Dual-Domain Coarse-to-Fine Progressive Estimation Network for Simultaneous Denoising, Limited-View Reconstruction, and Attenuation Correction of Cardiac SPECT

TL;DR

This work tackles simultaneous low-dose denoising, limited-view reconstruction, and CT-free attenuation correction in cardiac SPECT by introducing DuDoCFNet, a dual-domain cascaded framework that fuses projection-domain and image-domain features via multi-layer fusion. The method uses two-stage progressive learning in both projection (TSP-Net) and image (BDA-Net) domains to achieve coarse-to-fine estimation of the full-dose/fuller-view projections $\hat{P}_{FDFV}$ and μ-maps $\hat{\mu}$, which feed a 30-iteration ML-EM reconstruction for AC SPECT. On clinical data, DuDoCFNet outperforms single-task and prior multi-task baselines in predicting projections, μ-maps, and AC images, with strong boundary accuracy and robustness across low-dose levels and iteration counts. The approach demonstrates the practical potential to enable accurate, CT-free attenuation correction and accelerated cardiac SPECT imaging, with implications for reduced radiation exposure and hardware requirements.

Abstract

Single-Photon Emission Computed Tomography (SPECT) is widely applied for the diagnosis of coronary artery diseases. Low-dose (LD) SPECT aims to minimize radiation exposure but leads to increased image noise. Limited-view (LV) SPECT, such as the latest GE MyoSPECT ES system, enables accelerated scanning and reduces hardware expenses but degrades reconstruction accuracy. Additionally, Computed Tomography (CT) is commonly used to derive attenuation maps ($μ$-maps) for attenuation correction (AC) of cardiac SPECT, but it will introduce additional radiation exposure and SPECT-CT misalignments. Although various methods have been developed to solely focus on LD denoising, LV reconstruction, or CT-free AC in SPECT, the solution for simultaneously addressing these tasks remains challenging and under-explored. Furthermore, it is essential to explore the potential of fusing cross-domain and cross-modality information across these interrelated tasks to further enhance the accuracy of each task. Thus, we propose a Dual-Domain Coarse-to-Fine Progressive Network (DuDoCFNet), a multi-task learning method for simultaneous LD denoising, LV reconstruction, and CT-free $μ$-map generation of cardiac SPECT. Paired dual-domain networks in DuDoCFNet are cascaded using a multi-layer fusion mechanism for cross-domain and cross-modality feature fusion. Two-stage progressive learning strategies are applied in both projection and image domains to achieve coarse-to-fine estimations of SPECT projections and CT-derived $μ$-maps. Our experiments demonstrate DuDoCFNet's superior accuracy in estimating projections, generating $μ$-maps, and AC reconstructions compared to existing single- or multi-task learning methods, under various iterations and LD levels. The source code of this work is available at https://github.com/XiongchaoChen/DuDoCFNet-MultiTask.

Figures (10)

• Figure 1: Overview of the Dual-Domain Coarse-To-Fine Progressive Network (DuDoCFNet). In each iteration, DuDoCFNet employs a Two-Stage Progressive Network (TSP-Net) in the projection domain for denoising and restoration of the LD and LV projections, and a Boundary-Aware Network (BDA-Net) in the image domain for predicting $\mu$-maps. All the TSP-Nets and BDA-Nets are cascaded to enable cross-domain and cross-modality feature fusion. The predicted projection and $\mu$-map of the last iteration are employed as the final prediction outputs of DuDoCFNet.
• Figure 2: Two-Stage Progressive Network (TSP-Net). In Stage 1, a U-Net-like structure is utilized to achieve the LV restoration. The auxiliary anatomical features are fed into multiple downsampling layers as the multi-layer fusion (MLF) mechanism. Cross-Domain Feature Fusion (CDF) modules recalibrate the channel weights for adaptive feature fusion. A non-downsampling module is employed in Stage 2 for the LD denoising.
• Figure 3: Boundary-Aware Network (BDA-Net). A shared encoder and two task-specific decoders are utilized to estimate a coarse $\mu$-map and its boundary image. Cross-domain features are embedded in multiple downsampling layers as the multi-level fusion. The estimated $\mu$-map and boundary image are jointly fed into a Spatial Boundary Enhancement (SBE) module to enhance the boundary accuracy of the final refined $\mu$-map.
• Figure 4: Predicted FD and FV projections displayed in the central-column angle, bottom-column angle, and side view. White arrows denote the regions with over- or under-estimated projection intensities. NMSE and SSIM between the predicted and ground-truth projections are annotated.
• Figure 5: Predicted $\mu$-maps (unit: cm$^{-1}$) with error maps. White arrows denote the $\mu$-map regions with inaccurate estimations. DuDoCFNet demonstrates the most accurate boundary estimations. NMSE and SSIM between the predicted and ground-truth $\mu$-maps are annotated.