Objective To assess whether an artificial intelligence (AI) tool improves the accuracy, speed and confidence of general radiologists, emergency clinicians and radiographers in detecting critical non-contrast CT head (NCCTH) abnormalities and to evaluate its stand-alone performance and factors influencing diagnostic accuracy.Methods and analysis A retrospective dataset of 150 NCCTH (52 normal and 98 with critical abnormalities) was reviewed by 30 readers (10 radiologists, 15 emergency clinicians and 5 radiographers) from four National Health Service trusts. Each interpreted scan is performed unaided and then with the qER EU 2.0 AI tool, separated by a 2-week washout period. Ground truth was established by two neuroradiologists. We measured the AI’s stand-alone performance and its effect on reader accuracy, confidence and speed.Results The qER algorithm showed strong diagnostic performance (area under the receiver operator curve 0.821–0.976). With AI, pooled reader sensitivity for critical abnormalities increased from 82.8% to 89.7% (+6.9%, p<0.001) and for intracranial haemorrhage from 84.6% to 91.6% (+7.0%, p<0.001), while specificity decreased from 84.5% to 78.9% (–5.5%, p=0.046). Reader confidence did not change significantly. Emergency department (ED) clinicians with AI achieved sensitivity similar to unaided radiologists.Conclusion AI assistance increased sensitivity for detecting critical abnormalities on NCCTH but reduced specificity. AI-enabled ED clinicians to achieve diagnostic sensitivity comparable to radiologists, supporting its potential to enhance non-radiologist performance. Further studies are needed to confirm these findings in clinical practice.Trial registration number NCT06018545.

The assessment of mitral regurgitation (MR) using cardiac MRI, particularly Cine MRI, is a promising technique due to its wide availability. However, some of the temporal information available in clinical Cine MRI may not be fully utilised, as it requires detailed temporal analysis across different cardiac views. We propose a new approach to identify MR which automatically extracts 4-dimensional (3D + Time) morphological features from the reconstructed mitral annulus (MA) using Cine long-axis (LAX) views MRI. Our feature extraction involves locating the MA insertion points to derive the reconstructed MA geometry and displacements, resulting in a total of 187 candidate features. We identify the 25 most relevant mitral valve features using minimum-redundancy maximum-relevance (MRMR) feature selection technique. We then apply linear discriminant analysis (LDA) and random forest (RF) model to determine the presence of MR. Both LDA and RF demonstrate good performance, with accuracies of 0.72± 0.05 and 0.73± 0.09 , respectively, in a 5-fold cross-validation analysis. This approach will be incorporated in an automatic tool to identify valvular diseases from Cine MRI by integrating both handcrafted and deep features. Our tool will facilitate the diagnosis of valvular disease from conventional cardiac MRI scans with no additional scanning or image analysis penalty. All code is made available on an open-source basis at: https://github.com/HenryOn2021/MA_Morphological_Features .

Non-contrast CT head scans (NCCTH) are the most frequently requested cross-sectional imaging in the Emergency Department. While AI tools have been developed to detect NCCTH abnormalities, most validation studies compare AI to radiologists, with limited evidence on the impact of AI assistance for other healthcare professionals. To evaluate whether an AI-powered tool improves the accuracy, speed, and confidence of general radiologists, emergency clinicians, and radiographers in detecting critical abnormalities on NCCTH, and to assess the tool’s stand-alone performance and factors influencing diagnostic accuracy and efficiency. A retrospective dataset of 150 NCCTH (52 normal, 98 with critical abnormalities: intracranial haemorrhage, hypodensity, midline shift, mass effect, or skull fracture) was reviewed by 30 readers (10 radiologists, 15 emergency clinicians, 5 radiographers) from four NHS trusts. Each reader interpreted scans first unaided, then with the qER EU 2.0 AI tool, separated by a 2-week washout. Ground truth was established by consensus of two neuroradiologists. We assessed the stand-alone performance of qER and its effect on reader diagnostic accuracy, confidence, and interpretation speed. The qER algorithm demonstrated strong diagnostic performance across most pathology subgroups (AUC 0.821–0.976). With AI assistance, pooled reader sensitivity for critically abnormal scans increased from 82.8% to 89.7% (+6.9%, 95% CI +1.4% to +10.6%, p<0.001), and for intracranial haemorrhage from 84.6% to 91.6% (+7.0%, 95% CI +3.2% to +10.8%, p<0.001), but specificity decreased from 84.5% to 78.9% (–5.5%, 95% CI –11.0% to –0.09%, p=0.046). Reader confidence AUC did not change significantly. ED clinicians with AI achieved sensitivity comparable to unaided radiologists, with no significant change in specificity. AI-assisted interpretation increased reader sensitivity for critical abnormalities but reduced specificity. Notably, AI assistance enabled ED clinicians to reach diagnostic sensitivity similar to unaided radiologists, supporting the potential for AI to extend the diagnostic capabilities of non-radiologists. Further prospective studies are warranted to confirm these findings in real-world settings. This study was funded by Qure.ai via an NHSX Award The study has been approved by the UK Healthcare Research Authority (IRAS 310995, approved 13/12/2022). The use of anonymised retrospective NCCTH has been authorised by Oxford University Hospitals. NCT06018545 . AI-derived algorithms for the detection of pathological findings on non-contrast CT head (NCCTH) images have previously demonstrated strong diagnostic performance when used on retrospective datasets. AI-assisted image interpretation using these algorithms has been shown to enhance the diagnostic performance of general and neuro-radiologists in silico . The potential for AI to enhance the performance of less skilled readers who may encounter and be required to act on these images in clinical practice (e.g. non-specialist radiologists, emergency medicine clinicians and radiographers) is as yet untested, however. This large multicase multireader study demonstrates that AI-assisted image interpretation may be used to enhance the in silico diagnostic performance of Emergency Department physicians to a level comparable to that of general radiologists. This study raises the possibility that AI-assisted image interpretation could be used to assist non-radiologist clinicians in the safe interpretation of NCCTH scans. Further prospective research is required to test this hypothesis in clinical practice and explore the potential for AI-assisted interpretation to support safe discharge of patients with normal or low-risk scans.

Background: Accurate measurements from cardiovascular magnetic resonance (CMR) images require precise positioning of scan planes and elimination of motion artifacts from arrhythmia or breathing. Unidentified or incorrectly managed artifacts degrade image quality, invalidate clinical measurements, and decrease diagnostic confidence. Currently, radiographers must manually inspect each acquired image to confirm diagnostic quality and decide whether reacquisition or a change in sequences is warranted. We aimed to develop artificial intelligence (AI) to provide continuous quality scores across different quality domains, and from these, determine whether cines are clinically adequate, require replanning, or warrant a change in protocol. Methods: A three-dimensional convolutional neural network was trained to predict cine quality graded on a continuous scale by a level 3 CMR expert, focusing separately on planning and motion artifacts. It incorporated four distinct output heads for the assessment of image quality in terms of (a, b, c) 2-, 3- and 4-chamber misplanning, and (d) long- and short-axis arrhythmia/breathing artifact. Backpropagation was selectively performed across these heads based on the labels present for each cine. Each image in the testing set was reported by four level 3 CMR experts, providing a consensus on clinical adequacy. The AI's assessment of image quality and ability to identify images requiring replanning or sequence changes were evaluated with Spearman’s rho and the area under receiver operating characteristic curve (AUROC), respectively. Results: A total of 1940 cines across 1387 studies were included. On the test set of 383 cines, AI-judged image quality correlated strongly with expert judgment, with Spearman’s rho of 0.84, 0.84, 0.81, and 0.81 for 2-, 3- and 4-chamber planning quality and the extent of arrhythmia or breathing artifacts, respectively. The AI also showed high efficacy in flagging clinically inadequate cines (AUROC 0.88, 0.93, and 0.93 for identifying misplanning of 2-, 3- and 4-chamber cines, and 0.90 for identifying movement artifacts). Conclusion: AI can assess distinct domains of CMR cine quality and provide continuous quality scores that correlate closely with a consensus of experts. These ratings could be used to identify cases where reacquisition is warranted and guide corrective actions to optimize image quality, including replanning, prospective gating, or real-time imaging.

Background: Late gadolinium enhancement (LGE) of the myocardium has significant diagnostic and prognostic implications, with even small areas of enhancement being important. Distinguishing between definitely normal and definitely abnormal LGE images is usually straightforward, but diagnostic uncertainty arises when reporters are not sure whether the observed LGE is genuine or not. This uncertainty might be resolved by repetition (to remove artifact) or further acquisition of intersecting images, but this must take place before the scan finishes. Real-time quality assurance by humans is a complex task requiring training and experience, so being able to identify which images have an intermediate likelihood of LGE while the scan is ongoing, without the presence of an expert is of high value. This decision-support could prompt immediate image optimization or acquisition of supplementary images to confirm or refute the presence of genuine LGE. This could reduce ambiguity in reports. Methods: Short-axis, phase-sensitive inversion recovery late gadolinium images were extracted from our clinical cardiac magnetic resonance (CMR) database and shuffled. Two, independent, blinded experts scored each individual slice for “LGE likelihood” on a visual analog scale, from 0 (absolute certainty of no LGE) to 100 (absolute certainty of LGE), with 50 representing clinical equipoise. The scored images were split into two classes—either “high certainty” of whether LGE was present or not, or “low certainty.” The dataset was split into training, validation, and test sets (70:15:15). A deep learning binary classifier based on the EfficientNetV2 convolutional neural network architecture was trained to distinguish between these categories. Classifier performance on the test set was evaluated by calculating the accuracy, precision, recall, F1-score, and area under the receiver operating characteristics curve (ROC AUC). Performance was also evaluated on an external test set of images from a different center. Results: One thousand six hundred and forty-five images (from 272 patients) were labeled and split at the patient level into training (1151 images), validation (247 images), and test (247 images) sets for the deep learning binary classifier. Of these, 1208 images were “high certainty” (255 for LGE, 953 for no LGE), and 437 were “low certainty”. An external test comprising 247 images from 41 patients from another center was also employed. After 100 epochs, the performance on the internal test set was accuracy = 0.94, recall = 0.80, precision = 0.97, F1-score = 0.87, and ROC AUC = 0.94. The classifier also performed robustly on the external test set (accuracy = 0.91, recall = 0.73, precision = 0.93, F1-score = 0.82, and ROC AUC = 0.91). These results were benchmarked against a reference inter-expert accuracy of 0.86. Conclusion: Deep learning shows potential to automate quality control of late gadolinium imaging in CMR. The ability to identify short-axis images with intermediate LGE likelihood in real-time may serve as a useful decision-support tool. This approach has the potential to guide immediate further imaging while the patient is still in the scanner, thereby reducing the frequency of recalls and inconclusive reports due to diagnostic indecision.

Introduction Diagnostic imaging is vital in emergency departments (EDs). Accessibility and reporting impacts ED workflow and patient care. With radiology workforce shortages, reporting capacity is limited, leading to image interpretation delays. Turnaround times for image reporting are an ED bottleneck. Artificial intelligence (AI) algorithms can improve productivity, efficiency and accuracy in diagnostic radiology, contingent on their clinical efficacy. This includes positively impacting patient care and improving clinical workflow. The ACCEPT-AI study will evaluate Qure.ai’s qER software in identifying and prioritising patients with critical findings from AI analysis of non-contrast head CT (NCCT) scans.Methods and analysis This is a multicentre trial, spanning four diverse sites, over 13 months. It will include all individuals above the age of 18 years who present to the ED, referred for an NCCT. The project will be divided into three consecutive phases (pre-implementation, implementation and post-implementation of the qER solution) in a stepped-wedge design to control for adoption bias and adjust for time-based changes in the background patient characteristics. Pre-implementation involves baseline data for standard care to support the primary and secondary outcomes. The implementation phase includes staff training and qER solution threshold adjustments in detecting target abnormalities adjusted, if necessary. The post-implementation phase will introduce a notification (prioritised flag) in the radiology information system. The radiologist can choose to agree with the qER findings or ignore it according to their clinical judgement before writing and signing off the report. Non-qER processed scans will be handled as per standard care.Ethics and dissemination The study will be conducted in accordance with the principles of Good Clinical Practice. The protocol was approved by the Research Ethics Committee of East Midlands (Leicester Central), in May 2023 (REC (Research Ethics Committee) 23/EM/0108). Results will be published in peer-reviewed journals and disseminated in scientific findings (ClinicalTrials.gov: NCT06027411)Trial registration number NCT06027411.

Abstract Background Surveillance of aortic dimensions requires reproducible measurements, and knowledge of the rate of progression in those with dilatation. Purpose To develop an open machine-learning method for measuring the aortic root and proximal ascending aorta on echocardiograms, validate it through a multi-expert panel from the Unity UK Echocardiography AI Collaborative, and applying the AI to derive the rate of progression in historical databases. Methods The neural network was trained on 1478 parasternal long-axis images. Each image was labelled with key points for the aortic annulus, sinus and sinotubular junction, and proximal ascending aorta dimensions. Labels accommodated inner-to-inner and leading-to-leading conventions. For validation, the end-diastolic and mid-systolic images were identified (accommodating different guidelines recommendations) from 100 studies, and 10 expert echocardiographers made the aortic measurements. The consensus of experts defined the reference standard, and the variation between individual experts defined the acceptable variation for the AI. The AI was then applied to 724 echocardiograms of 102 patients under surveillance spanning 12 years (ranging from 4 to 17 scans per patient) without intervention. Training data labels and networks are made freely available on our project website. Results The median absolute deviations between the AI and the expert consensus ranged from 0.06cm to 0.17cm across the 16 measurements. For the individual expert opinions this was from 0.08cm to 0.19cm. For 7/16 measurements, there was no statistically significant difference between the AI deviation and the individual-expert deviation. The AI’s confidence level was a useful indicator of the reliability of the AI measure. For the top 9 deciles of AI confidence level, the AI measurements had significantly smaller deviations than the individual experts. The rates of progression averaged across the three aortic measurements was 2.0 mm/decade (95% CI 1.0 to 3.0; p =0.007). Conclusion Expert consensus can be used to both define the reference standard and also the range of acceptable deviation from consensus. Overall, the AI performs similarly to experts and more importantly, provides an automated estimate of confidence. The validated AI is consistent over time, and when applied retrospectively to patients with dilated aortic roots, found the rate of progression was more rapid than in previously reported healthy patients. This approach could be applied generally in developing medical AI to not only make reproducible measurements but to automate large scale longitudinal studies with little input, and ultimately serves as a useful research and clinical tool.Figure: AI(red) vs Expert (blue)Table: AIDeviations from Consensus

Introduction Cardiac magnetic resonance imaging (CMR) evaluates aortic stenosis (AS) and concurrent myocardial abnormalities. Initial diagnosis of aortic valve (AV) disease can occur during CMR scanning, but universal multiparametric AS assessment is inefficient. An automated strategy for identifying AS patients from the 3-chamber view (part of all protocols) is therefore valuable. We observed that in patients with AS, there was reduced blood signal intensity in the ascending aorta compared to the cardiac chambers. We investigated the diagnostic potential of quantifying this signal reduction as a radiomic marker for AS severity. We introduce an AI-based solution to enhance this metric's precision and reproducibility. Materials and Methods This was a multi-centre, retrospective cohort study with 249 patients. Signal intensity was quantified within a 1cm2 region of interest (ROI) in the ascending aorta (Ao), left ventricle (LV), and left atrium (LA) (figure 1). Normalised Ao:LV ratio was calculated and compared against echocardiographic gold standards of AS severity: e.g., dimensionless index (DI) and AV maximum velocity, utilising Pearson correlation coefficients. Automated analysis was conducted using a point-tracking algorithm. Results The cohort (n = 249, median age 67 [IQR 58–77], 63% male) was stratified into no AS (n=87), mild AS (n=52), moderate AS (n=53) or severe AS (n=57) based on gold-standard echocardiography. The Ao:LV signal ratio strongly correlated with echocardiography parameters (figure 2A-B). A ratio of <0.87 exhibited 87% sensitivity and 83% specificity in identifying aortic stenosis of any severity (figure 2D). Discussion The Ao:LV ratio is a novel, automatable radiomic marker with good correlation to echocardiographic parameters for AS severity assessment. Derived from routine 3CH bSSFP cines, it provides clinical information and could optimise clinical workflow by eliminating the need for unnecessary imaging sequences. Its multi-vendor compatibility allows generalizability across various scanning technologies. The algorithmic framework is designed for machine learning adaptation, offering the potential for real-time analysis. Conclusion The Ao:LV ratio is a robust, simple tool for the initial diagnosis and severity assessment of AS available in a standard clinical protocol. This study demonstrates feasibility of automated Ao:LV computation which could enhance efficiency by targeting the appropriate use of patient-specific AV sequences. Acknowledgements KV is funded by the UK research and Innovation [UKRI Centre for Doctoral Training in AI for Healthcare grant number EP/S023283/1]. JH is funded by the British Heart Foundation [FS/ICRF/22/26039]. GDC is supported by the National Institute of Health Research (NIHR) Imperial Biomedical Research Centre (BRC).

BACKGROUND Global longitudinal strain (GLS) is reported to be more reproducible and prognostic than ejection fraction. Automated, transparent methods may increase trust and uptake. OBJECTIVES The authors developed open machine-learning-based GLS methodology and validate it using multiexpert consensus from the Unity UK Echocardiography AI Collaborative. METHODS We trained a multi-image neural network (Unity-GLS) to identify annulus, apex, and endocardial curve on 6,819 apical 4-, 2-, and 3-chamber images. The external validation dataset comprised those 3 views from 100 echocardiograms. End-systolic and-diastolic frames were each labelled by 11 experts to form consensus tracings and points. They also ordered the echocardiograms by visual grading of longitudinal function. One expert calculated global strain using 2 proprietary packages. RESULTS The median GLS, averaged across the 11 individual experts, was-16.1 (IQR:-19.3 to-12.5). Using each case's expert consensus measurement as the reference standard, individual expert measurements had a median absolute error of 2.00 GLS units. In comparison, the errors of the machine methods were: Unity-GLS 1.3, proprietary A 2.5, proprietary B 2.2. The correlations with the expert consensus values were for individual experts 0.85, Unity-GLS 0.91, proprietary A 0.73, proprietary B 0.79. Using the multiexpert visual ranking as the reference, individual expert strain measurements found a median rank correlation of 0.72, Unity-GLS 0.77, proprietary A 0.70, and proprietary B 0.74. CONCLUSIONS Our open-source approach to calculating GLS agrees with experts' consensus as strongly as the individual expert measurements and proprietary machine solutions. The training data, code, and trained networks are freely available online. (JACC Cardiovasc Imaging 2024;17:865-876) (c) 2024 The Authors. Published by Elsevier on behalf of the American College of Cardiology Foundation. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).

Background: Cardiovascular magnetic resonance (CMR) imaging is an important tool for evaluating the severity of aortic stenosis (AS), co-existing aortic disease, and concurrent myocardial abnormalities. Acquiring this additional information requires protocol adaptations and additional scanner time, but is not necessary for the majority of patients who do not have AS. We observed that the relative signal intensity of blood in the ascending aorta on a balanced steady state free precession (bSSFP) 3-chamber cine was often reduced in those with significant aortic stenosis. We investigated whether this effect could be quantified and used to predict AS severity in comparison to existing gold -standard measurements. Methods: Multi-centre, multi-vendor retrospective analysis of patients with AS undergoing CMR and transthoracic echocardiography (TTE). Blood signal intensity was measured in a similar to 1 cm(2) region of interest (ROI) in the aorta and left ventricle (LV) in the 3-chamber bSSFP cine. Because signal intensity varied across patients and scanner vendors, a ratio of the mean signal intensity in the aorta ROI to the LV ROI (Ao:LV) was used. This ratio was compared using Pearson correlations against TTE parameters of AS severity: aortic valve peak velocity, mean pressure gradient and the dimensionless index. The study also assessed whether field strength (1.5 T vs. 3 T) and patient characteristics (presence of bicuspid aortic valves (BAV), dilated aortic root and low flow states) altered this signal relationship. Results: 314 patients (median age 69 [IQR 57-77], 64% male) who had undergone both CMR and TTE were studied; 84 had severe AS, 78 had moderate AS, 66 had mild AS and 86 without AS were studied as a comparator group. The median time between CMR and TTE was 12 weeks (IQR 4-26). The Ao:LV ratio at 1.5 T strongly correlated with peak velocity (r = -0.796, p = 0.001), peak gradient (r = -0.772, p = 0.001) and dimensionless index (r = 0.743, p = 0.001). An Ao:LV ratio of < 0.86 was 84% sensitive and 82% specific for detecting AS of any severity and a ratio of 0.58 was 83% sensitive and 92% specific for severe AS. The ability of Ao:LV ratio to predict AS severity remained for patients with bicuspid aortic valves, dilated aortic root or low indexed stroke volume. The relationship between Ao:LV ratio and AS severity was weaker at 3 T. Conclusions: The Ao:LV ratio, derived from bSSFP 3 -chamber cine images, shows a good correlation with existing measures of AS severity. It demonstrates utility at 1.5 T and offers an easily calculable metric that can be used at the time of scanning or automated to identify on an adaptive basis which patients benefit from dedicated imaging to assess which patients should have additional sequences to assess AS.

Introduction A non-contrast CT head scan (NCCTH) is the most common cross-sectional imaging investigation requested in the emergency department. Advances in computer vision have led to development of several artificial intelligence (AI) tools to detect abnormalities on NCCTH. These tools are intended to provide clinical decision support for clinicians, rather than stand-alone diagnostic devices. However, validation studies mostly compare AI performance against radiologists, and there is relative paucity of evidence on the impact of AI assistance on other healthcare staff who review NCCTH in their daily clinical practice.Methods and analysis A retrospective data set of 150 NCCTH will be compiled, to include 60 control cases and 90 cases with intracranial haemorrhage, hypodensities suggestive of infarct, midline shift, mass effect or skull fracture. The intracranial haemorrhage cases will be subclassified into extradural, subdural, subarachnoid, intraparenchymal and intraventricular. 30 readers will be recruited across four National Health Service (NHS) trusts including 10 general radiologists, 15 emergency medicine clinicians and 5 CT radiographers of varying experience. Readers will interpret each scan first without, then with, the assistance of the qER EU 2.0 AI tool, with an intervening 2-week washout period. Using a panel of neuroradiologists as ground truth, the stand-alone performance of qER will be assessed, and its impact on the readers’ performance will be analysed as change in accuracy (area under the curve), median review time per scan and self-reported diagnostic confidence. Subgroup analyses will be performed by reader professional group, reader seniority, pathological finding, and neuroradiologist-rated difficulty.Ethics and dissemination The study has been approved by the UK Healthcare Research Authority (IRAS 310995, approved 13 December 2022). The use of anonymised retrospective NCCTH has been authorised by Oxford University Hospitals. The results will be presented at relevant conferences and published in a peer-reviewed journal.Trial registration number NCT06018545.

Abstract Background The utilisation of ratiometric intensity measures from cardiac magnetic resonance imaging (CMR) offers a promising biomarker for the diagnosis of aortic stenosis (AS)[1]. The Ao:LV ratio, an approximation of AS severity, is determined by comparing the relative blood signal intensity in the aorta and left ventricle (LV) within three-chamber (3Ch) cine sequences[1]. In patients with AS, the blood signal intensity of aortic blood above the valve is diminished compared to that within the LV in steady-state free precession (SSFP) 3Ch CMR cine. Although the Ao:LV ratio serves as a reliable indicator of AS severity, manual computation of this ratio may encounter difficulties due to visual obstructions caused by small LV cavities or prominent papillary muscles. Purpose This study aims to leverage artificial intelligence (AI) to automate the Ao:LV ratio analysis from 3Ch SSFP cine images and introduce the Ao:LA (aorta to left atrium) ratio, thus enhancing the diagnostic accuracy for AS severity. Methods Our methodology extends the ratiometric analysis to include both Ao:LV and Ao:LA ratios in three main steps: first, developing an AI-based algorithm for automated detection and tracking of cardiac landmarks; second, using these landmarks to automatically compute regions of interest (ROIs) in the cardiac chambers; and third, training and validating classification models with 5-fold cross-validation to select the most effective for AS severity classification. The final model's performance is assessed on a holdout test set. Data for model training and evaluation were sourced from CMR scans across three hospitals and two scanner types. Results We analysed 220 patients of which 78 patients had no AS and 122 had AS (mild AS, n = 29; moderate AS; n = 35, severe AS; n = 78). Our model yielded high efficacy in classifying AS, particularly in differentiating any grade of AS from a normal classification, which is clinically relevant. The Ao:LA ratio demonstrated a stronger correlation with AS severity class than Ao:LV, suggesting a more reliable biomarker. The proposed model demonstrated robust performance in AS classification, achieving an Area Under the Curve (AUC) of 0.845 in the automated binary classification of AS at any grade. The model exhibited a precision of 0.889, recall of 0.865, and an F1 score of 0.877 on a holdout set. Conclusion By the integration of AI in automating the analysis of CMR images through a novel ratiometric approach that includes Ao:LV and Ao:LA ratios, our model significantly improves the accuracy of early AS detection. This advancement enhances imaging strategies for AS evaluation, promoting more efficient and effective use of cardiac MRI sequences as a diagnostic tool for aortic stenosis. It has the potential to be implemented in real-time scanning protocols as a clinical decision support system.AI-inferred cardiac landmarks.ROC curve delineating AS prediction.

Abstract Funding Acknowledgements Type of funding sources: Public Institution(s). Main funding source(s): UK research and Innovation [UKRI Centre for Doctoral Training in AI for Healthcare]. Background Aortic stenosis (AS) is the most common valvular heart disease in developed countries with prevalence increasing with age. CMR is an important tool for the evaluation of AS, co-existing aortic disease and concurrent myocardial abnormalities. Whilst a 3-chamber aortic valve view is standard for most cardiac protocols, a full evaluation of the aortic valve including short-axis cine imaging of the valve and flow imaging in the ascending aorta incurs additional time penalty and is not necessary for all patients. We noted that the SSFP signal of blood in the ascending aorta on a standard 3-chamber view was often reduced in those with aortic stenosis. Our aim was to compare the aortic to left ventricular (LV) blood ratio of SSFP signal with existing gold-standard imaging biomarkers of aortic stenosis. Methods Retrospective analysis of 53 patients with varying aortic stenosis severity. We manually measured a 1–2cm2 region of interest (ROI) in the aorta and LV in end-systole (Figure 1). We compared the signal intensity in the aorta ROI to the LV ROI (Ao:LV) with echocardiography parameters including dimensionless index (DI) and aortic valve maximum velocity (Vmax). Pearson correlation coefficient (R) was used to compare methods. Results Patients (n=53, median age 67 [24–91], 33/53 male) included none or trace AS (n=14), mild AS (n=12), moderate AS (n=8) and severe AS (n=19) according to echocardiography. Median time between CMR and echocardiography was 43 days [1–917]. There was a reasonable correlation (R=0.785, −0.771 respectively) between blood Ao:LV ratio of SSFP signal with DI and Vmax (Figure 2). Conclusion The ratio of blood signal seen in SSFP 3-chamber cine images gives a reasonable approximation to aortic stenosis severity measured using gold-standard echocardiography strategies. It is potentially automatable and may allow identification of the subset of patients whose scans would be enhanced by need of dedicated aortic valve imaging.

The assessment of aortic valve pathology using magnetic resonance imaging (MRI) typically relies on blood velocity estimates acquired using phase contrast (PC) MRI. However, abnormalities in blood flow through the aortic valve often manifest by the dephasing of blood signal in gated balanced steady-state free precession (bSSFP) scans (Cine MRI). We propose a 3D classification neural network (NN) to automatically identify aortic valve pathology (aortic regurgitation, aortic stenosis, mixed valve disease) from Cine MR images. We train and test our approach on a retrospective clinical dataset from three UK hospitals, using single-slice 3-chamber cine MRI from N = 576 patients. Our classification model accurately predicts the presence of aortic valve pathology (AVD) with an accuracy of 0.85 +/- 0.03 and can also correctly discriminate the type of AVD pathology (accuracy: 0.75 +/- 0.03). Gradient-weighted class activation mapping (Grad-CAM) confirms that the blood pool voxels close to the aortic root contribute the most to the classification. Our approach can be used to improve the diagnosis of AVD and optimise clinical CMR protocols for accurate and efficient AVD detection.

Some patients are found to have myocardial scarring after infection with coronavirus-2019 disease (COVID-19) as evidenced by the presence of late gadolinium enhancement on cardiac MRI (CMR). In many types of heart disease, the presence of late gadolinium enhancement (even without symptoms) is associated with a poorer prognosis. However, it is not known whether the presence of scar after COVID-19 is associated with outcome. This study explores the association between late gadolinium enhancement (LGE) in recovered patients with COVID-19 and of longer-term clinical outcomes. In this single-centre, retrospective, observational cohort study, troponin levels, CMR data, and follow-up outcomes of 169 patients with COVID-19 were collected. The primary outcome was all-cause mortality. The secondary outcome was a composite of myocardial infarction, stroke, and admission for heart failure. The log-rank test was used to compare survival of those with and without late gadolinium enhancement. A total of 169 patients (mean age 61 ± 16 years, 54% male) were included. Scans were typically performed in patients with a raised troponin or ongoing cardiac symptoms post COVID-19 infection. The median (IQR) time between COVID-19 diagnosis and CMR was 14 (7-23) weeks. Median follow-up was 28 (IQR 23 to 37) months. Troponin was performed in 92% (n=155) of patients. Of those, 78% (n=121) had a positive result. Late gadolinium enhancement was present in 54 patients (32%). There were no observed differences in comorbidities such as hypertension, known ischaemic heart disease or heart failure, diabetes, obesity, or frailty between in patients with LGE compared to those without LGE. Kaplan-Meier survival analysis showed no significant difference in all cause mortality for patients with COVID-19 with LGE compared to those without LGE (Log-rank P = 0.36). Similarly, the composite secondary endpoint was not significantly different (Log-rank P = 0.48). In this single centre study, patients found to have myocardial LGE after COVID-19 did not have an increased risk of mortality or cardiovascular events compared to those without. The overall event rates remain low even after 2-3 years of follow-up. The cause of this is unclear but underlines the importance of larger multicentre studies to follow-up COVID-19 survivors.

Background:Getting the most value from expert clinicians' limited labelling time is a major challenge for artificial intelligence (AI) development in clinical imaging. We present a novel method for ground-truth labelling of cardiac magnetic resonance imaging (CMR) image data by leveraging multiple clinician experts ranking multiple images on a single ordinal axis, rather than manual labelling of one image at a time. We apply this strategy to train a deep learning (DL) model to classify the anatomical position of CMR images. This allows the automated removal of slices that do not contain the left ventricular (LV) myocardium. Methods:Anonymised LV short-axis slices from 300 random scans (3,552 individual images) were extracted. Each image's anatomical position relative to the LV was labelled using two different strategies performed for 5 hours each: (I) 'one-image-at-a-time': each image labelled according to its position: 'too basal', 'LV', or 'too apical' individually by one of three experts; and (II) 'multiple-image-ranking': three independent experts ordered slices according to their relative position from 'most-basal' to 'most apical' in batches of eight until each image had been viewed at least 3 times. Two convolutional neural networks were trained for a three-way classification task (each model using data from one labelling strategy). The models' performance was evaluated by accuracy, F1-score, and area under the receiver operating characteristics curve (ROC AUC). Results:After excluding images with artefact, 3,323 images were labelled by both strategies. The model trained using labels from the 'multiple-image-ranking strategy' performed better than the model using the 'one-image-at-a-time' labelling strategy (accuracy 86% vs. 72%, P=0.02; F1-score 0.86 vs. 0.75; ROC AUC 0.95 vs. 0.86). For expert clinicians performing this task manually the intra-observer variability was low (Cohen's κ=0.90), but the inter-observer variability was higher (Cohen's κ=0.77). Conclusions:We present proof of concept that, given the same clinician labelling effort, comparing multiple images side-by-side using a 'multiple-image-ranking' strategy achieves ground truth labels for DL more accurately than by classifying images individually. We demonstrate a potential clinical application: the automatic removal of unrequired CMR images. This leads to increased efficiency by focussing human and machine attention on images which are needed to answer clinical questions.

Background Aortic stenosis (AS) is the most common valvular heart disease in developed countries with prevalence increasing with age. CMR is an important tool for the evaluation of AS, co-existing aortic disease and concurrent myocardial abnormalities. Whilst a 3-chamber aortic valve view is standard for most cardiac protocols, a full evaluation of the aortic valve including short-axis cine imaging of the valve and flow imaging in the ascending aorta incurs additional time penalty and is not necessary for all patients. We noted that the steady-state free precession (SSFP) signal of blood in the ascending aorta on a standard 3-chamber view was often reduced in those with aortic stenosis. Our aim was to develop radiomic analysis comparing the aortic to left ventricular (LV) blood ratio of SSFP signal with existing gold-standard imaging biomarkers of aortic stenosis. Methods We conducted a retrospective analysis of 53 patients with varying aortic stenosis severity. We manually measured a 1-2cm2 region of interest (ROI) in the aorta and LV in end-systole (Figure 1). We compared the signal intensity in the aorta ROI to the LV ROI (Ao:LV) with echocardiography parameters including dimensionless index (DI) and aortic valve maximum velocity (Vmax). Pearson correlation coefficient (R) was used to compare methods. Results Patients (n=53, median age 67 [24-91], 33/53 male) included none or trace AS (n=14), mild AS (n=12), moderate AS (n=8) and severe AS (n=19) according to echocardiography. Median time between CMR and echocardiography was 43 days [1-487]. There was a reasonable correlation (R=0.785, -0.771 respectively) between blood Ao:LV ratio of SSFP signal with DI and Vmax (Figure 2). Conclusion The ratio of blood signal seen in SSFP 3-chamber cine images gives a reasonable approximation to aortic stenosis severity measured using gold-standard echocardiography strategies. It is potentially automatable and may allow identification of the subset of patients whose scans would be enhanced by need of dedicated aortic valve imaging. Conflict of Interest None

Cardiac magnetic resonance (CMR) is the gold standard for quantification of cardiac volumes, function, and blood flow. Tailored MR pulse sequences define the contrast mechanisms, acquisition geometry and timing which can be applied during CMR to achieve unique tissue characterisation. It is impractical for each patient to have every possible acquisition option. We target the aortic valve in the three-chamber (3-CH) cine CMR view. Two major types of anomalies are possible in the aortic valve. Stenosis: the narrowing of the valve which prevents an adequate outflow of blood, and insufficiency (regurgitation): the inability to stop the back-flow of blood into the left ventricle. We develop and evaluate a deep learning system to accurately classify aortic valve abnormalities to enable further directed imaging for patients who require it. Inspired by low level image processing tasks, we propose a multi-level network that generates heat maps to locate the aortic valve leaflets' hinge points and aortic stenosis or regurgitation jets. We trained and evaluated all our models on a dataset of clinical CMR studies obtained from three NHS hospitals (n = 1,017 patients). Our results (mean accuracy = 0.93 and F1 score = 0.91), show that an expert-guided deep learning-based feature extraction and a classification model provide a feasible strategy for prescribing further, directed imaging, thus improving the efficiency and utility of CMR scanning.