Acquisition Time-Specific Deep Learning-Guided Image Quality Restoration in Accelerated I-123 DaTSCAN Brain SPECT on a Ring-Shaped CZT-Based Camera.
Acquisition Time-Specific Deep Learning-Guided Image Quality Restoration in Accelerated I-123 DaTSCAN Brain SPECT on a Ring-Shaped CZT-Based Camera.
Where did the research take place?
The study site has not been established. Author addresses may differ from where the research occurred.
Geneva, CH · Author affiliation
Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland.Location evidence
Groningen, NL · Author affiliation
Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, Netherlands. habib.zaidi@hcuge.ch.Location evidence
Odense, DK · Author affiliation
Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark. habib.zaidi@hcuge.ch.Location evidence
Óbuda, HU · Author affiliation
University Research and Innovation Center, Óbuda University, Budapest, Hungary. habib.zaidi@hcuge.ch.Location evidence
Budapest, HU · Author affiliation
University Research and Innovation Center, Óbuda University, Budapest, Hungary. habib.zaidi@hcuge.ch.Location evidence
A plain-language reading has not been prepared for this paper yet.
Original abstract
Brain single-photon emission computed tomography (SPECT) imaging using I-123 DaTSCAN is an effective tool for the diagnosis and follow-up of Parkinson disease. Reducing acquisition time decreases the likelihood of patient motion, improves patient comfort, and increases scanner throughput. However, shorter acquisition times often result in degraded image quality with reduced diagnostic value. This study aimed to use deep learning (DL) approaches to enhance the image quality of accelerated SPECT DaTSCAN acquisitions. A total of 85 patients were scanned on a CZT-based GE StarGuide scanner with a standard acquisition time of 15 min. To simulate fast acquisition protocols, raw list-mode data were retrospectively undersampled to represent 20%, 25%, and 50% of the original acquisition time and then reconstructed using the clinical routine protocol. A modified U-Net DL architecture incorporating attention and transformer mechanisms was trained to convert the low-count images into full-time equivalents. The output images were compared to full-time reference images using subjective image quality assessment by nuclear medicine physicians as well as region-wise and voxel-wise quantitative metrics on the test set. Both voxel-wise and region-wise metrics showed significant improvement when using the DL models for all fast acquisition times. Subjective image quality evaluations confirmed that the DL-predicted images were noticeably superior to the original low-count reconstructions in terms of perceived image quality and diagnostic confidence. The mean absolute percentage error (MAPE) was reduced from ~ 30 to ~ 18% for fast 1/5 acquisition time images and from ~ 26 to ~ 16% for 1/4 acquisition time images. Our acquisition time-specific deep learning models effectively restore information loss in fast SPECT acquisitions and reduce image noise, without compromising diagnostic value. The models offer a promising approach for faster, patient-friendly brain SPECT imaging without sacrificing image quality or quantitative accuracy.