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 physicsbased approach. A convolutional neural network is then trained to segment this initial estimate into different regions. Predefined 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 transmissionless AC and motivate further evaluation.

Investigating the limited performance of a deep-learning-based SPECT denoising approach: an observer-study-based characterization

“…27 Moreover, recent studies are investigating the evaluation of DL-based imaging methods for nuclear medicine on specific clinical tasks. 28,29 In this context, the proposed observer study-based characterization can be used to investigate the task performance for individual signal properties. For example, we evaluated a DL-based transmission-less attenuation compensation method for SPECT on the task of defect detection.…”

Ideal-observer computation with anthropomorphic phantoms using Markov Chain Monte Carlo

“…The proposed approach has multiple applications in addition to computing the IO. This includes generating phantom populations for virtual clinical trials and other image-quality evaluation studies [13,14,15,16,17]. Another application is in simulation-guided deep learning approaches that provide the advantage of using patient populations with known ground truth, which can then be used for training [18].…”

Development of attenuation correction methods using deep learning in brain‐perfusion single‐photon emission computed tomography

“…Deep learning studies on SPECT have shown promise for improving diagnostic accuracy, 12 reducing acquisition time, 13 reducing image noise at low doses, 14 and enabling automatic segmentation 15 . In terms of AC, deep learning has been used to generate attenuation maps from non‐attenuation‐corrected (NAC) images in myocardial‐perfusion SPECT 16,17 . To generate attenuation maps, Shi et al 16 .…”

“…To generate attenuation maps, Shi et al 16 . used the generative adversarial network (GAN) to train both NAC images reconstructed from photopeak window and scatter window data, and Yu et al 17 . used convolutional neural network (CNN) to train NAC images reconstructed from scatter window data only.…”