Segmentation-free PVC for Cardiac SPECT using a Densely-connected Multi-dimensional Dynamic Network

TL;DR

This paper introduces a novel deep learning method for partial volume correction in cardiac SPECT imaging that does not require anatomical segmentation, using a densely-connected multi-dimensional dynamic network to improve image quality and quantitative accuracy.

Contribution

The work presents a segmentation-free deep learning approach with a dynamic mechanism for PVC in cardiac SPECT, eliminating the need for anatomical registration and segmentation.

Findings

The proposed network outperforms non-dynamic versions in PVC accuracy.

It achieves statistically comparable IMBV measurements to anatomical-guided methods.

The method demonstrates promising results on canine cardiac SPECT data.

Abstract

In nuclear imaging, limited resolution causes partial volume effects (PVEs) that affect image sharpness and quantitative accuracy. Partial volume correction (PVC) methods incorporating high-resolution anatomical information from CT or MRI have been demonstrated to be effective. However, such anatomical-guided methods typically require tedious image registration and segmentation steps. Accurately segmented organ templates are also hard to obtain, particularly in cardiac SPECT imaging, due to the lack of hybrid SPECT/CT scanners with high-end CT and associated motion artifacts. Slight mis-registration/mis-segmentation would result in severe degradation in image quality after PVC. In this work, we develop a deep-learning-based method for fast cardiac SPECT PVC without anatomical information and associated organ segmentation. The proposed network involves a densely-connected multi-dimensional dynamic mechanism, allowing the convolutional kernels to be adapted based on the input images, even after the network is fully trained. Intramyocardial blood volume (IMBV) is introduced as an additional clinical-relevant loss function for network optimization. The proposed network demonstrated promising performance on 28 canine studies acquired on a GE Discovery NM/CT 570c dedicated cardiac SPECT scanner with a 64-slice CT using Technetium-99m-labeled red blood cells. This work showed that the proposed network with densely-connected dynamic mechanism produced superior results compared with the same network without such mechanism. Results also showed that the proposed network without anatomical information could produce images with statistically comparable IMBV measurements to the images generated by anatomical-guided PVC methods, which could be helpful in clinical translation.