Ultrafast Multi-tracer Total-body PET Imaging Using a Transformer-Based Deep Learning Model

Article Article scientifique Article Ultrafast Multi-tracer Total-body PET Imaging Using a Transformer-Based Deep Learning Model eng 2025-08-29 author Sun Hao School of Biomedical Engineering, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China (H.S., W.Y., L.L.); Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH‑1211 Geneva, Switzerland (H.S., A.S., Y.S., C.E.D., C.I., H.Z.); Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China (H.S., W.Y., L.L.); Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China (H.S., W.Y., L.L.). 418909 author Sanaat Amirhossein 0000-0001-8437-2060 Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH‑1211 Geneva, Switzerland (H.S., A.S., Y.S., C.E.D., C.I., H.Z.). 919308 Département de radiologie et informatique médicale (RADIO) author Yi Wenxiang School of Biomedical Engineering, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China (H.S., W.Y., L.L.); Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China (H.S., W.Y., L.L.); Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China (H.S., W.Y., L.L.). author Salimi Yazdan 0000-0002-1233-9576 Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH‑1211 Geneva, Switzerland (H.S., A.S., Y.S., C.E.D., C.I., H.Z.). 943941 Département de radiologie et informatique médicale (RADIO) author Huang Yanchao Laboratory for Quality Control and Evaluation of Radiopharmaceuticals, Department of Nuclear Medicine, Nanfang Hospital Southern Medical University, Guangzhou 510515, China (Y.H., H.W.). author Decorads Charles-Edouard Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH‑1211 Geneva, Switzerland (H.S., A.S., Y.S., C.E.D., C.I., H.Z.). 419147 author Castarede Inès Mariam Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH‑1211 Geneva, Switzerland (H.S., A.S., Y.S., C.E.D., C.I., H.Z.). 936497 author Wu Hubing Laboratory for Quality Control and Evaluation of Radiopharmaceuticals, Department of Nuclear Medicine, Nanfang Hospital Southern Medical University, Guangzhou 510515, China (Y.H., H.W.). author Lu Lijun School of Biomedical Engineering, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China (H.S., W.Y., L.L.); Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China (H.S., W.Y., L.L.); Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China (H.S., W.Y., L.L.); Pazhou Lab, Guangzhou 510330, China (L.L.). author Zaidi Habib 0000-0001-7559-5297 Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH‑1211 Geneva, Switzerland (H.S., A.S., Y.S., C.E.D., C.I., H.Z.); Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, 9700 RB Groningen, Netherlands (H.Z.); Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark (H.Z.); University Research and Innovation Center, Óbuda University, Budapest, Hungary (H.Z.). Electronic address: habib.zaidi@hcuge.ch. 98447 Département de radiologie et informatique médicale (RADIO) 7499-7512 10.1016/j.acra.2025.08.015 40885633 1076-6332 https://www.sciencedirect.com/science/article/pii/S1076633225007524 Background: Reducing PET scan acquisition time to minimize motion-related artifacts and improving patient comfort is always demanding. This study proposes a deep-learning framework for synthesizing diagnostic-quality PET images from ultrafast scans in multi-tracer total-body PET imaging. Methods: A retrospective analysis was conducted on clinical uEXPLORER PET/CT datasets from a single institution, including [18 F]FDG (N=50), [18 F]FAPI (N=45) and [68 Ga]FAPI (N=60) studies. Standard 300-s acquisitions were performed for each patient, with ultrafast scan PET images (3, 6, 15, 30, and 40 s) generated through list-mode data truncation. We developed two variants of a 3D SwinUNETR-V2 architecture: Model 1 (PET-only input) and Model 2 (PET+CT fusion input). The proposed methodology was trained and tested on all three datasets using 5-fold cross-validation. Results: The proposed Model 1 and Model 2 significantly enhanced subjective image quality and lesion detectability in multi-tracer PET images compared to the original ultrafast scans. Model 1 and Model 2 also improved objective image quality metrics. For the [¹⁸F]FDG datasets, both approaches improved peak signal-to-noise ratio (PSNR) metrics across ultra-short acquisitions: 3 s: 48.169±6.121 (Model 1) vs. 48.123±6.103 (Model 2) vs. 44.092±7.508 (ultrafast), p < 0.001; 6 s: 48.997±5.960 vs. 48.461±5.897 vs. 46.503±7.190, p < 0.001; 15 s: 50.310±5.674 vs. 50.042±5.734 vs. 49.331±6.732, p < 0.001. Conclusion: The proposed Model 1 and Model 2 effectively enhance image quality of multi-tracer total-body PET scans with ultrafast acquisition times. The predicted PET images demonstrate comparable performance in terms of image quality and lesion detectability. Deep learning Lesion detectability Multi-tracer imaging Total-body PET Ultrafast imaging Dewey 616.0757 Swiss National Science Foundation Deep learning-assisted improvement of image quality and quantitative accuracy in hybrid PET/CT imaging 10002941 CH Projects 62 Département de radiologie et informatique médicale 227 false 287 Imagerie Médicale (TEP et TEMP) 542 Academic radiology 32 12 e33fc8a8-63c3-4c28-8975-1be034bb367a Article (Accepted version) Public AcadRadiol2025_TB.pdf 9813158 application/pdf CC BY-4.0 9e06624675bbe4659f83b9f9f3f6dd9d68565839bd3778074ca3bcfc194ae671 c7a47255-7d6c-41d2-89b6-408f90c6c8aa Supplemental data Public 1-s2.0-S1076633225007524-mmc1.pdf 9502882 application/pdf 4425f0cff661ac1385dfe08b35eb2c9d7fd17676ea84272f40c903553168e69c openAccess Faculté de médecine / Section de médecine clinique / Département de radiologie et informatique médicale

Title	Published in	Year	Views	Downloads

Ultrafast Multi-tracer Total-body PET Imaging Using a Transformer-Based Deep Learning Model	Academic radiology	2025	22	150
Proximal tibiofibular synostosis in HDP SPECT/CT bone scan: A case report	Radiology case reports	2025	6	116

Archive ouverte UNIGE

Decorads, Charles-Edouard