Quality assurance of late gadolinium enhancement cardiac magnetic resonance images: a deep learning classifier for confidence in the presence or absence of abnormality with potential to prompt real-time image optimization.

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.

AI assisted reader evaluation in acute CT head interpretation (AI-REACT): protocol for a multireader multicase study.

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.

Aortic stenosis assessment from the 3-chamber cine: Ratio of balanced steady-state-free-precession (bSSFP) blood signal between the aorta and left ventricle predicts severity.

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 ∼1 cm2 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.

Efficient labelling for efficient deep learning: the benefit of a multiple-image-ranking method to generate high volume training data applied to ventricular slice level classification in cardiac MRI.

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.

Automatic Diagnosis Labeling of Cardiovascular MRI by Using Semisupervised Natural Language Processing of Text Reports.

PURPOSE: To assess whether the semisupervised natural language processing (NLP) of text from clinical radiology reports could provide useful automated diagnosis categorization for ground truth labeling to overcome manual labeling bottlenecks in the machine learning pipeline. MATERIALS AND METHODS: In this retrospective study, 1503 text cardiac MRI reports from 2016 to 2019 were manually annotated for five diagnoses by clinicians: normal, dilated cardiomyopathy (DCM), hypertrophic cardiomyopathy, myocardial infarction (MI), and myocarditis. A semisupervised method that uses bidirectional encoder representations from transformers (BERT) pretrained on 1.14 million scientific publications was fine-tuned by using the manually extracted labels, with a report dataset split into groups of 801 for training, 302 for validation, and 400 for testing. The model's performance was compared with two traditional NLP models: a rule-based model and a support vector machine (SVM) model. The models' F1 scores and receiver operating characteristic curves were used to analyze performance. RESULTS: After 15 epochs, the F1 scores on the test set of 400 reports were as follows: normal, 84%; DCM, 79%; hypertrophic cardiomyopathy, 86%; MI, 91%; and myocarditis, 86%. The pooled F1 score and area under the receiver operating curve were 86% and 0.96, respectively. On the same test set, the BERT model had a higher performance than the rule-based model (F1 score, 42%) and SVM model (F1 score, 82%). Diagnosis categories classified by using the BERT model performed the labeling of 1000 MR images in 0.2 second. CONCLUSION: The developed model used labels extracted from radiology reports to provide automated diagnosis categorization of MR images with a high level of performance.Keywords: Semisupervised Learning, Diagnosis/Classification/Application Domain, Named Entity Recognition, MRI Supplemental material is available for this article. © RSNA, 2021.

Myocardial Perfusion Imaging After Severe COVID-19 Infection Demonstrates Regional Ischemia Rather Than Global Blood Flow Reduction.

Background: Acute myocardial damage is common in severe COVID-19. Post-mortem studies have implicated microvascular thrombosis, with cardiovascular magnetic resonance (CMR) demonstrating a high prevalence of myocardial infarction and myocarditis-like scar. The microcirculatory sequelae are incompletely characterized. Perfusion CMR can quantify the stress myocardial blood flow (MBF) and identify its association with infarction and myocarditis. Objectives: To determine the impact of the severe hospitalized COVID-19 on global and regional myocardial perfusion in recovered patients. Methods: A case-control study of previously hospitalized, troponin-positive COVID-19 patients was undertaken. The results were compared with a propensity-matched, pre-COVID chest pain cohort (referred for clinical CMR; angiography subsequently demonstrating unobstructed coronary arteries) and 27 healthy volunteers (HV). The analysis used visual assessment for the regional perfusion defects and AI-based segmentation to derive the global and regional stress and rest MBF. Results: Ninety recovered post-COVID patients {median age 64 [interquartile range (IQR) 54-71] years, 83% male, 44% requiring the intensive care unit (ICU)} underwent adenosine-stress perfusion CMR at a median of 61 (IQR 29-146) days post-discharge. The mean left ventricular ejection fraction (LVEF) was 67 ± 10%; 10 (11%) with impaired LVEF. Fifty patients (56%) had late gadolinium enhancement (LGE); 15 (17%) had infarct-pattern, 31 (34%) had non-ischemic, and 4 (4.4%) had mixed pattern LGE. Thirty-two patients (36%) had adenosine-induced regional perfusion defects, 26 out of 32 with at least one segment without prior infarction. The global stress MBF in post-COVID patients was similar to the age-, sex- and co-morbidities of the matched controls (2.53 ± 0.77 vs. 2.52 ± 0.79 ml/g/min, p = 0.10), though lower than HV (3.00 ± 0.76 ml/g/min, p< 0.01). Conclusions: After severe hospitalized COVID-19 infection, patients who attended clinical ischemia testing had little evidence of significant microvascular disease at 2 months post-discharge. The high prevalence of regional inducible ischemia and/or infarction (nearly 40%) may suggest that occult coronary disease is an important putative mechanism for troponin elevation in this cohort. This should be considered hypothesis-generating for future studies which combine ischemia and anatomical assessment.

Automated Left Ventricular Dimension Assessment Using Artificial Intelligence Developed and Validated by a UK-Wide Collaborative.

BACKGROUND: requires training and validation to standards expected of humans. We developed an online platform and established the Unity Collaborative to build a dataset of expertise from 17 hospitals for training, validation, and standardization of such techniques. METHODS: The training dataset consisted of 2056 individual frames drawn at random from 1265 parasternal long-axis video-loops of patients undergoing clinical echocardiography in 2015 to 2016. Nine experts labeled these images using our online platform. From this, we trained a convolutional neural network to identify keypoints. Subsequently, 13 experts labeled a validation dataset of the end-systolic and end-diastolic frame from 100 new video-loops, twice each. The 26-opinion consensus was used as the reference standard. The primary outcome was precision SD, the SD of the differences between AI measurement and expert consensus. RESULTS: In the validation dataset, the AI's precision SD for left ventricular internal dimension was 3.5 mm. For context, precision SD of individual expert measurements against the expert consensus was 4.4 mm. Intraclass correlation coefficient between AI and expert consensus was 0.926 (95% CI, 0.904-0.944), compared with 0.817 (0.778-0.954) between individual experts and expert consensus. For interventricular septum thickness, precision SD was 1.8 mm for AI (intraclass correlation coefficient, 0.809; 0.729-0.967), versus 2.0 mm for individuals (intraclass correlation coefficient, 0.641; 0.568-0.716). For posterior wall thickness, precision SD was 1.4 mm for AI (intraclass correlation coefficient, 0.535 [95% CI, 0.379-0.661]), versus 2.2 mm for individuals (0.366 [0.288-0.462]). We present all images and annotations. This highlights challenging cases, including poor image quality and tapered ventricles. CONCLUSIONS: Experts at multiple institutions successfully cooperated to build a collaborative AI. This performed as well as individual experts. Future echocardiographic AI research should use a consensus of experts as a reference. Our collaborative welcomes new partners who share our commitment to publish all methods, code, annotations, and results openly.

Patterns of myocardial injury in recovered troponin-positive COVID-19 patients assessed by cardiovascular magnetic resonance.

BACKGROUND: Troponin elevation is common in hospitalized COVID-19 patients, but underlying aetiologies are ill-defined. We used multi-parametric cardiovascular magnetic resonance (CMR) to assess myocardial injury in recovered COVID-19 patients. METHODS AND RESULTS: One hundred and forty-eight patients (64 ± 12 years, 70% male) with severe COVID-19 infection [all requiring hospital admission, 48 (32%) requiring ventilatory support] and troponin elevation discharged from six hospitals underwent convalescent CMR (including adenosine stress perfusion if indicated) at median 68 days. Left ventricular (LV) function was normal in 89% (ejection fraction 67% ± 11%). Late gadolinium enhancement and/or ischaemia was found in 54% (80/148). This comprised myocarditis-like scar in 26% (39/148), infarction and/or ischaemia in 22% (32/148) and dual pathology in 6% (9/148). Myocarditis-like injury was limited to three or less myocardial segments in 88% (35/40) of cases with no associated LV dysfunction; of these, 30% had active myocarditis. Myocardial infarction was found in 19% (28/148) and inducible ischaemia in 26% (20/76) of those undergoing stress perfusion (including 7 with both infarction and ischaemia). Of patients with ischaemic injury pattern, 66% (27/41) had no past history of coronary disease. There was no evidence of diffuse fibrosis or oedema in the remote myocardium (T1: COVID-19 patients 1033 ± 41 ms vs. matched controls 1028 ± 35 ms; T2: COVID-19 46 ± 3 ms vs. matched controls 47 ± 3 ms). CONCLUSIONS: During convalescence after severe COVID-19 infection with troponin elevation, myocarditis-like injury can be encountered, with limited extent and minimal functional consequence. In a proportion of patients, there is evidence of possible ongoing localized inflammation. A quarter of patients had ischaemic heart disease, of which two-thirds had no previous history. Whether these observed findings represent pre-existing clinically silent disease or de novo COVID-19-related changes remain undetermined. Diffuse oedema or fibrosis was not detected.

Role of rivaroxaban in the management of atrial fibrillation: insights from clinical practice.

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, and it leads to significant morbidity and mortality, predominantly from ischemic stroke. Vitamin K antagonists, mainly warfarin, have been used for decades to prevent ischemic stroke in AF, but their use is limited due to interactions with food and other drugs, as well as the requirement for regular monitoring of the international normalized ratio. Rivaroxaban, a direct factor Xa inhibitor and the most commonly used non-vitamin K oral anticoagulant, avoids many of these challenges and is being prescribed with increasing frequency for stroke prevention in non-valvular AF. Randomized controlled trial (RCT) data from the ROCKET-AF(Rivaroxaban once daily oral direct Factor Xa inhibition compared with vitamin K antagonism for prevention of stroke and embolism trial in atrial fibrillation) trial have shown rivaroxaban to be non-inferior to warfarin in preventing ischemic stroke and systemic embolism and to have comparable overall bleeding rates. Applicability of the RCT data to real-world practice can sometimes be limited by complex clinical scenarios or multiple comorbidities not adequately represented in the trials. Available real-world evidence in non-valvular AF patients with comorbidities - including renal impairment, acute coronary syndrome, diabetes mellitus, malignancy, or old age - supports the use of rivaroxaban as safe and effective in preventing ischemic stroke in these subgroups, though with some important considerations required to reduce bleeding risk. Patient perspectives on rivaroxaban use are also considered. Real-world evidence indicates superior rates of drug adherence with rivaroxaban when compared with vitamin K antagonists and with alternative non-vitamin K oral anticoagulants - perhaps, in part, due to its once-daily dosing regimen. Furthermore, self-reported quality of life scores are highest among patients compliant with rivaroxaban therapy. The generally high levels of patient satisfaction with rivaroxaban therapy contribute to overall favorable clinical outcomes.

Limitations of poster presentations reporting educational innovations at a major international medical education conference.

BACKGROUND: In most areas of medical research, the label of 'quality' is associated with well-accepted standards. Whilst its interpretation in the field of medical education is contentious, there is agreement on the key elements required when reporting novel teaching strategies. We set out to assess if these features had been fulfilled by poster presentations at a major international medical education conference. METHODS: Such posters were analysed in four key areas: reporting of theoretical underpinning, explanation of instructional design methods, descriptions of the resources needed for introduction, and the offering of materials to support dissemination. RESULTS: Three hundred and twelve posters were reviewed with 170 suitable for analysis. Forty-one percent described their methods of instruction or innovation design. Thirty-three percent gave details of equipment, and 29% of studies described resources that may be required for delivering such an intervention. Further resources to support dissemination of their innovation were offered by 36%. Twenty-three percent described the theoretical underpinning or conceptual frameworks upon which their work was based. CONCLUSIONS: These findings suggest that posters presenting educational innovation are currently limited in what they offer to educators. Presenters should seek to enhance their reporting of these crucial aspects by employing existing published guidance, and organising committees may wish to consider explicitly requesting such information at the time of initial submission.