Reduction of scan duration and radiation dose in cerebral CT perfusion imaging of acute stroke using a recurrent neural network.

Objective. Cerebral CT perfusion (CTP) imaging is most commonly used to diagnose acute ischaemic stroke and support treatment decisions. Shortening CTP scan duration is desirable to reduce the accumulated radiation dose and the risk of patient head movement. In this study, we present a novel application of a stochastic adversarial video prediction approach to reduce CTP imaging acquisition time.Approach. A variational autoencoder and generative adversarial network (VAE-GAN) were implemented in a recurrent framework in three scenarios: to predict the last 8 (24 s), 13 (31.5 s) and 18 (39 s) image frames of the CTP acquisition from the first 25 (36 s), 20 (28.5 s) and 15 (21 s) acquired frames, respectively. The model was trained using 65 stroke cases and tested on 10 unseen cases. Predicted frames were assessed against ground-truth in terms of image quality and haemodynamic maps, bolus shape characteristics and volumetric analysis of lesions.Main results. In all three prediction scenarios, the mean percentage error between the area, full-width-at-half-maximum and maximum enhancement of the predicted and ground-truth bolus curve was less than 4 ± 4%. The best peak signal-to-noise ratio and structural similarity of predicted haemodynamic maps was obtained for cerebral blood volume followed (in order) by cerebral blood flow, mean transit time and time to peak. For the 3 prediction scenarios, average volumetric error of the lesion was overestimated by 7%-15%, 11%-28% and 7%-22% for the infarct, penumbra and hypo-perfused regions, respectively, and the corresponding spatial agreement for these regions was 67%-76%, 76%-86% and 83%-92%.Significance. This study suggests that a recurrent VAE-GAN could potentially be used to predict a portion of CTP frames from truncated acquisitions, preserving the majority of clinical content in the images, and potentially reducing the scan duration and radiation dose simultaneously by 65% and 54.5%, respectively.

Efficient radiation dose reduction in whole-brain CT perfusion imaging using a 3D GAN: performance and clinical feasibility.

Dose reduction in cerebral CT perfusion (CTP) imaging is desirable but is accompanied by an increase in noise that can compromise the image quality and the accuracy of image-based haemodynamic modelling used for clinical decision support in acute ischaemic stroke. The few reported methods aimed at denoising low-dose CTP images lack practicality by considering only small sections of the brain or being computationally expensive. Moreover, the prediction of infarct and penumbra size and location-the chief means of decision support for treatment options-from denoised data has not been explored using these approaches. In this work, we present the first application of a 3D generative adversarial network (3D GAN) for predicting normal-dose CTP data from low-dose CTP data. Feasibility of the approach was tested using real data from 30 acute ischaemic stroke patients in conjunction with low dose simulation. The 3D GAN model was applied to 643voxel patches extracted from two different configurations of the CTP data-frame-based and stacked. The method led to whole-brain denoised data being generated for haemodynamic modelling within 90 s. Accuracy of the method was evaluated using standard image quality metrics and the extent to which the clinical content and lesion characteristics of the denoised CTP data were preserved. Results showed an average improvement of 5.15-5.32 dB PSNR and 0.025-0.033 structural similarity index (SSIM) for CTP images and 2.66-3.95 dB PSNR and 0.036-0.067 SSIM for functional maps at 50% and 25% of normal dose using GAN model in conjunction with a stacked data regime for image synthesis. Consequently, the average lesion volumetric error reduced significantly (p-value <0.05) by 18%-29% and dice coefficient improved significantly by 15%-22%. We conclude that GAN-based denoising is a promising practical approach for reducing radiation dose in CTP studies and improving lesion characterisation.

Markerless motion estimation for motion-compensated clinical brain imaging.

Motion-compensated brain imaging can dramatically reduce the artifacts and quantitative degradation associated with voluntary and involuntary subject head motion during positron emission tomography (PET), single photon emission computed tomography (SPECT) and computed tomography (CT). However, motion-compensated imaging protocols are not in widespread clinical use for these modalities. A key reason for this seems to be the lack of a practical motion tracking technology that allows for smooth and reliable integration of motion-compensated imaging protocols in the clinical setting. We seek to address this problem by investigating the feasibility of a highly versatile optical motion tracking method for PET, SPECT and CT geometries. The method requires no attached markers, relying exclusively on the detection and matching of distinctive facial features. We studied the accuracy of this method in 16 volunteers in a mock imaging scenario by comparing the estimated motion with an accurate marker-based method used in applications such as image guided surgery. A range of techniques to optimize performance of the method were also studied. Our results show that the markerless motion tracking method is highly accurate (<2 mm discrepancy against a benchmarking system) on an ethnically diverse range of subjects and, moreover, exhibits lower jitter and estimation of motion over a greater range than some marker-based methods. Our optimization tests indicate that the basic pose estimation algorithm is very robust but generally benefits from rudimentary background masking. Further marginal gains in accuracy can be achieved by accounting for non-rigid motion of features. Efficiency gains can be achieved by capping the number of features used for pose estimation provided that these features adequately sample the range of head motion encountered in the study. These proof-of-principle data suggest that markerless motion tracking is amenable to motion-compensated brain imaging and holds good promise for a practical implementation in clinical PET, SPECT and CT systems.