Evolving operational guidance and experiences for radiology and nuclear medicine facilities in response to and beyond the COVID-19 pandemic.

The resulting pandemic from the novel severe acute respiratory coronavirus 2, SARS-CoV-2 (COVID-19), continues to exert a strain on worldwide health services due to the incidence of hospitalization and mortality associated with infection. The aim of clinical services throughout the period of the pandemic and likely beyond to endemic infections as the situation stabilizes is to enhance safety aspects to mitigate transmission of COVID-19 while providing a high quality of service to all patients (COVID-19 positive and negative) while still upholding excellent medical standards. In order to achieve this, new strategies of clinical service operation are essential. Researchers have published peer-reviewed reference materials such as guidelines, experiences and advice to manage the resulting issues from the unpredictable challenges presented by the pandemic. There is a range of international guidance also from professional medical organizations, including best practice and advice in order to help imaging facilities adjust their standard operating procedures and workflows in line with infection control principles. This work provides a broad review of the main sources of advice and guidelines for radiology and nuclear medicine facilities during the pandemic, and also of rapidly emerging advice and local/national experiences as facilities begin to resume previously canceled non-urgent services as well as effects on imaging research.

Comparison of the performances of machine learning and deep learning in improving the quality of low dose lung cancer PET images.

PURPOSE: To compare the performances of machine learning (ML) and deep learning (DL) in improving the quality of low dose (LD) lung cancer PET images and the minimum counts required. MATERIALS AND METHODS: 33 standard dose (SD) PET images, were used to simulate LD PET images at seven-count levels of 0.25, 0.5, 1, 2, 5, 7.5 and 10 million (M) counts. Image quality transfer (IQT), a ML algorithm that uses decision tree and patch-sampling was compared to two DL networks-HighResNet (HRN) and deep-boosted regression (DBR). Supervised training was performed by training the ML and DL algorithms with matched-pair SD and LD images. Image quality evaluation and clinical lesion detection tasks were performed by three readers. Bias in 53 radiomic features, including mean SUV, was evaluated for all lesions. RESULTS: ML- and DL-estimated images showed higher signal and smaller error than LD images with optimal image quality recovery achieved using LD down to 5 M counts. True positive rate and false discovery rate were fairly stable beyond 5 M counts for the detection of small and large true lesions. Readers rated average or higher ratings to images estimated from LD images of count levels above 5 M only, with higher confidence in detecting true lesions. CONCLUSION: LD images with a minimum of 5 M counts (8.72 MBq for 10 min scan or 25 MBq for 3 min scan) are required for optimal clinical use of ML and DL, with slightly better but more varied performance shown by DL.

Parametric mapping for 11C-metomidate PET-computed tomography imaging in the study of primary aldosteronism.

OBJECTIVE: 11C-metomidate (11C-MTO) PET-computed tomography (CT) imaging has shown good sensitivity and specificity for the classification of bilateral or unilateral overexpression of aldosterone. This work seeks to investigate the usefulness of parametric maps via kinetic modeling of 11C-metomidate data into the clinical diagnosis pathway. METHODS: Twenty-five patients were injected with 172 ± 12 MBq of 11C-metomidate and a dynamic PET scan performed of the adrenal glands. A blood time-activity curve was drawn from a volume of interest in the left ventricle and converted to a plasma time-activity curve. Metabolite correction was performed with a population-based correction. We performed regional-based graphical Patlak analysis to calculate the regional uptake rate constant Ki(REG), and also calculated parametric maps of Ki(VOX) using a voxel-based technique. RESULTS: Comparison of Ki(REG), and the maximum lesion voxel from parametric maps Ki(mVOX) demonstrated a high correlation for all subjects (r2 = 0.96). Ki(mVOX) allowed differentiation between cases of active and inactive unilateral adenoma when compared to bilateral hyperplasia (P < 0.017), a feature not observed with standardized uptake ratios (SUVmax) analysis. Ki(mVOX) demonstrated a poor correlation of 0.68 with SUVmax, indicating the differences through the use of static and dynamic imaging. Three false-negative cases based on SUV analysis indicated that Ki(mVOX) was able to successfully differentiate the clinical presentation for these cases. CONCLUSION: Our work demonstrates that parametric Ki(VOX) was able to successfully differentiate between patients with bilateral hyperplasia and patients with unilateral adrenal adenoma in our cohort and that Ki may be considered be an additional useful metric to SUV in 11C-metomidate PET-CT imaging.

Comparison of metrics for the evaluation of medical segmentations using prostate MRI dataset.

Nine previously proposed segmentation evaluation metrics, targeting medical relevance, accounting for holes, and added regions or differentiating over- and under-segmentation, were compared with 24 traditional metrics to identify those which better capture the requirements for clinical segmentation evaluation. Evaluation was first performed using 2D synthetic shapes to highlight features and pitfalls of the metrics with known ground truths (GTs) and machine segmentations (MSs). Clinical evaluation was then performed using publicly-available prostate images of 20 subjects with MSs generated by 3 different deep learning networks (DenseVNet, HighRes3DNet, and ScaleNet) and GTs drawn by 2 readers. The same readers also performed the 2D visual assessment of the MSs using a dual negative-positive grading of -5 to 5 to reflect over- and under-estimation. Nine metrics that correlated well with visual assessment were selected for further evaluation using 3 different network ranking methods - based on a single metric, normalizing the metric using 2 GTs, and ranking the network based on a metric then averaging, including leave-one-out evaluation. These metrics yielded consistent ranking with HighRes3DNet ranked first then DenseVNet and ScaleNet using all ranking methods. Relative volume difference yielded the best positivity-agreement and correlation with dual visual assessment, and thus is better for providing over- and under-estimation. Interclass Correlation yielded the strongest correlation with the absolute visual assessment (0-5). Symmetric-boundary dice consistently yielded good discrimination of the networks for all three ranking methods with relatively small variations within network. Good rank discrimination may be an additional metric feature required for better network performance evaluation.

Validation of low-dose lung cancer PET-CT protocol and PET image improvement using machine learning.

PURPOSE: To conduct a simplified lesion-detection task of a low-dose (LD) PET-CT protocol for frequent lung screening using 30% of the effective PETCT dose and to investigate the feasibility of increasing clinical value of low-statistics scans using machine learning. METHODS: We acquired 33 SD PET images, of which 13 had actual LD (ALD) PET, and simulated LD (SLD) PET images at seven different count levels from the SD PET scans. We employed image quality transfer (IQT), a machine learning algorithm that performs patch-regression to map parameters from low-quality to high-quality images. At each count level, patches extracted from 23 pairs of SD/SLD PET images were used to train three IQT models - global linear, single tree, and random forest regressions with cubic patch sizes of 3 and 5 voxels. The models were then used to estimate SD images from LD images at each count level for 10 unseen subjects. Lesion-detection task was carried out on matched lesion-present and lesion-absent images. RESULTS: LD PET-CT protocol yielded lesion detectability with sensitivity of 0.98 and specificity of 1. Random forest algorithm with cubic patch size of 5 allowed further 11.7% reduction in the effective PETCT dose without compromising lesion detectability, but underestimated SUV by 30%. CONCLUSION: LD PET-CT protocol was validated for lesion detection using ALD PET scans. Substantial image quality improvement or additional dose reduction while preserving clinical values can be achieved using machine learning methods though SUV quantification may be biased and adjustment of our research protocol is required for clinical use.

Evaluation of Multimodal Algorithms for the Segmentation of Multiparametric MRI Prostate Images.

Prostate segmentation in multiparametric magnetic resonance imaging (mpMRI) can help to support prostate cancer diagnosis and therapy treatment. However, manual segmentation of the prostate is subjective and time-consuming. Many deep learning monomodal networks have been developed for automatic whole prostate segmentation from T2-weighted MR images. We aimed to investigate the added value of multimodal networks in segmenting the prostate into the peripheral zone (PZ) and central gland (CG). We optimized and evaluated monomodal DenseVNet, multimodal ScaleNet, and monomodal and multimodal HighRes3DNet, which yielded dice score coefficients (DSC) of 0.875, 0.848, 0.858, and 0.890 in WG, respectively. Multimodal HighRes3DNet and ScaleNet yielded higher DSC with statistical differences in PZ and CG only compared to monomodal DenseVNet, indicating that multimodal networks added value by generating better segmentation between PZ and CG regions but did not improve the WG segmentation. No significant difference was observed in the apex and base of WG segmentation between monomodal and multimodal networks, indicating that the segmentations at the apex and base were more affected by the general network architecture. The number of training data was also varied for DenseVNet and HighRes3DNet, from 20 to 120 in steps of 20. DenseVNet was able to yield DSC of higher than 0.65 even for special cases, such as TURP or abnormal prostate, whereas HighRes3DNet's performance fluctuated with no trend despite being the best network overall. Multimodal networks did not add value in segmenting special cases but generally reduced variations in segmentation compared to the same matched monomodal network.