A physics and learning-based transmission-less attenuation compensation method for SPECT

Abstract

Attenuation compensation (AC) is a pre-requisite for reliable quantification and beneficial for visual interpretation tasks in single-photon emission computed tomography (SPECT). Typical AC methods require the availability of an attenuation map, which is obtained using a transmission scan, such as a CT scan. This has several disadvantages such as increased radiation dose, higher costs, and possible misalignment between SPECT and CT scans. Also, often a CT scan is unavailable. In this context, we and others are showing that scattered photons in SPECT contain information to estimate the attenuation distribution. To exploit this observation, we propose a physics and learning-based method that uses the SPECT emission data in the photopeak and scatter windows to perform transmission-less AC in SPECT. The proposed method uses data acquired in the scatter window to reconstruct an initial estimate of the attenuation map using a physics-based approach. A convolutional neural network is then trained to segment this initial estimate into different regions. Pre-defined attenuation coefficients are assigned to these regions, yielding the reconstructed attenuation map, which is then used to reconstruct the activity distribution using an ordered subsets expectation maximization (OSEM)-based reconstruction approach. We objectively evaluated the performance of this method using highly realistic simulation studies conducted on the clinically relevant task of detecting perfusion defects in myocardial perfusion SPECT. Our results showed no statistically significant differences between the performance achieved using the proposed method and that with the true attenuation maps. Visually, the images reconstructed using the proposed method looked similar to those with the true attenuation map. Overall, these results provide evidence of the capability of the proposed method to perform transmission-less AC and motivate further evaluation.

Keywords: deep learning; image reconstruction; objective assessment of image quality; single-photon emission computed tomography; transmission-less attenuation compensation.

Fig. 1:

The workflow of the proposed method

Fig. 2:

Schematic of the proposed CNN-based approach to segment the initial estimate of the attenuation map

Fig. 3:

ROC curves obtained using the proposed method, the TAAC method (true attenuation map), and the UAAC (uniform attenuation map) method. The ROC curves of the proposed method and the TAAC method were overlapped. Further, the proposed method outperformed the UAAC method.

Fig. 4:

(a) Representative reconstructed activity images examples using the true attenuation map (middle column) and the proposed method (right column). The upper example was a defect-absent case, while the lower sample was a defect-present case. (b) Zoomed version of the red-boxed regions in (a). Our results show that images generated using the proposed approach were visually similar to those obtained with the TAAC approach.