Introducing a secondary segmentation to construct a radiomics model for pulmonary tuberculosis cavities.

PURPOSE: Accurate segmentation (separating diseased portions of the lung from normal appearing lung) is a challenge in radiomic studies of non-neoplastic diseases, such as pulmonary tuberculosis (PTB). In this study, we developed a segmentation method, applicable to chest X-rays (CXR), that can eliminate the need for precise disease delineation, and that is effective for constructing radiomic models for automatic PTB cavity classification. METHODS: This retrospective study used a dataset of 266 posteroanterior CXR of patients diagnosed with laboratory confirmed PTB. The lungs were segmented using a U-net-based in-house automatic segmentation model. A secondary segmentation was developed using a sliding window, superimposed on the primary lung segmentation. Pyradiomics was used for feature extraction from every window which increased the dimensionality of the data, but this allowed us to accurately capture the spread of the features across the lung. Two separate measures (standard-deviation and variance) were used to consolidate the features. Pearson's correlation analysis (with a 0.8 cut-off value) was then applied for dimensionality reduction followed by the construction of Random Forest radiomic models. RESULTS: Two almost identical radiomic signatures consisting of 10 texture features each (9 were the same plus 1 other feature) were identified using the two separate consolidation measures. Two well performing random forest models were constructed from these signatures. The standard-deviation model (AUC = 0.9444 (95% CI, 0.8762; 0.9814)) performed marginally better than the variance model (AUC = 0.9288 (95% CI, 0.9046; 0.9843)). CONCLUSION: The introduction of the secondary sliding window segmentation on CXR could eliminate the need for disease delineation in pulmonary radiomic studies, and it could improve the accuracy of CXR reporting currently regaining prominence as a high-volume screening tool as the developed radiomic models correctly classify cavities from normal CXR.

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.

Quantitative PET in the 2020s: a roadmap.

Positron emission tomography (PET) plays an increasingly important role in research and clinical applications, catalysed by remarkable technical advances and a growing appreciation of the need for reliable, sensitive biomarkers of human function in health and disease. Over the last 30 years, a large amount of the physics and engineering effort in PET has been motivated by the dominant clinical application during that period, oncology. This has led to important developments such as PET/CT, whole-body PET, 3D PET, accelerated statistical image reconstruction, and time-of-flight PET. Despite impressive improvements in image quality as a result of these advances, the emphasis on static, semi-quantitative 'hot spot' imaging for oncologic applications has meant that the capability of PET to quantify biologically relevant parameters based on tracer kinetics has not been fully exploited. More recent advances, such as PET/MR and total-body PET, have opened up the ability to address a vast range of new research questions, from which a future expansion of applications and radiotracers appears highly likely. Many of these new applications and tracers will, at least initially, require quantitative analyses that more fully exploit the exquisite sensitivity of PET and the tracer principle on which it is based. It is also expected that they will require more sophisticated quantitative analysis methods than those that are currently available. At the same time, artificial intelligence is revolutionizing data analysis and impacting the relationship between the statistical quality of the acquired data and the information we can extract from the data. In this roadmap, leaders of the key sub-disciplines of the field identify the challenges and opportunities to be addressed over the next ten years that will enable PET to realise its full quantitative potential, initially in research laboratories and, ultimately, in clinical practice.

Experimental evaluation of the dosimetric impact of intrafraction prostate rotation using film measurement with a 6DoF robotic arm.

PURPOSE: Tumor motion during radiotherapy can cause a reduction in target dose coverage and an increase in healthy tissue exposure. Tumor motion is not strictly translational and often exhibits complex six degree-of-freedom (6DoF) translational and rotational motion. Although the dosimetric impact of prostate tumor translational motion is well investigated, the dosimetric impact of 6DoF motion has only been studied with simulations or dose reconstruction. This study aims to experimentally quantify the dose error caused by 6DoF motion. The experiment was designed to test the hypothesis that 6DoF motion would cause larger dose errors than translational motion alone through gamma analyses of two-dimensional film measurements. METHODS: Four patient-measured intrafraction prostate motion traces and four VMAT 7.25 Gy/Fx SBRT treatment plans were selected for the experiment. The traces represented typical motion patterns, including small-angle rotations (<4°), transient movement, persistent excursion, and erratic rotations (>6°). Gafchromic film was placed inside a custom-designed phantom, held by a high-precision 6DoF robotic arm for dose measurements in the coronal plane during treatment delivery. For each combination of the motion trace and treatment plan, two film measurements were made, one with 6DoF motion and the other with the three-dimensional (3D) translation components of the same trace. A gamma pass rate criteria of 2% relative dose/2 mm distance-to-agreement was used in this study and evaluated for each measurement with respect to the static reference film. Two test thresholds, 90% and 50% of the reference dose, were applied to investigate the difference in dose coverage for the PTV region and surrounding areas, respectively. The hypothesis was tested using a Wilcoxon signed-rank test. RESULTS: For each of the 16 plan and motion trace pairs, a reduction in the gamma pass rate was observed for 6DoF motion compared with 3D translational motion. With 90% gamma-test threshold, the reduction was 5.8% ± 7.1% (P < 0.01). With 50% gamma-test threshold, the reduction was 4.1% ± 4.8% (P < 0.01). CONCLUSION: For the first time, the dosimetric impact of intrafraction prostate rotation during SBRT treatment was measured experimentally. The experimental results support the hypothesis that 6DoF tumor motion causes higher dose error than translation motion alone.

A six-degree-of-freedom robotic motion system for quality assurance of real-time image-guided radiotherapy.

In this study we develop and characterise a six degree-of-freedom (6 DoF) robotic motion system for quality assurance of real-time image-guided radiotherapy techniques. The system consists of a commercially available robotic arm, an acrylic phantom with embedded Calypso markers, a custom base plate to mount the robot to the treatment couch, and control software implementing the appropriate sequence of transformations to reproduce measured tumour motion traces. The robotic motion system was evaluated in terms of the set-up and motion trace repeatability, static localization accuracy and dynamic localization accuracy. Four prostate, two liver and three lung motion traces, representing a range of tumor motion trajectories recorded in real patient treatments, were executed using the robotic motion system and compared with motion measurements from the clinical Calypso motion tracking system. System set-up and motion trace repeatability was better than 0.5 deg and 0.3 mm for rotation and translation, respectively. The static localization accuracy of the robotic motion system in the LR, SI and AP directions was 0.09 mm, 0.08 mm and 0.02 mm for translations, respectively, and 0.2°, 0.06° and 0.06° for rotations, respectively. The dynamic localization accuracy of the robotic motion system was <0.2 mm and <0.6° for translations and rotations, respectively. Thus, we have demonstrated the ability to accurately mimic rigid-body tumor motion using a robotically controlled phantom to provide precise geometric QA for advanced radiotherapy delivery approaches.

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.