Search

Automatic quantification of the left ventricle (LV) from cardiac magnetic resonance (CMR) images plays an important role in making the diagnosis procedure efficient, reliable, and alleviating the laborious reading work for physicians. Considerable efforts have been devoted to LV quantification using different strategies that include segmentation-based (SG) methods and the recent direct regression (DR) methods. Although both SG and DR methods have obtained great success for the task, a systematic platform to benchmark them remains absent because of differences in label information during model learning. In this paper, we conducted an unbiased evaluation and comparison of cardiac LV quantification methods that were submitted to the Left Ventricle Quantification (LVQuan) challenge, which was held in conjunction with the Statistical Atlases and Computational Modeling of the Heart (STACOM) workshop at the MICCAI 2018. The challenge was targeted at the quantification of 1) areas of LV cavity and myocardium, 2) dimensions of the LV cavity, 3) regional wall thicknesses (RWT), and 4) the cardiac phase, from mid-ventricle short-axis CMR images. First, we constructed a public quantification dataset Cardiac-DIG with ground truth labels for both the myocardium mask and these quantification targets across the entire cardiac cycle. Then, the key techniques employed by each submission were described. Next, quantitative validation of these submissions were conducted with the constructed dataset. The evaluation results revealed that both SG and DR methods can offer good LV quantification performance, even though DR methods do not require densely labeled masks for supervision. Among the 12 submissions, the DR method LDAMT offered the best performance, with a mean estimation error of 301 mm $^2$ for the two areas, 2.15 mm for the cavity dimensions, 2.03 mm for RWTs, and a 9.5% error rate for the cardiac phase classification. Three of the SG methods also delivered comparable performances. Finally, we discussed the advantages and disadvantages of SG and DR methods, as well as the unsolved problems in automatic cardiac quantification for clinical practice applications.

Background: We aimed to explore the effectiveness of one-dose BNT162b2 vaccination upon SARS-CoV-2 infection, its effect on COVID-19 presentation, and post-vaccination symptoms in children and adolescents (CA) in the UK during periods of Delta and Omicron variant predominance. Methods: In this prospective longitudinal cohort study, we analysed data from 115,775 CA aged 12-17 years, proxy-reported through the Covid Symptom Study (CSS) smartphone application. We calculated post-vaccination infection risk after one dose of BNT162b2, and described the illness profile of CA with post-vaccination SARS-CoV-2 infection, compared to unvaccinated CA, and post-vaccination side-effects. Findings: Between August 5, 2021 and February 14, 2022, 25,971 UK CA aged 12-17 years received one dose of BNT162b2 vaccine. The probability of testing positive for infection diverged soon after vaccination, and was lower in CA with prior SARS-CoV-2 infection. Vaccination reduced proxy-reported infection risk (-80·4% (95% CI -0·82 -0·78) and -53·7% (95% CI -0·62 -0·43) at 14–30 days with Delta and Omicron variants respectively, and -61·5% (95% CI -0·74 -0·44) and -63·7% (95% CI -0·68 -0.59) after 61–90 days). Vaccinated CA who contracted SARS-CoV-2 during the Delta period had milder disease than unvaccinated CA; during the Omicron period this was only evident in children aged 12-15 years. Overall disease profile was similar in both vaccinated and unvaccinated CA. Post-vaccination local side-effects were common, systemic side-effects were uncommon, and both resolved within few days (3 days in most cases). Interpretation: One dose of BNT162b2 vaccine reduced risk of SARS-CoV-2 infection for at least 90 days in CA aged 12-17 years. Vaccine protection varied for SARS-CoV-2 variant type (lower for Omicron than Delta variant), and was enhanced by pre-vaccination SARS-CoV-2 infection. Severity of COVID-19 presentation after vaccination was generally milder, although unvaccinated CA also had generally mild disease. Overall, vaccination was well-tolerated. Funding: UK Government Department of Health and Social Care, Chronic Disease Research Foundation, The Wellcome Trust, UK Engineering and Physical Sciences Research Council, UK Research and Innovation London Medical Imaging & Artificial Intelligence Centre for Value Based Healthcare, UK National Institute for Health Research, UK Medical Research Council, British Heart Foundation and Alzheimer's Society, and ZOE Limited.

BackgroundSelf-reported symptom studies rapidly increased our understanding of SARS-CoV-2 during the pandemic and enabled the monitoring of long-term effects of COVID-19 outside the hospital setting. It is now evident that post-COVID syndrome presents with heterogeneous profiles, which need characterisation to enable personalised care among the most affected survivors. This study describes post-COVID profiles, and how they relate to different viral variants and vaccination status.MethodsIn this prospective longitudinal cohort study, we analysed data from 336,652 subjects, with regular health reports through the Covid Symptom Study (CSS) smartphone application. These subjects had reported feeling physically normal for at least 30 days before testing positive for SARS-CoV-2. 9,323 individuals subsequently developed Long-COVID, defined as symptoms lasting longer than 28 days. 1,459 had post-COVID syndrome, defined as more than 12 weeks of symptoms. Clustering analysis of the time-series data was performed to identify distinct symptom profiles for post-COVID patients, across variants of SARS-CoV-2 and vaccination status at the time of infection. Clusters were then characterised based on symptom prevalence, duration, demography, and prior conditions (comorbidities).Using an independent testing sample with additional data (n=140), we investigated the impact of post-COVID symptom clusters on the lives of affected individuals.FindingsWe identified distinct profiles of symptoms for post-COVID syndrome within and across variants: four endotypes were identified for infections due to the wild-type variant; seven for the alpha variant; and five for delta. Across all variants, a cardiorespiratory cluster of symptoms was identified. A second cluster related to central neurological, and a third to cases with the most severe and debilitating multi-organ symptoms. Gastrointestinal symptoms clustered in no more than two specific phenotypes per viral variant. The three main clusters were confirmed in an independent testing sample, and their functional impact was assessed.InterpretationUnsupervised analysis identified different post-COVID profiles, characterised by differing symptom combinations, durations, and functional outcomes. Phenotypes were at least partially concordant with individuals’ reported experiences.Our classification may be useful to understand distinct mechanisms of the post-COVID syndrome, as well as subgroups of individuals at risk of prolonged debilitation.FundingUK Government Department of Health and Social Care, Chronic Disease Research Foundation, The Wellcome Trust, UK Engineering and Physical Sciences Research Council, UK Research and Innovation London Medical Imaging & Artificial Intelligence Centre for Value-Based Healthcare, UK National Institute for Health Research, UK Medical Research Council, British Heart Foundation and Alzheimer’s Society, and ZOE Limited, UK.Research in contextEvidence before this studyWe conducted a search in the PubMed Central database, with keywords: (“Long-COVID*” OR “post?covid*” OR “post?COVID*” OR postCOVID* OR postCovid*) AND (cluster* OR endotype* OR phenotype* OR sub?type* OR subtype).On 15 June 2022, 161 documents were identified, of which 24 either provided descriptions of sub-types or proposed phenotypes of Long-COVID or post-COVID syndrome(s). These included 16 studies attempting manual sub-grouping of phenotypes, 6 deployments of unsupervised methods for patient clustering and automatic semantic phenotyping (unsupervised k-means=2; random forest classification=1; other=2), and two reports of uncommon presentations of Long-COVID/post-COVID syndrome. Overall, two to eight symptom profiles (clusters) were identified, with three recurring clusters. A cardiopulmonary syndrome was the predominant observation, manifesting with exertional intolerance and dyspnoea (n=10), fatigue (n=8), autonomic dysfunction, tachycardia or palpitations (n=5), lung radiological abnormalities including fibrosis (n=2), and chest pain (n=1). A second common presentation consisted in persistent general autoimmune activation and proinflammatory state (n=2), comprising multi-organ mild sequelae (n=2), gastrointestinal symptoms (n=2), dermatological symptoms (n=2), and/or fever (n=1). A third syndrome was reported, with neurological or neuropsychiatric symptoms: brain fog or dizziness (n=2), poor memory or cognition (n=2), and other mental health issues including mood disorders (n=5), headache (n=2), central sensitization (n=1), paresthesia (n=1), autonomic dysfunction (n=1), fibromyalgia (n=2), and chronic pain or myalgias (n=6). Unsupervised clustering methods identified two to six different post-COVID phenotypes, mapping to the ones described above.14 further documents focused on possible causes and/or mechanisms of disease underlying one or more manifestations of Long-COVID or post-COVID and identifying immune response dysregulation as a potential common element. All the other documents were beyond the scope of this work.To our knowledge, there are no studies examining the symptom profile of post-COVID syndrome between different variants and vaccination status. Also, no studies reported the modelling of longitudinally collected symptoms, as time-series data, aiming at the characterisation of post-COVID syndrome.Added-value of this studyOur study aimed to identify symptom profiles for post-COVID syndrome across the dominant variants in 2020 and 2021, and across vaccination status at the time of infection, using a large sample with prospectively collected longitudinal self-reports of symptoms. For individuals developing 12 weeks or more of symptoms, we identified three main symptom profiles which were consistent across variants and by vaccination status, differing only in the ratio of individuals affected by each profile and symptom duration overall.Implications of all the available evidenceWe demonstrate the existence of different post-COVID syndromes, which share commonalities across SARS-CoV-2 variant types in both symptoms themselves and how they evolved through the illness. We describe subgroups of patients with specific post-COVID presentations which might reflect different underlying pathophysiological mechanisms. Given the time-series component, our study is relevant for post-COVID prognostication, indicating how long certain symptoms last. These insights could aid in the development of personalised diagnosis and treatment, as well as helping policymakers plan for the delivery of care for people living with post-COVID syndrome.

Summary Background In children, SARS-CoV-2 infection is usually asymptomatic or causes a mild illness of short duration. Persistent illness has been reported; however, its prevalence and characteristics are unclear. We aimed to determine illness duration and characteristics in symptomatic UK school-aged children tested for SARS-CoV-2 using data from the COVID Symptom Study, one of the largest UK citizen participatory epidemiological studies to date. Methods In this prospective cohort study, data from UK school-aged children (age 5–17 years) were reported by an adult proxy. Participants were voluntary, and used a mobile application (app) launched jointly by Zoe Limited and King's College London. Illness duration and symptom prevalence, duration, and burden were analysed for children testing positive for SARS-CoV-2 for whom illness duration could be determined, and were assessed overall and for younger (age 5–11 years) and older (age 12–17 years) groups. Children with longer than 1 week between symptomatic reports on the app were excluded from analysis. Data from symptomatic children testing negative for SARS-CoV-2, matched 1:1 for age, gender, and week of testing, were also assessed. Findings 258 790 children aged 5–17 years were reported by an adult proxy between March 24, 2020, and Feb 22, 2021, of whom 75 529 had valid test results for SARS-CoV-2. 1734 children (588 younger and 1146 older children) had a positive SARS-CoV-2 test result and calculable illness duration within the study timeframe (illness onset between Sept 1, 2020, and Jan 24, 2021). The most common symptoms were headache (1079 [62·2%] of 1734 children), and fatigue (954 [55·0%] of 1734 children). Median illness duration was 6 days (IQR 3–11) versus 3 days (2–7) in children testing negative, and was positively associated with age (Spearman's rank-order rs 0·19, p

BackgroundWe aimed to explore the effectiveness of one-dose BNT162b2 vaccination upon SARS-CoV-2 infection, its effect on COVID-19 presentation, and post-vaccination symptoms in children and young people (CYP) in the UK during periods of Delta and Omicron variant predominance.MethodsIn this prospective longitudinal cohort study, we analysed data from 115,775 CYP aged 12-17 years, proxy-reported through the Covid Symptom Study (CSS) smartphone application. We calculated post-vaccination infection risk after one dose of BNT162b2, and described the illness profile of CYP with post-vaccination SARS- CoV-2 infection, compared to unvaccinated CYP, and post-vaccination side-effects.FindingsBetween August 5, 2021 and February 14, 2022, 25,971 UK CYP aged 12-17 years received one dose of BNT162b2 vaccine. Vaccination reduced (proxy-reported) infection risk (-80·4% and -53·7% at 14–30 days with Delta and Omicron variants respectively, and -61·5% and -63·7% after 61–90 days). The probability of remaining infection-free diverged soon after vaccination, and was greater in CYP with prior SARS-CoV-2 infection. Vaccinated CYP who contracted SARS-CoV-2 during the Delta period had milder disease than unvaccinated CYP; during the Omicron period this was only evident in children aged 12-15 years. Overall disease profile was similar in both vaccinated and unvaccinated CYP. Post-vaccination local side-effects were common, systemic side-effects were uncommon, and both resolved quickly.InterpretationOne dose of BNT162b2 vaccine reduced risk of SARS-CoV-2 infection for at least 90 days in CYP aged 12-17 years. Vaccine protection varied for SARS-CoV-2 variant type (lower for Omicron than Delta variant), and was enhanced by pre-vaccination SARS-CoV-2 infection. Severity of COVID-19 presentation after vaccination was generally milder, although unvaccinated CYP also had generally mild disease. Overall, vaccination was well-tolerated.FundingUK Government Department of Health and Social Care, Chronic Disease Research Foundation, The Wellcome Trust, UK Engineering and Physical Sciences Research Council, UK Research and Innovation London Medical Imaging & Artificial Intelligence Centre for Value Based Healthcare, UK National Institute for Health Research, UK Medical Research Council, British Heart Foundation and Alzheimer’s Society, and ZOE Limited.Research in contextEvidence before this study:We searched PubMed database for peer-reviewed articles and medRxiv for preprint papers, published between January 1, 2021 and February 15, 2022 using keywords (“SARS-CoV-2” OR “COVID-19”) AND (child* OR p?ediatric* OR teenager*) AND (“vaccin*” OR “immunization campaign”) AND (“efficacy” OR “effectiveness” OR “symptoms”) AND (“delta” or “omicron” OR “B.1.617.2” OR “B.1.1.529”). The PubMed search retrieved 36 studies, of which fewer than 30% specifically investigated individuals Eleven studies explored SARS-CoV-2 viral transmission: seroprevalence in children (n=4), including age-dependency of susceptibility to SARS-CoV-2 infection (n=1), SARS-CoV-2 transmission in schools (n=5), and the effect of school closure on viral transmission (n=1).Eighteen documents reported clinical aspects, including manifestation of infection (n=13), symptomatology, disease duration, and severity in children. Other studies estimated emergency department visits, hospitalization, need for intensive care, and/or deaths in children (n=4), and explored prognostic factors (n=1).Thirteen studies explored vaccination-related aspects, including vaccination of children within specific paediatric co-morbidity groups (e.g., children with Down syndrome, inflammatory bowel disease, and cancer survivors, n=4), mRNA vaccine efficacy in children and adolescents from the general population (n=7), and the relation between vaccination and severity of disease and hospitalization cases (n=2). Four clinical trials were conducted using mRNA vaccines in minors, also exploring side effects. Sixty percent of children were found to have side effects after BNT162b2 vaccination, and especially after the second dose; however, most symptoms were mild and transient apart from rare uncomplicated skin ulcers. Two studies focused on severe adverse effects and safety of SARS-CoV-2 vaccines in children, reporting on myocarditis episodes and two cases of Guillain-Barrè syndrome. All other studies were beyond the scope of our research.Added value of this study:We assessed multiple components of the UK vaccination campaign in a cohort of children and young people (CYP) aged 12-17 years drawn from a large UK community-based citizen-science study, who received a first dose of BNT162b2 vaccine. We describe a variant-dependent protective effect of the first dose against both Delta and Omicron, with additional protective effect of pre-vaccination SARS- CoV-2 infection on post-vaccination re-infection. We compare the illness profile in CYP infected post-vaccination with that of unvaccinated CYP, demonstrating overall milder disease with fewer symptoms for vaccinated CYP. We describe local and systemic side-effects during the first week following first-dose vaccination, confirming that local symptoms are common, systemic symptoms uncommon, and both usually transient.Implications of all the available evidence:Our data confirm that first dose BNT162b2 vaccination in CYP reduces risk of infection by SARS-CoV-2 variants, with generally local and brief side-effects. If infected after vaccination, COVID-19 is milder, if manifest at all. The study aims to contribute quantitative evidence to the risk-benefit evaluation of vaccination in CYP to inform discussion regarding rationale for their vaccination and the designing of national immunisation campaigns for this age group; and applies citizen-science approaches in the conduct of epidemiological surveillance and data collection in the UK community.Importantly, this study was conducted during Delta and Omicron predominance in UK; specificity of vaccine efficacy to variants is also illustrated; and results may not be generalizable to future SARS-CoV-2 strains.

BackgroundThe Delta (B.1.617.2) variant became the predominant UK circulating SARS-CoV-2 strain in May 2021. How Delta infection compares with previous variants is unknown.MethodsThis prospective observational cohort study assessed symptomatic adults participating in the app-based COVID Symptom Study who tested positive for SARS-CoV-2 from May 26 to July 1, 2021 (Delta overwhelmingly predominant circulating UK variant), compared (1:1, age- and sex-matched) with individuals presenting from December 28, 2020 to May 6, 2021 (Alpha (B.1.1.7) predominant variant). We assessed illness (symptoms, duration, presentation to hospital) during Alpha- and Delta-predominant timeframes; and transmission, reinfection, and vaccine effectiveness during the Delta-predominant period.Findings3,581 individuals (aged 18 to 100 years) from each timeframe were assessed. The seven most frequent symptoms were common to both variants. Within the first 28 days of illness, some symptoms were more common with Delta vs. Alpha infection (including fever, sore throat and headache) and vice versa (dyspnoea). Symptom burden in the first week was higher with Delta vs. Alpha infection; however, the odds of any given symptom lasting ≥7 days was either lower or unchanged. Illness duration ≥28 days was lower with Delta vs. Alpha infection, though unchanged in unvaccinated individuals. Hospitalisation for COVID-19 was unchanged. The Delta variant appeared more (1·47) transmissible than Alpha. Re-infections were low in all UK regions. Vaccination markedly (69-84%) reduced risk of Delta infection.InterpretationCOVID-19 from Delta or Alpha infections is clinically similar. The Delta variant is more transmissible than Alpha; however, current vaccines show good efficacy against disease.FundingUK Government Department of Health and Social Care, Wellcome Trust, UK Engineering and Physical Sciences Research Council, UK Research and Innovation London Medical Imaging & Artificial Intelligence Centre for Value Based Healthcare, UK National Institute for Health Research, UK Medical Research Council, British Heart Foundation, Alzheimer’s Society, and ZOE Limited.Research in contextEvidence before this studyTo identify existing evidence for differences (including illness, transmissibility, and vaccine effectiveness) from SARS-CoV-2 infection due to Alpha (B.1.1.7) and Delta (B.1.617.2) variants, we searched PubMed for peer-reviewed articles and medRxiv for preprint publications between March 1 and November 18, 2021 using keywords (“SARS-CoV-2” OR “COVID-19”) AND (“delta variant” OR “B.1.617.2”) AND (symptom* OR transmiss* OR “disease duration” OR “illness duration” OR “symptom* duration”). Searches were not restricted by language. Among 169 identified PubMed articles, we found evidence that Delta variant has increased replication capacity (from 4-fold, up to 21-fold, compared with wild-type) and greater transmissibility (estimated between +20% and +97%), compared with previous strains. Currently available vaccines may have 2- to 5-fold lower neutralizing response to Delta vs. previous variants, depending on vaccine formulation, although their protective effect against severe disease and death appears to remain strong. REACT-1 study found that in UK infections were increasing exponentially in the 5-17-year old children in September 2021, coinciding with the start of the autumn school term in England. This was interpreted as an effect of the relatively low rate of vaccinated individuals in this age group. Other studies found that in unvaccinated individuals, Delta variant may be associated with higher odds of pneumonia, oxygen requirement, emergency care requests, ICU admission, and death. In a study of 27 (mainly young) cases, 22 persons were symptomatic, with fever (41%), cough (33%), headache (26%), and sore throat (26%) the commonest symptoms. We found no studies, beyond case series, investigating symptom and/or illness duration due to Delta variant infection otherwise.Added value of this studyUsing data from one of the largest UK citizen science epidemiological initiatives, we describe and compare illness (symptom duration, burden, profile, risk of long illness, and hospital attendance) in symptomatic community-based adults presenting when either the Alpha or Delta variant was the predominant circulating strain of SARS-CoV-2 in the UK. We assess evidence of transmission, reinfection, and vaccine effectiveness. Our data show that the seven most common symptoms with Delta infection were the same as with Alpha infection. Risks of illness duration ≥7 days and ≥28 days, and of requiring hospital care, were not increased. In line with previous research, we found increased transmissibility of Delta vs. previous variants; and no evidence of increased re-infection rates. Our data support high vaccine efficacy of BNT162b2 and ChAdOx1 nCoV-19 formulations against Delta variant infection. Overall, our study adds quantitative information regarding meaningful clinical differences in COVID-19 due to Delta vs. other variants.Implications of all the available evidenceOur observational data confirm that COVID-19 disease in UK in adults is generally comparable to infection with the Alpha variant, including in elderly individuals. Our data contribute to epidemiological surveillance from the wider UK population and may capture information from COVID-19 presentation within the community that might be missed in healthcare-based surveillance. Our data may be useful in informing healthcare service planning, vaccination policies, and measures for social protection.

In this paper, we applied a method for quantifying several left intraventricular hemodynamic parameters from 4D Flow data and its application in a proof-of-concept study in dilated cardiomyopathy (DCM) patients. In total, 12 healthy volunteers and 13 DCM patients under treatment underwent short-axis cine b-SSFP and 4D Flow MRI. Following 3D segmentation of the left ventricular (LV) cavity and registration of both sequences, several hemodynamic parameters were calculated at peak systole, e-wave, and end-diastole using a finite element approach. Sensitivity, inter- and intra-observer reproducibility of hemodynamic parameters were evaluated by analyzing LV segmentation. A local analysis was performed by dividing the LV cavity into 16 regions. We found significant differences between volunteers and patients in velocity, vorticity, viscous dissipation, energy loss, and kinetic energy at peak systole and e-wave. Furthermore, although five patients showed a recovered ejection fraction after treatment, their hemodynamic parameters remained low. We obtained several hemodynamic parameters with high inter- and intra-observer reproducibility. The sensitivity study revealed that hemodynamic parameters showed a higher accuracy when the segmentation underestimates the LV volumes. Our approach was able to identify abnormal flow patterns in DCM patients compared to volunteers and can be applied to any other cardiovascular diseases.

The Covid Symptom Study, a smartphone-based surveillance study on COVID-19 symptoms in the population, is an exemplar of big data citizen science. As of May 23rd, 2021, over 5 million participants have collectively logged over 360 million self-assessment reports since its introduction in March 2020. The success of the Covid Symptom Study creates significant technical challenges around effective data curation. The primary issue is scale. The size of the dataset means that it can no longer be readily processed using standard Python-based data analytics software such as Pandas on commodity hardware. Alternative technologies exist but carry a higher technical complexity and are less accessible to many researchers. We present ExeTera, a Python-based open source software package designed to provide Pandas-like data analytics on datasets that approach terabyte scales. We present its design and capabilities, and show how it is a critical component of a data curation pipeline that enables reproducible research across an international research group for the Covid Symptom Study.

BackgroundThe Delta (B.1.617.2) SARS-CoV-2 variant became the predominant UK circulating strain in May 2021. Whether COVID-19 from Delta infection differs to infection with other variants in children is unknown.MethodsThrough the prospective COVID Symptom Study, 109,626 UK school-aged children were proxy-reported between December 28, 2020 and July 8, 2021. We selected all symptomatic children who tested positive for SARS-CoV-2 and were proxy-reported at least weekly, within two timeframes: December 28, 2020 to May 6, 2021 (Alpha (B.1.1.7) the main UK circulating variant); and May 26 to July 8, 2021 (Delta the main UK circulating variant). We assessed illness profiles (symptom prevalence, duration, and burden), hospital presentation, and presence of long (≥28 day) illness; and calculated odds ratios for symptoms presenting within the first 28 days of illness.Findings694 (276 younger [5-11 years], 418 older [12-17 years]) symptomatic children tested positive for SARS-CoV-2 with Alpha infection and 706 (227 younger and 479 older) children with Delta infection. Median illness duration was short with either variant (overall cohort: 5 days (IQR 2–9.75) with Alpha, 5 days (IQR 2-9) with Delta). The seven most prevalent symptoms were common to both variants. Symptom burden over the first 28 days was slightly greater with Delta compared with Alpha infection (in younger children, 3 (IQR 2–5) with Alpha, 4 (IQR 2–7) with Delta; in older children 5 (IQR 3–8) with Alpha and 6 (IQR 3–9) with Delta infection in older children). The odds of several symptoms were higher with Delta than Alpha infection, including headache and fever. Few children presented to hospital, and long illness duration was uncommon, with either variant.InterpretationCOVID-19 in UK school-aged children due to SARS-CoV-2 Delta strain B.1.617.2 resembles illness due to the Alpha variant B.1.1.7., with short duration and similar symptom burden.FundingZOE Limited, UK Government Department of Health and Social Care, Wellcome Trust, UK Engineering and Physical Sciences Research Council, UK Research and Innovation London Medical Imaging & Artificial Intelligence Centre for Value Based Healthcare, UK National Institute for Health Research, UK Medical Research Council, British Heart Foundation and Alzheimer’s Society.EthicsEthics approval was granted by KCL Ethics Committee (reference LRS-19/20-18210).Research in contextEvidence before this studyTo identify existing evidence for differences in COVID-19 due to infection with Alpha (B.1.1.7) or Delta (B.1.617.2) SARS-CoV-2 variants, we searched PubMed for peer-reviewed articles and medRxiv for preprint publications between March 1, and September 17, 2021 using keywords (“SARS-CoV-2” OR “COVID-19”) AND (children OR p?ediatric*) AND (“delta variant” OR “B.1.617.2”). We did not restrict our search by language. Of twenty published articles identified in PubMed, we found one case study describing disease presentation associated with Delta variant infection in a child. Another study examining the increase in hospitalization rates of paediatric cases in USA from August 1, 2020 to August 27, 2021 stated that “It is not known whether the B.1.617.2 (Delta) variant […] causes different clinical outcomes in children and adolescents compared with variants that circulated earlier.” Four studies reported cases of transmission of the Delta variant in school and community contexts; and two discussed screening testing in school-aged children (thus not directly relevant to the research question here). Remaining papers did not target paediatric age specifically. We found no studies investigating differences in COVID-19 presentation (e.g., duration, burden, individual symptoms) in school-aged children either in the UK or world-wide.Added value of this studyWe describe and compare illness profiles in symptomatic UK school-aged children (aged 5–17 years) with COVID-19 when either Alpha or Delta strains were the predominant circulating SARS-CoV-2 variant. Our data, collected through one of the largest UK citizen science epidemiological initiatives, show that symptom profile and illness duration of COVID-19 are broadly similar between the strains. Although there were slightly more symptoms with Delta than with Alpha, particularly in older children, this was offset by similar symptom duration (whether considered for symptoms individually or for illness overall). Our study adds quantitative information to the debate on whether there are meaningful clinical differences in COVID-19 due to Alpha vs. Delta variants; and contributes to the discussion regarding rationale for vaccinating children (particularly younger children) against SARS-CoV-2.Implications of all the available evidenceOur data confirm that COVID-19 in UK school-aged children is usually of short duration and similar symptom burden, whether due to Delta or Alpha. Our data contribute to epidemiological surveillance from the wider UK population, and we capture common and generally mild paediatric presentations of COVID-19 that might be missed using clinician-based surveillance alone. Our data will also be useful for the vaccination debate.

BackgroundIdentifying and testing individuals likely to have SARS-CoV-2 is critical for infection control, including post-vaccination. Vaccination is a major public health strategy to reduce SARS-CoV-2 infection globally. Some individuals experience systemic symptoms post-vaccination, which overlap with COVID-19 symptoms. This study compared early post-vaccination symptoms in individuals who subsequently tested positive or negative for SARS-CoV-2, using data from the COVID Symptom Study (CSS) app.DesignWe conducted a prospective observational study in UK CSS participants who were asymptomatic when vaccinated with Pfizer-BioNTech mRNA vaccine (BNT162b2) or Oxford-AstraZeneca adenovirus-vectored vaccine (ChAdOx1 nCoV-19) between 8 December 2020 and 17 May 2021, who subsequently reported symptoms within seven days (other than local symptoms at injection site) and were tested for SARS-CoV-2, aiming to differentiate vaccination side-effects per se from superimposed SARS-CoV-2 infection. The post-vaccination symptoms and SARS-CoV-2 test results were contemporaneously logged by participants. Demographic and clinical information (including comorbidities) were also recorded. Symptom profiles in individuals testing positive were compared with a 1:1 matched population testing negative, including using machine learning and multiple models including UK testing criteria.FindingsDifferentiating post-vaccination side-effects alone from early COVID-19 was challenging, with a sensitivity in identification of individuals testing positive of 0.6 at best. A majority of these individuals did not have fever, persistent cough, or anosmia/dysosmia, requisite symptoms for accessing UK testing; and many only had systemic symptoms commonly seen post-vaccination in individuals negative for SARS-CoV-2 (headache, myalgia, and fatigue).InterpretationPost-vaccination side-effects per se cannot be differentiated from COVID-19 with clinical robustness, either using symptom profiles or machine-derived models. Individuals presenting with systemic symptoms post-vaccination should be tested for SARS-CoV-2, to prevent community spread.FundingZoe Limited, UK Government Department of Health and Social Care, Wellcome Trust, UK Engineering and Physical Sciences Research Council, UK National Institute for Health Research, UK Medical Research Council and British Heart Foundation, Alzheimer’s Society, Chronic Disease Research Foundation, Massachusetts Consortium on Pathogen Readiness (MassCPR).Research in contextEvidence before this studyThere are now multiple surveillance platforms internationally interrogating COVID-19 and/or post-vaccination side-effects. We designed a study to examine for differences between vaccination side-effects and early symptoms of COVID-19. We searched PubMed for peer-reviewed articles published between 1 January 2020 and 21 June 2021, using keywords: “COVID-19” AND “Vaccination” AND (“mobile application” OR “web tool” OR “digital survey” OR “early detection” OR “Self-reported symptoms” OR “side-effects”). Of 185 results, 25 studies attempted to differentiate symptoms of COVID-19 vs. post-vaccination side-effects; however, none used artificial intelligence (AI) technologies (“machine learning”) coupled with real-time data collection that also included comprehensive and systematic symptom assessment. Additionally, none of these studies attempt to discriminate the early signs of infection from side-effects of vaccination (specifically here: Pfizer-BioNTech mRNA vaccine (BNT162b2) and Oxford-AstraZeneca adenovirus-vectored vaccine (ChAdOx1 nCoV-19)). Further, none of these studies sought to provide comparisons with current testing criteria used by healthcare services.Added value of this studyThis study, in a uniquely large community-based cohort, uses prospective data capture in a novel effort to identify individuals with COVID-19 in the immediate post-vaccination period. Our results show that early symptoms of SARS-CoV-2 cannot be differentiated from vaccination side-effects robustly. Thus, post-vaccination systemic symptoms should not be ignored, and testing should be considered to prevent COVID-19 dissemination by vaccinated individuals.Implications of all the available evidenceOur study demonstrates the critical importance of testing symptomatic individuals - even if vaccinated – to ensure early detection of SARS-CoV-2 infection, helping to prevent future pandemic waves in the UK and elsewhere.

One of the challenges in developing deep learning algorithms for medical image segmentation is the scarcity of annotated training data. To overcome this limitation, data augmentation and semi-supervised learning (SSL) methods have been developed. However, these methods have limited effectiveness as they either exploit the existing data set only (data augmentation) or risk negative impact by adding poor training examples (SSL). Segmentations are rarely the final product of medical image analysis - they are typically used in downstream tasks to infer higher-order patterns to evaluate diseases. Clinicians take into account a wealth of prior knowledge on biophysics and physiology when evaluating image analysis results. We have used these clinical assessments in previous works to create robust quality-control (QC) classifiers for automated cardiac magnetic resonance (CMR) analysis. In this paper, we propose a novel scheme that uses QC of the downstream task to identify high quality outputs of CMR segmentation networks, that are subsequently utilised for further network training. In essence, this provides quality-aware augmentation of training data in a variant of SSL for segmentation networks (semiQCSeg). We evaluate our approach in two CMR segmentation tasks (aortic and short axis cardiac volume segmentation) using UK Biobank data and two commonly used network architectures (U-net and a Fully Convolutional Network) and compare against supervised and SSL strategies. We show that semiQCSeg improves training of the segmentation networks. It decreases the need for labelled data, while outperforming the other methods in terms of Dice and clinical metrics. SemiQCSeg can be an efficient approach for training segmentation networks for medical image data when labelled datasets are scarce., MICCAI STACOM 2020

SummaryBackgroundMental health issues have been reported after SARS-CoV-2 infection. However, comparison to prevalence in uninfected individuals and contribution from common risk factors (e.g., obesity, comorbidities) have not been examined. We identified how COVID-19 relates to mental health in the large community-based COVID Symptom Study.MethodsWe assessed anxiety and depression symptoms using two validated questionnaires in 413,148 individuals between February and April 2021; 26,998 had tested positive for SARS-CoV-2. We adjusted for physical and mental pre-pandemic comorbidities, BMI, age, and sex.FindingsOverall, 26.4% of participants met screening criteria for general anxiety and depression. Anxiety and depression were slightly more prevalent in previously SARS-CoV-2 positive (30.4%) vs. negative (26.1%) individuals. This association was small compared to the effect of an unhealthy BMI and the presence of other comorbidities, and not evident in younger participants (≤40 years). Findings were robust to multiple sensitivity analyses. Association between SARS-CoV-2 infection and anxiety and depression was stronger in individuals with recent (120 days) infection, suggesting a short-term effect.InterpretationA small association was identified between SARS-CoV-2 infection and anxiety and depression symptoms. The proportion meeting criteria for self-reported anxiety and depression disorders is only slightly higher than pre-pandemic.FundingZoe Limited, National Institute for Health Research, Chronic Disease Research Foundation, National Institutes of Health, Medical Research Council UK

BACKGROUND: COVID-19 vaccines show excellent efficacy in clinical trials and effectiveness in real-world data, but some people still become infected with SARS-CoV-2 after vaccination. This study aimed to identify risk factors for post-vaccination SARS-CoV-2 infection and describe the characteristics of post-vaccination illness.METHODS: This prospective, community-based, nested, case-control study used self-reported data (eg, on demographics, geographical location, health risk factors, and COVID-19 test results, symptoms, and vaccinations) from UK-based, adult (≥18 years) users of the COVID Symptom Study mobile phone app. For the risk factor analysis, cases had received a first or second dose of a COVID-19 vaccine between Dec 8, 2020, and July 4, 2021; had either a positive COVID-19 test at least 14 days after their first vaccination (but before their second; cases 1) or a positive test at least 7 days after their second vaccination (cases 2); and had no positive test before vaccination. Two control groups were selected (who also had not tested positive for SARS-CoV-2 before vaccination): users reporting a negative test at least 14 days after their first vaccination but before their second (controls 1) and users reporting a negative test at least 7 days after their second vaccination (controls 2). Controls 1 and controls 2 were matched (1:1) with cases 1 and cases 2, respectively, by the date of the post-vaccination test, health-care worker status, and sex. In the disease profile analysis, we sub-selected participants from cases 1 and cases 2 who had used the app for at least 14 consecutive days after testing positive for SARS-CoV-2 (cases 3 and cases 4, respectively). Controls 3 and controls 4 were unvaccinated participants reporting a positive SARS-CoV-2 test who had used the app for at least 14 consecutive days after the test, and were matched (1:1) with cases 3 and 4, respectively, by the date of the positive test, health-care worker status, sex, body-mass index (BMI), and age. We used univariate logistic regression models (adjusted for age, BMI, and sex) to analyse the associations between risk factors and post-vaccination infection, and the associations of individual symptoms, overall disease duration, and disease severity with vaccination status.FINDINGS: Between Dec 8, 2020, and July 4, 2021, 1 240 009 COVID Symptom Study app users reported a first vaccine dose, of whom 6030 (0·5%) subsequently tested positive for SARS-CoV-2 (cases 1), and 971 504 reported a second dose, of whom 2370 (0·2%) subsequently tested positive for SARS-CoV-2 (cases 2). In the risk factor analysis, frailty was associated with post-vaccination infection in older adults (≥60 years) after their first vaccine dose (odds ratio [OR] 1·93, 95% CI 1·50-2·48; pINTERPRETATION: To minimise SARS-CoV-2 infection, at-risk populations must be targeted in efforts to boost vaccine effectiveness and infection control measures. Our findings might support caution around relaxing physical distancing and other personal protective measures in the post-vaccination era, particularly around frail older adults and individuals living in more deprived areas, even if these individuals are vaccinated, and might have implications for strategies such as booster vaccinations.FUNDING: ZOE, the UK Government Department of Health and Social Care, the Wellcome Trust, the UK Engineering and Physical Sciences Research Council, UK Research and Innovation London Medical Imaging and Artificial Intelligence Centre for Value Based Healthcare, the UK National Institute for Health Research, the UK Medical Research Council, the British Heart Foundation, and the Alzheimer's Society.

BackgroundCOVID-19 vaccines show excellent efficacy in clinical trials and real-world data, but some people still contract SARS-CoV-2 despite vaccination. This study sought to identify risk factors associated with SARS-CoV-2 infection post-vaccination and describe characteristics of post-vaccination illness.MethodsAmongst 1,102,192 vaccinated UK adults from the COVID Symptom Study, 2394 (0.2%) cases of post-vaccination SARS-CoV-2 infection were identified between 8th December 2020 and 1st May 2021. Using a control group of vaccinated individuals testing negative, we assessed the associations of age, frailty, comorbidity, area-level deprivation and lifestyle factors with infection. Illness profile post-vaccination was assessed using a second control group of unvaccinated cases.FindingsOlder adults with frailty (OR=2.78, 95% CI=[1.98-3.89], p-valueInterpretationOur findings suggest that older individuals with frailty and those living in most deprived areas are at increased risk of infection post-vaccination. We also showed reduced symptom burden and duration in those infected post-vaccination. Efforts to boost vaccine effectiveness in at-risk populations, and to targeted infection control measures, may still be appropriate to minimise SARS-CoV-2 infection.FundingThis work is supported by UK Department of Health via the National Institute for Health Research (NIHR) comprehensive Biomedical Research Centre (BRC) award to Guy’s & St Thomas’ NHS Foundation Trust in partnership with King’s College London and King’s College Hospital NHS Foundation Trust and via a grant to ZOE Global; the Wellcome Engineering and Physical Sciences Research Council (EPSRC) Centre for Medical Engineering at King’s College London (WT 203148/Z/16/Z). Investigators also received support from the Chronic Disease Research Foundation, the Medical Research Council (MRC), British Heart Foundation, the UK Research and Innovation London Medical Imaging & Artificial Intelligence Centre for Value Based Healthcare, the Wellcome Flagship Programme (WT213038/Z/18/Z and Alzheimer’s Society (AS-JF-17-011), and the Massachusetts Consortium on Pathogen Readiness (MassCPR).Research in contextEvidence before this studyTo identify existing evidence for risk factors and characteristics of SARS-CoV-2 infection post-vaccination, we searched PubMed for peer-reviewed articles published between December 1, 2020 and May 18, 2021 using keywords (“COVID-19” OR “SARS-CoV-2”) AND (“Vaccine” OR “vaccination”) AND (“infection”) AND (“risk factor*” OR “characteristic*”). We did not restrict our search by language or type of publication. Of 202 articles identified, we found no original studies on individual risk and protective factors for COVID-19 infection following vaccination nor on nature and duration of symptoms in vaccinated, community-based individuals. Previous studies in unvaccinated populations have shown that social and occupational factors influence risk of SARS-CoV-2infection, and that personal factors (age, male sex, multiple morbidities and frailty) increased risk for adverse outcomes in COVID-19. Phase III clinical trials have demonstrated good efficacy of BNT162b2 and ChAdOx1 vaccines against SARS-CoV-2 infection, confirmed in published real-world data, which additionally showed reduced risk of adverse outcomes including hospitalisation and death.Added value of this studyThis is the first observational study investigating characteristics of and factors associated with SARS-CoV-2 infection after COVID-19 vaccination. We found that vaccinated individuals with frailty had higher rates of infection after vaccination than those without. Adverse determinants of health such as increased social deprivation, obesity, or a less healthy diet were associated with higher likelihood of infection after vaccination. In comparison with unvaccinated individuals, those with post-vaccination infection had fewer symptoms of COVID-19, and more were entirely asymptomatic. Fewer vaccinated individuals experienced five or more symptoms, required hospitalisation, and, in the older adult group, fewer had prolonged illness duration (symptoms lasting longer than 28 days).Implications of all the available evidenceSome individuals still contract COVID-19 after vaccination and our data suggest that frail older adults and those living in more deprived areas are at higher risk. However, in most individuals illness appears less severe, with reduced need for hospitalisation and lower risk of prolonged illness duration. Our results are relevant for health policy post-vaccination and highlight the need to prioritise those most at risk, whilst also emphasising the balance between the importance of personal protective measures versus adverse effects from ongoing social restrictions. Strategies such as timely prioritisation of booster vaccination and optimised infection control could be considered for at-risk groups. Research is also needed on how to enhance the immune response to vaccination in those at higher risk.

BackgroundIn children, SARS-CoV-2 is usually asymptomatic or causes a mild illness of short duration. Persistent illness has been reported; however, its prevalence and characteristics are unclear. We aimed to determine illness duration and characteristics in symptomatic UK school-aged children tested for SARS-CoV-2 using data from the COVID Symptom Study, the largest UK citizen participatory epidemiological study to date.MethodsData from 258,790 children aged 5-17 years were reported by an adult proxy between 24 March 2020 and 22 February 2021. Illness duration and symptom profiles were analysed for all children testing positive for SARS-CoV-2 for whom illness duration could be determined, considered overall and within younger (5-11 years) and older (12-17 years) groups. Data from symptomatic children testing negative for SARS-CoV-2, matched 1:1 for age, gender, and week of testing, were also assessed.Findings1,734 children (588 younger, 1,146 older children) had a positive SARS-CoV-2 test result and calculable illness duration within the study time frame. The commonest symptoms were headache (62.2%) and fatigue (55.0%). Median illness duration was six days (vs. three days in children testing negative), and was positively associated with age (rs 0.19, pSeventy-seven (4.4%) children had illness duration ≥28 days (LC28), more commonly experienced by older vs. younger children (59 (5.1%) vs. 18 (3.1%), p=0.046). The commonest symptoms experienced by these children were fatigue (84%), headache (80%) and anosmia (80%); however, by day 28 the symptom burden was low (median, two). Only 25 (1.8%) of 1,379 children experienced symptoms for ≥56 days. Few children (15 children, 0.9%) in the negatively-tested cohort experienced prolonged symptom duration; however, these children experienced greater symptom burden (both throughout their illness and at day 28) than children positive for SARS-CoV-2.InterpretationSome children with COVID-19 experience prolonged illness duration. Reassuringly, symptom burden in these children did not increase with time, and most recovered by day 56. Some children who tested negative for SARS-CoV-2 also had persistent and burdensome illness. A holistic approach for all children with persistent illness during the pandemic is appropriate.Research in contextEvidence before this studySARS-CoV-2 in children is usually asymptomatic or manifests as a mild illness of short duration. Concerns have been raised regarding prolonged illness in children, with no clear resolution of symptoms several weeks after onset, as is observed in some adults. How common this might be in children, the clinical features of such prolonged illness in children, and how it might compare with illnesses from other respiratory viruses (and with general population prevalence of these symptoms) is unclear.Added value of this studyWe provide systematic description of COVID-19 in UK school-aged children. Our data, collected in a digital surveillance platform through one of the largest UK citizen science initiatives, show that long illness duration after SARS-CoV-2 infection in school-aged children does occur, but is uncommon, with only a small proportion of children experiencing illness duration beyond four weeks; and the symptom burden in these children usually decreases over time. Almost all children have symptom resolution by eight weeks, providing reassurance about long-term outcomes. Additionally, symptom burden in children with long COVID was not greater than symptom burden in children with long illnesses due to causes other than SARS-CoV-2 infection.Implications of all the available evidenceOur data confirm that COVID-19 in UK school-aged children is usually of short duration and of low symptom burden. Some children do experience longer illness duration, validating their experience; however, most of these children usually recover with time. Our findings highlight that appropriate resources will be necessary for any child with prolonged illness, whether due to COVID-19 or other illness. Our study provides timely and critical data to inform discussions around the impact and implications of the pandemic on paediatric healthcare resource allocation.

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, characterised by a rapid and irregular electrical activation of the atria. Treatments for AF are often ineffective and few atrial biomarkers exist to automatically characterise atrial function and aid in treatment selection for AF. Clinical metrics of left atrial (LA) function, such as ejection fraction (EF) and active atrial contraction ejection fraction (aEF), are promising, but have until now typically relied on volume estimations extrapolated from single-slice images.

Delayed-enhancement cardiac magnetic resonance (DE-CMR) provides important diagnostic and prognostic information on myocardial viability. The presence and extent of late gadolinium enhancement (LGE) in DE-CMR is negatively associated with the probability of improvement in left ventricular function after revascularization. Moreover, LGE findings can support the diagnosis of several other cardiomyopathies, but their absence does not rule them out, making disease classification by visual assessment difficult. In this work, we propose deep learning neural networks that can automatically predict myocardial disease from patient clinical information and DE-CMR. All the proposed networks achieved very good classification accuracy (>85%). Including information from DE-CMR (directly as images or as metadata following DE-CMR segmentation) is valuable in this classification task, improving the accuracy to 95–100%.

Valve annuli motion and morphology, measured from non-invasive imaging, can be used to gain a better understanding of healthy and pathological heart function. Measurements such as long-axis strain as well as peak strain rates provide markers of systolic function. Likewise, early and late-diastolic filling velocities are used as indicators of diastolic function. Quantifying global strains, however, requires a fast and precise method of tracking long-axis motion throughout the cardiac cycle. Valve landmarks such as the insertion of leaflets into the myocardial wall provide features that can be tracked to measure global long-axis motion. Feature tracking methods require initialisation, which can be time-consuming in studies with large cohorts. Therefore, this study developed and trained a neural network to identify ten features from unlabeled long-axis MR images: six mitral valve points from three long-axis views, two aortic valve points and two tricuspid valve points. This study used manual annotations of valve landmarks in standard 2-, 3- and 4-chamber long-axis images collected in clinical scans to train the network. The accuracy in the identification of these ten features, in pixel distance, was compared with the accuracy of two commonly used feature tracking methods as well as the inter-observer variability of manual annotations. Clinical measures, such as valve landmark strain and motion between end-diastole and end-systole, are also presented to illustrate the utility and robustness of the method.

Introduction The importance of atrial mechanical dysfunction in atrial and ventricular pathologies is becoming increasingly recognised. Although machine learning (ML) tools have the ability to automatically estimate atrial function, to date ML techniques have not been used to automatically estimate atrial volumes and functional parameters directly from short axis CINE MRI. Purpose We introduce a convolutional neural network (CNN) to automatically segment the left atria (LA) in CINE-MRI. As a demonstration of the clinical utility of this technique, we calculated LA and left ventricular (LV) ejection fractions automatically from CINE images. Methods Short axis CINE MRI stacks, covering both ventricles and atria, were obtained in a 1.5T Philips Ingenia scanner. A 2D bSSFP ECG-gated protocol was used (FA=60°, TE/TR=1.5/2.9 ms), typical FOV =385 x 310 x 150 mm3, acquisition matrix = 172 x 140, slice thickness = 10 mm, reconstructed with resolution 1.25 x 1.25 x 10 mm3, 30–50 cardiac phases. Images were collected from 37 AF patients in sinus rythm at the time of scan (31–72 years old, 75% male, 18 with paroxysmal AF (PAF), 19 with persistent AF (persAF)). To automatically segment the LA, we used a dedicated CNN that follows a U-Net architecture and was trained in 715 images of the LA, manually segmented by an expert. Data augmentation techniques that included noise addition and linear and non-linear image transforms were also used to increase the training dataset. Ventricular structures, including the LV blood pool, were automatically segmented in these images using a CNN previously trained for this task. Volumetric time plots of LA and LV volume were produced and used to automatically compute maximal and minimal volumes, from which LA and LV ejection fractions (EFs) were assessed. A Bland-Altman analysis compared these automatically computed LA volumes and LA EFs with clinical manual estimates from the same scanning session. Results The CNN achieved very good quality LA segmentations when compared to manual ones (Fig a,b): Dice coefficients (0.90±0.07), median contour distances (0.50±1.12mm) and Hausdorff distances (6.70±6.16mm). Bland-Altman analyses show very good agreement between automatic and manual LA volumes and EFs (Fig e). A moderate linear correlation between LA and LV EFs in AF patients was found (Fig d). The measured LA EF was higher for PAF (29±8%) than PersAF patients (21±11%), although non-significantly (t-test p-value: 0.10). Conclusions We present a reliable automatic method to perform LA segmentations from CINE MRI across the entire cardiac cycle. This approachs opens up the possibility of automatically calculating more sophisticated biomarkers of LA function which take into account information about LA volumes across the entire cardiac cycle, including biomarkers of LA booster pump function. Figure 1 Funding Acknowledgement Type of funding source: Foundation. Main funding source(s): British Heart Foundation; EPSRC/Wellcome Centre for Medical Engineering

Background: Identifying and testing individuals likely to have SARS-CoV-2 is critical for infection control, including post-vaccination. Vaccination is a major public health strategy to reduce SARS-CoV-2 infection globally. Some individuals experience systemic symptoms post-vaccination, which overlap with COVID-19 symptoms. This study compared early post-vaccination symptoms in individuals who subsequently tested positive or negative for SARS-CoV-2, using data from the COVID Symptom Study (CSS) app. Methods: We conducted a prospective observational study in 1,072,313 UK CSS participants who were asymptomatic when vaccinated with Pfizer-BioNTech mRNA vaccine (BNT162b2) or Oxford-AstraZeneca adenovirus-vectored vaccine (ChAdOx1 nCoV-19) between 8 December 2020 and 17 May 2021, who subsequently reported symptoms within seven days (N=362,770) (other than local symptoms at injection site) and were tested for SARS-CoV-2 (N=14,842), aiming to differentiate vaccination side-effects per se from superimposed SARS-CoV-2 infection. The post-vaccination symptoms and SARS-CoV-2 test results were contemporaneously logged by participants. Demographic and clinical information (including comorbidities) were recorded. Symptom profiles in individuals testing positive were compared with a 1:1 matched population testing negative, including using machine learning and multiple models considering UK testing criteria. Findings: Differentiating post-vaccination side-effects alone from early COVID-19 was challenging, with a sensitivity in identification of individuals testing positive of 0.6 at best. Most of these individuals did not have fever, persistent cough, or anosmia/dysosmia, requisite symptoms for accessing UK testing; and many only had systemic symptoms commonly seen post-vaccination in individuals negative for SARS-CoV-2 (headache, myalgia, and fatigue). Interpretation: Post-vaccination symptoms per se cannot be differentiated from COVID-19 with clinical robustness, either using symptom profiles or machine-derived models. Individuals presenting with systemic symptoms post-vaccination should be tested for SARS-CoV-2 or quarantining, to prevent community spread. Funding: UK Government Department of Health and Social Care, Wellcome Trust, UK Engineering and Physical Sciences Research Council, UK National Institute for Health Research, UK Medical Research Council and British Heart Foundation, Chronic Disease Research Foundation, Zoe Limited.

Real-time (RT) sequences for cardiac magnetic resonance imaging (CMR) have recently been proposed as alternatives to standard cine CMR sequences for subjects unable to hold the breath or suffering from arrhythmia. RT image acquisitions during free breathing produce comparatively poor quality images, a trade-off necessary to achieve the high temporal resolution needed for RT imaging and hence are less suitable in the clinical assessment of cardiac function. We demonstrate the application of a CycleGAN architecture to train autoencoder networks for synthesising cine-like images from RT images and vice versa. Applying this conversion to real-time data produces clearer images with sharper distinctions between myocardial and surrounding tissues, giving clinicians a more precise means of visually inspecting subjects. Furthermore, applying the transformation to segmented cine data to produce pseudo-real-time images allows this label information to be transferred to the real-time image domain. We demonstrate the feasibility of this approach by training a U-net based architecture using these pseudo-real-time images which can effectively segment actual real-time images.

Estimating dimensional measurements of the left ventricle provides diagnostic values which can be used to assess cardiac health and identify certain pathologies. In this paper we describe our methodology of calculating measurements from left ventricle segmentations automatically generated using deep learning. We use a U-net convolutional neural network architecture built from residual units to segment the left ventricle and then process these segmentations to estimate the area of the cavity and myocardium, the dimensions of the cavity, and the thickness of the myocardium. Determining if an image is part of the diastolic or systolic portion of the cardiac cycle is done by analysing the cavity volume. The quality of our results are dependent on our training regime where we have generated a large derivative dataset by augmenting the original images with free-form deformations. Our expanded training set, in conjunction with simple affine image transforms, creates a sufficiently large training population to prevent over-fitting of the network while still creating an accurate and robust segmentation network. Assessing our method on the STACOM18 LVQuan challenge dataset we find that it significantly outperforms the previously published state-of-the-art on a 5-fold validation all tasks considered.

[\({}^{18}\)F]fluorodeoxyglucose (FDG) positron emission tomography (PET) aids in the localisation of the epileptogenic zone in patients with focal epilepsy, especially when magnetic resonance imaging (MRI) is normal or non-contributory. We propose a two-stage deep learning framework to support the clinical evaluation of patients with focal epilepsy by identifying candidate regions of hypometabolism in [18F]FDG PET scans. In the first stage, we train a generative adversarial network (GAN) to learn the mapping between healthy [18F]FDG PET and T1-weighted (T1w) MRI data. In the second stage, we synthesise pseudo-normal PET images from T1w MRI scans of patients with epilepsy to compare to the real PET scans. Comparing the estimated pseudo-PET images to the true PET scans in healthy control data, our GAN produced whole-brain mean absolute errors of \(0.053 \pm 0.015\), outperforming a U-Net (\(0.058 \pm 0.021\)) and a high-resolution dilated convolutional neural network (\(0.060 \pm 0.024\); all images scaled 0–1). In a sample of 20 epilepsy patients, we created Z-statistic images (with thresholding at +2.33) by subtracting the patient’s true PET scans from their estimated pseudo-normal PET images to identify regions of hypometabolism. Excellent sensitivity for lobar location of abnormalities (\(92.9 \pm 13.1\%\)) was observed for the seven cases with MR-visible epileptogenic lesions. For the 13 cases with non-contributory MR, a lower sensitivity of \(74.8 \pm 32.3\%\) was observed. Our method performed better than a statistical parametric mapping analysis. Our results highlight the potential of deep learning-based pseudo-normal [18F]FDG PET synthesis to contribute to the management of epilepsy.

Cardiac Resynchronization Therapy (CRT) is associated with increased arrhythmogenic risk in infarct patients when pacing adjacent to a scar. We investigated the role of pacing location relative to scar on dispersion of repolarization, as a surrogate for arrhythmogenic risk. For this task, we developed a personalization and simulation pipeline that allows fast development of personalized computational models and simulation of cardiac electrophysiology. Twenty four models of left ventricular anatomy and scar morphology were built and repolarization sequences were simulated. Simulation results show that CRT increases dispersion of repolarization around a scar when pacing adjacent to it, thus, providing a mechanistic explanation of increased arrhythmogenic risk in infarct patients undergoing CRT.

INTRODUCTION: Atrial fibrillation (AF) is a widespread cardiac arrhythmia that commonly affects the left atrium (LA), causing it toquiver instead of contracting effectively. This behavior is triggered by abnormal electrical impulses at a specific site in the atrial wall. Catheter ablation (CA) treatment consists of isolating this driver site by burning the surrounding tissue to restore sinus rhythm (SR). However, evidence suggests that CA can concur to the formation of blood clots by promoting coagulation near the heat source and in regions with low flow velocity and blood stagnation.METHODS: A patient-specific modelling workflow was created and applied to simulate thermal-fluid dynamics in two patients pre- and post-CA. Each model was personalised based on pre- and post-CA imaging datasets. The wall motion and anatomy were derived from SSFP Cine MRI data, while the trans-valvular flow was based on Doppler ultrasound data. The temperature distribution in the blood was modelled using a modified Pennes bioheat equation implemented in a finite-element based Navier-Stokes solver. Blood particles were also classified based on their residence time in the LA using a particle-tracking algorithm.RESULTS: SR simulations showed multiple short-lived vortices with an average blood velocity of 0.2-0.22 m/s. In contrast, AF patients presented a slower vortex and stagnant flow in the LA appendage, with the average blood velocity reduced to 0.08-0.14 m/s. Restoration of SR also increased the blood kinetic energy and the viscous dissipation due to the presence of multiple vortices. Particle tracking showed a dramatic decrease in the percentage of blood remaining in the LA for longer than one cycle after CA (65.9% vs 43.3% in patient A and 62.2% vs 54.8% in patient B). Maximum temperatures of 76 C and 58 C were observed when CA was performed near the appendage and in a pulmonary vein, respectively.CONCLUSION: This computational study presents novel models to elucidate relations between catheter temperature, patient-specific atrial anatomy and blood velocity, and predict how they change from SR to AF. The models can quantify blood flow in critical regions, including residence times and temperature distribution for different catheter positions, providing a basis for quantifying stroke risks.