What question did this study set out to answer?

The aim is to reduce noise in low-dose μSPECT imaging using deep learning techniques, specifically to evaluate the effectiveness of transfer-learning from PET.

March 28, 2026Open Access

Cross-Modality Deep Learning Denoising for Low-Dose μSPECT: Transfer of PET-Trained U-Net and Diffusion Models

Key Points

The aim is to reduce noise in low-dose μSPECT imaging using deep learning techniques, specifically to evaluate the effectiveness of transfer-learning from PET.
Evaluated two 2D architectures: U-Net and denoising diffusion probabilistic model (DDPM).
Used pretrained models from PET (mouse and human data) for a zero-shot evaluation in μSPECT.
Compared performance of transfer-learned models against those trained from scratch with limited μSPECT data.
Conducted experiments with in vivo mouse scans at varying counts (10%, 25%, 50% of standard).
Both architectures achieved significant noise reduction in low-count μSPECT images.
Zero-shot PET-pretrained models reduced RMSE by over 25% at the lowest count level.
Transfer-learning provided additional RMSE reductions exceeding 5% compared to zero-shot models.
U-Net demonstrated more robust performance with lower computational costs.

Abstract

Reducing radiation dose in microsingle photon emission computed tomography (μSPECT) is essential to limit adverse biological effects in small animal studies, especially for longitudinal experiments. However, dose reduction increases noise and degrades image quality. While deep learning-based denoising (DL-DN) has shown promise for low-dose imaging, most prior work has focused on positron emission tomography (PET). DL-DN for μSPECT remains largely unexplored. In this study, we evaluate postreconstruction DL-DN for low-count μSPECT using two 2D architectures: a U-Net and a denoising diffusion probabilistic model (DDPM). To mitigate the limited availability of preclinical training data, we investigated transfer-learning from PET, a related molecular imaging modality, using models pretrained on both μPET (mouse) and clinical PET (human) data. These models were evaluated in a zero-shot setting and further adapted to the μSPECT domain via transfer-learning. Their performance was compared to models trained from scratch using varying amounts of μSPECT data (4–32 volumes). The data set consisted of in vivo mouse scans acquired with two tracers at 10%, 25%, and 50% of standard counts. Both architectures achieved meaningful noise reduction and improved quantitative agreement with standard-count references. Zero-shot PET-pretrained models demonstrated cross-modality generalization, reducing root mean squared error (RMSE) by more than 25% at the lowest count level, although residual artifacts remained due to differences between the PET source and μSPECT target domains. Transfer-learning consistently improved performance, yielding additional RMSE reductions exceeding 5% relative to zero-shot models. Its advantage over scratch-training decreased with increasing data set size, with maximal RMSE gains dropping from over 10% for small training sets to below 3% for larger data sets. Overall, the U-Net provided more robust performance with lower computational cost. These results indicate that DL-DN can support dose reduction in μSPECT, and that transfer-learning from PET offers a practical approach to address the small data set sizes common for preclinical settings.

Cross-Modality Deep Learning Denoising for Low-Dose μSPECT: Transfer of PET-Trained U-Net and Diffusion Models

Key Points

Abstract

Cite This Study