Background There has been a recent increased interest in monitoring health using wearable sensor technologies; however, few have focused on breathing. The ability to monitor breathing metrics may have indications both for general health as well as respiratory conditions such as asthma, where long-term monitoring of lung function has shown promising utility. Objective In this paper, we explore a long short-term memory (LSTM) architecture and predict measures of interbreath intervals, respiratory rate, and the inspiration-expiration ratio from a photoplethysmogram signal. This serves as a proof-of-concept study of the applicability of a machine learning architecture to the derivation of respiratory metrics. Methods A pulse oximeter was mounted to the left index finger of 9 healthy subjects who breathed at controlled respiratory rates. A respiratory band was used to collect a reference signal as a comparison. Results Over a 40-second window, the LSTM model predicted a respiratory waveform through which breathing metrics could be derived with a bias value and 95% CI. Metrics included inspiration time (–0.16 seconds, –1.64 to 1.31 seconds), expiration time (0.09 seconds, –1.35 to 1.53 seconds), respiratory rate (0.12 breaths per minute, –2.13 to 2.37 breaths per minute), interbreath intervals (–0.07 seconds, –1.75 to 1.61 seconds), and the inspiration-expiration ratio (0.09, –0.66 to 0.84). Conclusions A trained LSTM model shows acceptable accuracy for deriving breathing metrics and could be useful for long-term breathing monitoring in health. Its utility in respiratory disease (eg, asthma) warrants further investigation.

Purpose Interventional treatments of aneurysms in the carotid artery are increasingly being supplemented with three‐dimensional (3D) x‐ray imaging. The 3D imaging provides additional information on device sizing and stent malapposition during the procedure. Standard 3D x‐ray image acquisition is a one‐size fits all model, exposing patients to additional radiation and results in images that may have cardiac‐induced motion blur around the artery. Here, we investigate the potential of a novel dynamic imaging technique Adaptive CaRdiac cOne BEAm computed Tomography (ACROBEAT) to personalize image acquisition by adapting the gantry velocity and projection rate in real‐time to changes in the patient’s electrocardiogram (ECG) trace. Methods We compared the total number of projections acquired, estimated carotid artery widths and image quality between ACROBEAT and conventional (single rotation fixed gantry velocity and acquisition rate, no ECG‐gating) scans in a simulation study and a proof‐of‐concept physical phantom experimental study. The simulation study dataset consisted of an XCAT digital software phantom programmed with five patient‐measured ECG traces and artery motion curves. The ECG traces had average heart rates of 56, 64, 76, 86, and 100 bpm. To validate the concept experimentally, we designed and manufactured the physical phantom from an 8‐mm diameter silicon rubber tubing cast into Phytagel. An artery motion curve and the ECG trace with an average heart rate of 56 bpm was passed through the phantom. To implement ACROBEAT on the Siemens ARTIS pheno angiography system for the proof‐of‐concept experimental study, the Siemens Test Automation Control System was used. The total number of projections acquired and estimated carotid artery widths were compared between the ACROBEAT and conventional scans. As the ground truth was available for the simulation studies, the image quality metrics of Root Mean Square Error (RMSE) and Structural Similarity Index (SSIM) were also utilized to assess image quality. Results In the simulation study, on average, ACROBEAT reduced the number of projections acquired by 63%, reduced carotid width estimation error by 65%, reduced RMSE by 11% and improved SSIM by 27% compared to conventional scans. In the proof‐of‐concept experimental study, ACROBEAT enabled a 60% reduction in the number of projections acquired and reduced carotid width estimation error by 69% compared to a conventional scan. Conclusion A simulation and proof‐of‐concept experimental study was completed applying a novel dynamic imaging protocol, ACROBEAT, to imaging the carotid artery. The ACROBEAT results showed significantly improved image quality with fewer projections, offering potential applications to intracranial interventional procedures negatively affected by cardiac motion.

No abstract

An important factor when considering the use of interventional cone beam computed tomography (CBCT) imaging during cardiac procedures is the trade-off between imaging dose and image quality. Accordingly, Adaptive CaRdiac cOne BEAm computed Tomography (ACROBEAT) presents an alternative acquisition method, adapting the gantry velocity and projection rate of CBCT imaging systems in accordance with a patient's electrocardiogram (ECG) signal in real-time. The aim of this study was to experimentally investigate that ACROBEAT acquisitions deliver improved image quality compared to conventional cardiac CBCT imaging protocols with fewer projections acquired. Methods: The Siemens ARTIS pheno (Siemens Healthcare, GmbH, Germany), a robotic CBCT Carm system, was used to compare ACROBEAT with a commercially available conventional cardiac imaging protocol that utilizes multisweep retrospective ECG-gated acquisition. For ACROBEAT, real-time control of the gantry position was enabled through the Siemens Test Automation Control system. ACROBEAT and conventional image acquisitions of the CIRS Dynamic Cardiac Phantom were performed, using five patient-measured ECG traces. The traces had average heart rates of 56, 64, 76, 86, and 100 bpm. The total number of acquired projections was compared between the ACROBEAT and conventional acquisition methods. The image quality was assessed via the contrastto-noise ratio (CNR), structural similarity index (SSIM), and root-mean square error (RMSE). Results: Compared to the conventional protocol, ACROBEAT reduced the total number of projections acquired by 90%. The visual image quality provided by the ACROBEAT acquisitions, across all traces, matched or improved compared to conventional acquisition and was independent of the patient's heart rate. Across all traces, ACROBEAT averaged 1.4 times increase in the CNR, a 23% increase in the SSIM and a 29% decrease in the RMSE compared to conventional and was independent of the patient's heart rate. Conclusion: Adaptive patient imaging is feasible on a clinical robotic CBCT system, delivering higher quality images while reducing the number of projections acquired by 90% compared to conventional cardiac imaging protocols.

No abstract

Objectives: To conduct a systematic survey of published techniques for automated diagnosis and prognosis of COVID-19 diseases using medical imaging, assessing the validity of reported performance and investigating the proposed clinical use-case. To conduct a scoping review into the authors publishing such work. Methods: The Scopus database was queried and studies were screened for article type, and minimum source normalized impact per paper and citations, before manual relevance assessment and a bias assessment derived from a subset of the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). The number of failures of the full CLAIM was adopted as a surrogate for risk-of-bias. Methodological and performance measurements were collected from each technique. Each study was assessed by one author. Comparisons were evaluated for significance with a two-sided independent t-test. Findings: Of 1002 studies identified, 390 remained after screening and 81 after relevance and bias exclusion. The ratio of exclusion for bias was 71%, indicative of a high level of bias in the field. The mean number of CLAIM failures per study was 8.3 ± 3.9 [1,17] (mean ± standard deviation [min,max]). 58% of methods performed diagnosis versus 31% prognosis. Of the diagnostic methods, 38% differentiated COVID-19 from healthy controls. For diagnostic techniques, area under the receiver operating curve (AUC) = 0.924 ± 0.074 [0.810,0.991] and accuracy = 91.7% ± 6.4 [79.0,99.0]. For prognostic techniques, AUC = 0.836 ± 0.126 [0.605,0.980] and accuracy = 78.4% ± 9.4 [62.5,98.0]. CLAIM failures did not correlate with performance, providing confidence that the highest results were not driven by biased papers. Deep learning techniques reported higher AUC (p < 0.05) and accuracy (p < 0.05), but no difference in CLAIM failures was identified. Interpretation: A majority of papers focus on the less clinically impactful diagnosis task, contrasted with prognosis, with a significant portion performing a clinically unnecessary task of differentiating COVID-19 from healthy. Authors should consider the clinical scenario in which their work would be deployed when developing techniques. Nevertheless, studies report superb performance in a potentially impactful application. Future work is warranted in translating techniques into clinical tools. Supplementary Information The online version contains supplementary material available at 10.1007/s13246-021-01093-0.

The ability to continuously monitor breathing metrics may have indications for general health as well as respiratory conditions such as asthma. However, few studies have focused on breathing due to a lack of available wearable technologies. To examine the performance of two machine learning algorithms in extracting breathing metrics from a finger-based pulse oximeter, which is amenable to long-term monitoring. Methods: Pulse oximetry data were collected from 11 healthy and 11 with asthma subjects who breathed at a range of controlled respiratory rates. U-shaped network (U-Net) and Long Short-Term Memory (LSTM) algorithms were applied to the data, and results compared against breathing metrics derived from respiratory inductance plethysmography measured simultaneously as a reference. Results: The LSTM vs. U-Net model provided breathing metrics which were strongly correlated with those from the reference signal (all p < 0.001, except for inspiratory: expiratory ratio). The following absolute mean bias (95% confidence interval) values were observed (in seconds): inspiration time 0.01(−2.31, 2.34) vs. −0.02(−2.19, 2.16), expiration time −0.19(−2.35, 1.98) vs. −0.24(−2.36, 1.89), and inter-breath intervals −0.19(−2.73, 2.35) vs. −0.25(2.76, 2.26). The inspiratory:expiratory ratios were −0.14(−1.43, 1.16) vs. −0.14(−1.42, 1.13). Respiratory rate (breaths per minute) values were 0.22(−2.51, 2.96) vs. 0.29(−2.54, 3.11). While percentage bias was low, the 95% limits of agreement was high (~35% for respiratory rate). Conclusion: Both machine learning models show strong correlation and good comparability with reference, with low bias though wide variability for deriving breathing metrics in asthma and health cohorts. Future efforts should focus on improvement of performance of these models, e.g., by increasing the size of the training dataset at the lower breathing rates.

Soft-polymer fibers allow strong conformal contact with the skin and are extremely sensitive for deformation, despite high propagation loss. This enables pulse wave velocities measurements. Blood pressure can then be inferred using the Moens-Kortweg model.