Few shots transfer learning for universal SPECT denoising across diverse acquisition protocols

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Highest PSNR of 48.02 and SSIM of 0.9918 in 30v6s protocol

• Primary Outcome: Transfer model achieved superior PSNR and SSIM across all acceleration protocols

• Nnt Or Sensitivity: Transfer model surpassed full-scan results in most clinical evaluation categories

• Confidence Interval: Clinical scores: 4.667 ± 0.508 to 4.800 ± 0.250

Clinical Application

Requires implementation of deep learning infrastructure and training protocols in nuclear medicine departments Relevant to Australian nuclear medicine practice; could improve patient throughput and reduce waiting times while maintaining diagnostic quality under TGA medical device regulations Patients requiring SPECT bone scans where reduced acquisition time is clinically beneficial

Abstract

Objective.Accelerated single photon emission computed tomography (SPECT) imaging, achieved by reducing either the number of projection angles or the acquisition time per angle, enhances clinical workflow efficiency but introduces elevated noise. This study aims to develop and validate a universal DL-based reconstruction framework that effectively generalizes across diverse, clinically-realistic SPECT acceleration protocols by overcoming the data scarcity challenge.Approach.SPECT bone scans from 103 patients were acquired under a standard scan (60 views, 12 s/view, 60v12s) followed by a fast scan using one of five acceleration protocols (60v6s, 60v3s, 30v12s, 30v6s, 16v12s). AU-Net-based reconstruction framework was implemented using three strategies: (1) single model, trained on individual acceleration protocol), (2) base model, trained on aggregated datasets from five acceleration protocols, and (3) transfer model, fine-tuned from the base model for protocol-specific optimization. Pixel-level accuracy and structural similarity were assessed using peak signal-to-noise ratio (PSNR), structural similarity index (SSIM) metrics, and maximum pixel value of lesions. Clinical evaluation of image quality, radionuclide detail, artifacts, and diagnostic confidence was conducted using a 5-point system.Main results.Quantitative evaluation showed the transfer model achieved better PSNR and SSIM across all protocols (highest 48.02 PSNR and 0.9918 SSIM in 30v6 s protocol). Qualitative analysis confirmed enhanced structural fidelity. Clinical evaluations rated the transfer model highest across metrics, with scores of 4.667 ± 0.508 (image quality, 30v12 s), 4.800 ± 0.250 (radionuclide detail, 60v6 s), 1.150 ± 0.173 (artifact reduction, 60v6 s), and 4.800 ± 0.250 (diagnostic confidence, 60v6 s), surpassing full-scan results in most cases.Significance. The proposed transfer learning (TL) framework effectively addressed data scarcity and improved reconstruction performance across diverse SPECT acceleration scenarios. The adoption of a TL strategy mitigates data scarcity by utilizing shared features and fine-tuning for specific protocols. The framework demonstrates potential for integration into fast SPECT workflows, facilitating reliable use across diverse imaging scenarios.

References

1. 1.Pan, B., Pan, J., Gan, K., Shen, Y., Chen, X., Zhong, L., Yang, H., Chen, J., Xie, L., Guo, W., Li, H., & Gong, N. J. (2026). Few shots transfer learning for universal SPECT denoising across diverse acquisition protocols. Physics in Medicine and Biology. https://doi.org/10.1088/1361-6560/ae5eb8