2018, January 15–20). Tasnet: Time-domain audio separation network for real-time, single-channel speech separation. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.10.1109/ICASSP.2018.8462116 ↗
41. Tong, J., Chen, Y., and Liu, H. (2019, January 13). Single-scan dual-tracer separation network based on pre-trained GRU. Proceedings of the International Workshop on Multiscale Multimodal Medical Imaging, Shenzhen, China.10.1007/978-3-030-37969-8_6 ↗
42. Temporal information-guided dynamic dual-tracer PET signal separation network10.1002/mp.15566 ↗
43. Lian, D., Li, Y., and Liu, H. (2022, January 27–29). Spatiotemporal Attention Constrained Deep Learning Framework for Dual-Tracer PET Imaging. Proceedings of the Medical Image Understanding and Analysis: 26th Annual Conference, MIUA 2022, Cambridge, UK.10.1007/978-3-031-12053-4_7 ↗
44. Three-dimensional convolutional neural networks for simultaneous dual-tracer PET imaging10.1088/1361-6560/ab3103 ↗
45. Zeng, F., and Liu, H. (2020, January 11–16). Dual-tracer PET image direct reconstruction and separation based on three-dimensional encoder–decoder network. Proceedings of the Optics in Health Care and Biomedical Optics X, Online.10.1117/12.2573439 ↗
46. Direct reconstruction for simultaneous dual-tracer PET imaging based on multi-task learning10.1186/s13550-023-00955-w ↗
47. Wan, Y., Ye, H., and Liu, H. (2021, January 15–20). Deep-learning based joint estimation of dual-tracer PET image activity maps and clustering of time activity curves. Proceedings of the Medical Imaging 2021: Physics of Medical Imaging, Online.10.1117/12.2580873 ↗
48. Isola, P., Zhu, J.Y., Zhou, T., and Efros, A.A. (2017, January 21–26). Image-to-image translation with conditional adversarial networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, Honolulu, HI, USA.10.1109/CVPR.2017.632 ↗
49. Anderson, D.H. (2013). Compartmental Modeling and Tracer Kinetics, Springer Science and Business Media.
50. Kinetic modeling in positron emission tomography10.1016/B978-012744482-6.50026-0 ↗
51. Caruana, R. (1993, January 27–29). Multitask learning: A knowledge-based source of inductive bias. Proceedings of the Tenth International Conference on Machine Learning, Amherst, MA, USA.10.1016/B978-1-55860-307-3.50012-5 ↗
52. Bayesian/information theoretic model of learning to learn via multiple task sampling10.1023/A:1007327622663 ↗
53. Cocosco, C.A., Kollokian, V., Kwan, R.K., Pike, G.B., and Evans, A.C. (1997). Brainweb: Online interface to a 3D MRI simulated brain database. NeuroImage, 5.
54. FBP-Net for direct reconstruction of dynamic PET images10.1088/1361-6560/abc09d ↗
55. Iterative PET image reconstruction using convolutional neural network representation10.1109/TMI.2018.2869871 ↗
56. A technique for extracting physiological parameters and the required input function simultaneously from PET image measurements: Theory and simulation study10.1109/4233.681168 ↗
57. A nomogram modeling 11C-MET PET/CT and clinical features in glioma helps predict IDH mutation10.3389/fonc.2020.01200 ↗
58. Maximum likelihood reconstruction for emission tomography10.1109/TMI.1982.4307558 ↗
59. Cheng, X., Navab, N., Ziegler, S.I., and Shi, K. (2013, January 22–26). Direct parametric image reconstruction of rapid multi-tracer PET. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Nagoya, Japan.10.1007/978-3-642-40760-4_20 ↗
60. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
61. Glorot, X., and Bengio, Y. (2010, January 13–15). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, JMLR Workshop and Conference Proceedings, Sardinia, Italy.
62. An interior trust region approach for nonlinear minimization subject to bounds10.1137/0806023 ↗
63. On the convergence of reflective newton methods for large-scale nonlinear minimization subject to bounds10.1007/BF01582221 ↗