A Novel and Automated Approach to Classify Radiation Induced Lung Tissue Damage on CT Scans

Radiation-induced lung damage (RILD) is a common side effect of radiotherapy (RT). The ability to automatically segment, classify, and quantify different types of lung parenchymal change is essential to uncover underlying patterns of RILD and their evolution over time. A RILD dedicated tissue classification system was developed to describe lung parenchymal tissue changes on a voxel-wise level. The classification system was automated for segmentation of five lung tissue classes on computed tomography (CT) scans that described incrementally increasing tissue density, ranging from normal lung (Class 1) to consolidation (Class 5). For ground truth data generation, we employed a two-stage data annotation approach, akin to active learning. Manual segmentation was used to train a stage one auto-segmentation method. These results were manually refined and used to train the stage two auto-segmentation algorithm. The stage two auto-segmentation algorithm was an ensemble of six 2D Unets using different loss functions and numbers of input channels. The development dataset used in this study consisted of 40 cases, each with a pre-radiotherapy, 3-, 6-, 12-, and 24-month follow-up CT scans (n = 200 CT scans). The method was assessed on a hold-out test dataset of 6 cases (n = 30 CT scans). The global Dice score coefficients (DSC) achieved for each tissue class were: Class (1) 99% and 98%, Class (2) 71% and 44%, Class (3) 56% and 26%, Class (4) 79% and 47%, and Class (5) 96% and 92%, for development and test subsets, respectively. The lowest values for the test subsets were caused by imaging artefacts or reflected subgroups that occurred infrequently and with smaller overall parenchymal volumes. We performed qualitative evaluation on the test dataset presenting manual and auto-segmentation to a blinded independent radiologist to rate them as 'acceptable', 'minor disagreement' or 'major disagreement'. The auto-segmentation ratings were similar to the manual segmentation, both having approximately 90% of cases rated as acceptable. The proposed framework for auto-segmentation of different lung tissue classes produces acceptable results in the majority of cases and has the potential to facilitate future large studies of RILD.

Radiology of Bronchiectasis

Bronchiectasis is a radiological diagnosis made using computed tomographic (CT) imaging. Although visual CT assessment is necessary for the diagnosis of bronchiectasis, visual assessment of disease severity and progression is challenging. Computer tools offer the potential to improve the characterization of lung damage in patients with bronchiectasis. Newer imaging techniques such as MRI with hyperpolarized gas inhalation have the potential to identify early forms of disease and are without the constraints of requiring ionizing radiation exposure.

234 Outcomes of Periprosthetic Femoral Fractures Between 2011–2021: An Observational Study

Background

Periprosthetic femoral fractures (PPFF) present a significant burden on the health services due to an increase in the ageing population and the number of hip and knee arthroplasties performed. This study observed how this burden changed between 2011 and 2021 and the outcomes for these patients undergoing an operation.

Method

Ten-year retrospective observational study assessing the variance depending on the fracture/operation, ASA scores, time to operation, length of stay and mortality.

Results

From January 2011 to March 2021, we identified 209 operations for femur periprosthetic fractures. The mean age was 83 with a female preponderance of 76%. There was a significant change in the ASA scores of the patients, with the proportion of ASA 3 or more increasing from 43% (2011–2016) to 73% (2017–2021), and ASA 4 or greater increasing from 10% to 17% respectively. There were 68 periprosthetic hip arthroplasty fracture fixations, 81 periprosthetic hip arthroplasty fracture revisions, 45 periprosthetic total knee replacements, and 15 inter-prosthetic fractures. One year mortality rates were 24.6%, 6.7%, 16.3% and 13.3% respectively. The average times to operation were 2.5 days, 4.5 days, 2.1 days, and 1.7 days respectively. The average lengths of stay were 20.8 days, 19.8 days, 12.1 days, and 13.1 days respectively.

Conclusions

PPFF carry a significant mortality risk and ASA scores have increased. Mortality rates were better in the periprosthetic hip arthroplasty patients who had revisions rather than fixations (representing different cohort). one year mortality figures were comparable to similar studies in Ireland and USA.

199 The Influence of Pre-Operative Factors on Patient Length of Stay After Total Knee Replacement

Aim

This study aims to assess the impact of pre-operative factors on the length of stay in patients following total knee replacement at our institution.

Method

A total of 478 patients following total knee replacement between January 2017-Decemeber 2019 are included in this study. All patients underwent total knee replacement with a medial rotating total knee prosthesis (MRK; Matt Ortho UK).

Data for each patient was collated retrospectively and included the following: Patient demographics (age and sex), American Society of Anaesthesiology (ASA) score, pre-operative range of movement (ROM), Body Mass Index (BMI), and pre-operative haemoglobin. Each factor was then compared with the length of stay for all 478 patients. Statistical significance was sort for each pre-operative factor for both men and women.

Results

Our cohort of patients includes 291 females and 187 males. Patients ranged from 39 to 90 years with an average age of 68. The average BMI of the cohort was 31.3(18.6–56.56) and the average ASA grade was 2.

Preoperative hemoglobin and the Age of the patient at the time of surgery were the only two factors which had a statistically significant impact on the length of hospital stay (p<0.05). BMI, Pre- operative range of motion and ASA scores had no statistically significant effect on the length of hospital stay in our cohort.

Conclusions

Low pre-operative hemoglobin and increasing age have significant effects on length of stay after total knee replacement. The BMI, pre-operative range of movement and ASA scores do not influence the length of hospital stay.

Quantitative Analysis of Radiation-Associated Parenchymal Lung Change

We present a novel classification system of the parenchymal features of radiation-induced lung damage (RILD). We developed a deep learning network to automate the delineation of five classes of parenchymal textures. We quantify the volumetric change in classes after radiotherapy in order to allow detailed, quantitative descriptions of the evolution of lung parenchyma up to 24 months after RT, and correlate these with radiotherapy dose and respiratory outcomes. Diagnostic CTs were available pre-RT, and at 3, 6, 12 and 24 months post-RT, for 46 subjects enrolled in a clinical trial of chemoradiotherapy for non-small cell lung cancer. All 230 CT scans were segmented using our network. The five parenchymal classes showed distinct temporal patterns. Moderate correlation was seen between change in tissue class volume and clinical and dosimetric parameters, e.g., the Pearson correlation coefficient was ≤0.49 between V30 and change in Class 2, and was 0.39 between change in Class 1 and decline in FVC. The effect of the local dose on tissue class revealed a strong dose-dependent relationship. Respiratory function measured by spirometry and MRC dyspnoea scores after radiotherapy correlated with the measured radiological RILD. We demonstrate the potential of using our approach to analyse and understand the morphological and functional evolution of RILD in greater detail than previously possible.

Healthcare Understanding of COVID-19 Antibody

Objective

: The SARS-CoV-2 pandemic has shed light on the difficulties in spreading uniform information. We rely on national and international organizations to provide scientifically accurate information to the public at large. With so many different sources of information, often not scientific, there appears to be an incomplete understanding of many aspects of SARS-CoV-2 infection. We sought to gain information about healthcare worker understanding of the implications of a positive serum COVID-19 antibody test result. We identified a broad range of responses among all categories of healthcare workers in our facility. Most notably we found that there was not complete understanding that there can be asymptomatic spread of COVID-19 infection.

Methods

: We provided health literacy and opinion questions to the healthcare workers of our facility.

Results

: Upon analysis of the data, we identified many differences in level of understanding among our healthcare workers.

Conclusion

: We identified a lack of consensus on important details leading to potentially growing uncertainty with respect to SARS-COV-2 antibody. A diminished health literacy with respect to antibody testing could potentially suggest future issues with understanding the importance of vaccination benefits.

Unravelling the effects of treated wastewater discharges on the water quality in a coastal lagoon system (Ria Formosa, South Portugal): Relevance of hydrodynamic conditions

This study aimed to assess the influence of treated wastewater disposal on Ria Formosa coastal lagoon (South Portugal), the largest national producer of bivalve mollusks. Water quality was evaluated at two areas under different wastewater loads and hydrodynamic conditions, using physico-chemical variables, bacterial indicators of contamination, chlorophyll-a concentration, phytoplankton abundance and composition. Samples were collected monthly, between October 2018 and September 2019. Minor influence of effluent discharge was detected at the eastern Olhão area, exposed to stronger hydrodynamics and higher wastewater load than the northwestern Faro area (ca. 2-4-fold total nitrogen and phosphorus). The lower load weakly flushed area showed a poorer water quality, up to 500 m from the discharge point, more marked during the spring-summer period. The intensity, persistence, and spatial extent of the wastewater footprint, lower for the highest-loading area, reflected the role of local hydrodynamic conditions, modulating the influence of wastewater discharge on lagoonal water quality.

Deep Learning-Based Long Term Mortality Prediction in the National Lung Screening Trial

In this study, the long-term mortality in the National Lung Screening Trial (NLST) was investigated using a deep learning-based method. Binary classification of the non-lung-cancer mortality (i.e. cardiovascular and respiratory mortality) was performed using neural network models centered around a 3D-ResNet. The models were trained on a participant age, gender, and smoking history matched cohort. Utilising both the 3D CT scan and clinical information, the models can achieve an AUC of 0.73 which outperforms humans at cardiovascular mortality prediction. The corresponding F1 and Matthews Correlation Coefficient are 0.60 and 0.38 respectively. By interpreting the trained models with 3D saliency maps, we examined the features on the CT scans that correspond to the mortality signal. By extracting information from 3D CT volumes, we can highlight regions in the thorax region that contribute to mortality that might be overlooked by the clinicians. Therefore, this can help focus preventative interventions appropriately, particularly for under-recognised pathologies and thereby reducing patient morbidity.

Towards nationally curated data archives for clinical radiology image analysis at scale: Learnings from national data collection in response to a pandemic

The prevalence of the coronavirus SARS-CoV-2 disease has resulted in the unprecedented collection of health data to support research. Historically, coordinating the collation of such datasets on a national scale has been challenging to execute for several reasons, including issues with data privacy, the lack of data reporting standards, interoperable technologies, and distribution methods. The coronavirus SARS-CoV-2 disease pandemic has highlighted the importance of collaboration between government bodies, healthcare institutions, academic researchers and commercial companies in overcoming these issues during times of urgency. The National COVID-19 Chest Imaging Database, led by NHSX, British Society of Thoracic Imaging, Royal Surrey NHS Foundation Trust and Faculty, is an example of such a national initiative. Here, we summarise the experiences and challenges of setting up the National COVID-19 Chest Imaging Database, and the implications for future ambitions of national data curation in medical imaging to advance the safe adoption of artificial intelligence in healthcare.

Increased severity in SARS-CoV-2 infection of minorities in Spain

Introduction

With the global spread of COVID-19, studies in the US and UK have shown that certain communities have been strongly impacted by COVID-19 in terms of incidence and mortality. The objective of the study was to determine social determinants of health among COVID-19 patients hospitalized in the two major cities of Spain.

Material and methods

A multicenter retrospective case series study was performed collecting administrative databases of all COVID-19 patients ≥18 years belonging to two centers in Madrid and two in Barcelona (Spain) collecting data from 1^st March to 15th April 2020. Variables obtained age, gender, birthplace and residence ZIP code. From ZIP code we obtained per capita income of the area. Predictors of the outcomes were explored through generalized linear mixed-effects models, using center as random effect.

Results

There were 5,235 patients included in the analysis. After multivariable analysis adjusted by age, sex, per capita income, population density, hospital experience, center and hospital saturation, patients born in Latin American countries were found to have an increase in ICU admission rates (OR 1.56 [1.13-2.15], p<0.01) but no differences were found in the same model regarding mortality (OR 1.35 [0.95-1.92], p=0.09).

Conclusions

COVID-19 severity varies widely, not only depending on biological but also socio-economic factors. With the emerging evidence that this subset of population is at higher risk of poorer outcomes, targeted public health strategies and studies are needed.

Imaging intact human organs with local resolution of cellular structures using hierarchical phase-contrast tomography

Imaging intact human organs from the organ to the cellular scale in three dimensions is a goal of biomedical imaging. To meet this challenge, we developed hierarchical phase-contrast tomography (HiP-CT), an X-ray phase propagation technique using the European Synchrotron Radiation Facility (ESRF)'s Extremely Brilliant Source (EBS). The spatial coherence of the ESRF-EBS combined with our beamline equipment, sample preparation and scanning developments enabled us to perform non-destructive, three-dimensional (3D) scans with hierarchically increasing resolution at any location in whole human organs. We applied HiP-CT to image five intact human organ types: brain, lung, heart, kidney and spleen. HiP-CT provided a structural overview of each whole organ followed by multiple higher-resolution volumes of interest, capturing organotypic functional units and certain individual specialized cells within intact human organs. We demonstrate the potential applications of HiP-CT through quantification and morphometry of glomeruli in an intact human kidney and identification of regional changes in the tissue architecture in a lung from a deceased donor with coronavirus disease 2019 (COVID-19).

An overview of the National COVID-19 Chest Imaging Database: data quality and cohort analysis

BACKGROUND

The National COVID-19 Chest Imaging Database (NCCID) is a centralized database containing mainly chest X-rays and computed tomography scans from patients across the UK. The objective of the initiative is to support a better understanding of the coronavirus SARS-CoV-2 disease (COVID-19) and the development of machine learning technologies that will improve care for patients hospitalized with a severe COVID-19 infection. This article introduces the training dataset, including a snapshot analysis covering the completeness of clinical data, and availability of image data for the various use-cases (diagnosis, prognosis, longitudinal risk). An additional cohort analysis measures how well the NCCID represents the wider COVID-19-affected UK population in terms of geographic, demographic, and temporal coverage.

FINDINGS

The NCCID offers high-quality DICOM images acquired across a variety of imaging machinery; multiple time points including historical images are available for a subset of patients. This volume and variety make the database well suited to development of diagnostic/prognostic models for COVID-associated respiratory conditions. Historical images and clinical data may aid long-term risk stratification, particularly as availability of comorbidity data increases through linkage to other resources. The cohort analysis revealed good alignment to general UK COVID-19 statistics for some categories, e.g., sex, whilst identifying areas for improvements to data collection methods, particularly geographic coverage.

CONCLUSION

The NCCID is a growing resource that provides researchers with a large, high-quality database that can be leveraged both to support the response to the COVID-19 pandemic and as a test bed for building clinically viable medical imaging models.

Physical, cognitive, and mental health impacts of COVID-19 after hospitalisation (PHOSP-COVID): a UK multicentre, prospective cohort study

BACKGROUND

The impact of COVID-19 on physical and mental health and employment after hospitalisation with acute disease is not well understood. The aim of this study was to determine the effects of COVID-19-related hospitalisation on health and employment, to identify factors associated with recovery, and to describe recovery phenotypes.

METHODS

The Post-hospitalisation COVID-19 study (PHOSP-COVID) is a multicentre, long-term follow-up study of adults (aged ≥18 years) discharged from hospital in the UK with a clinical diagnosis of COVID-19, involving an assessment between 2 and 7 months after discharge, including detailed recording of symptoms, and physiological and biochemical testing. Multivariable logistic regression was done for the primary outcome of patient-perceived recovery, with age, sex, ethnicity, body-mass index, comorbidities, and severity of acute illness as covariates. A post-hoc cluster analysis of outcomes for breathlessness, fatigue, mental health, cognitive impairment, and physical performance was done using the clustering large applications k-medoids approach. The study is registered on the ISRCTN Registry (ISRCTN10980107).

FINDINGS

We report findings for 1077 patients discharged from hospital between March 5 and Nov 30, 2020, who underwent assessment at a median of 5·9 months (IQR 4·9-6·5) after discharge. Participants had a mean age of 58 years (SD 13); 384 (36%) were female, 710 (69%) were of white ethnicity, 288 (27%) had received mechanical ventilation, and 540 (50%) had at least two comorbidities. At follow-up, only 239 (29%) of 830 participants felt fully recovered, 158 (20%) of 806 had a new disability (assessed by the Washington Group Short Set on Functioning), and 124 (19%) of 641 experienced a health-related change in occupation. Factors associated with not recovering were female sex, middle age (40-59 years), two or more comorbidities, and more severe acute illness. The magnitude of the persistent health burden was substantial but only weakly associated with the severity of acute illness. Four clusters were identified with different severities of mental and physical health impairment (n=767): very severe (131 patients, 17%), severe (159, 21%), moderate along with cognitive impairment (127, 17%), and mild (350, 46%). Of the outcomes used in the cluster analysis, all were closely related except for cognitive impairment. Three (3%) of 113 patients in the very severe cluster, nine (7%) of 129 in the severe cluster, 36 (36%) of 99 in the moderate cluster, and 114 (43%) of 267 in the mild cluster reported feeling fully recovered. Persistently elevated serum C-reactive protein was positively associated with cluster severity.

INTERPRETATION

We identified factors related to not recovering after hospital admission with COVID-19 at 6 months after discharge (eg, female sex, middle age, two or more comorbidities, and more acute severe illness), and four different recovery phenotypes. The severity of physical and mental health impairments were closely related, whereas cognitive health impairments were independent. In clinical care, a proactive approach is needed across the acute severity spectrum, with interdisciplinary working, wide access to COVID-19 holistic clinical services, and the potential to stratify care.

FUNDING

UK Research and Innovation and National Institute for Health Research.

Remote Assessment of Lung Disease and Impact on Physical and Mental Health (RALPMH): Protocol for a Prospective Observational Study

BACKGROUND

Chronic lung disorders like chronic obstructive pulmonary disease (COPD) and idiopathic pulmonary fibrosis (IPF) are characterized by exacerbations. They are unpleasant for patients and sometimes severe enough to cause hospital admission and death. Moreover, due to the COVID-19 pandemic, vulnerable populations with these disorders are at high risk, and their routine care cannot be done properly. Remote monitoring offers a low cost and safe solution for gaining visibility into the health of people in their daily lives, making it useful for vulnerable populations.

OBJECTIVE

The primary objective is to assess the feasibility and acceptability of remote monitoring using wearables and mobile phones in patients with pulmonary diseases. The secondary objective is to provide power calculations for future studies centered around understanding the number of exacerbations according to sample size and duration.

METHODS

Twenty participants will be recruited in each of three cohorts (COPD, IPF, and posthospitalization COVID). Data collection will be done remotely using the RADAR-Base (Remote Assessment of Disease And Relapse) mobile health (mHealth) platform for different devices, including Garmin wearable devices and smart spirometers, mobile app questionnaires, surveys, and finger pulse oximeters. Passive data include wearable-derived continuous heart rate, oxygen saturation, respiration rate, activity, and sleep. Active data include disease-specific patient-reported outcome measures, mental health questionnaires, and symptom tracking to track disease trajectory. Analyses will assess the feasibility of lung disorder remote monitoring (including data quality, data completeness, system usability, and system acceptability). We will attempt to explore disease trajectory, patient stratification, and identification of acute clinical events such as exacerbations. A key aspect is understanding the potential of real-time data collection. We will simulate an intervention to acquire responses at the time of the event to assess model performance for exacerbation identification.

RESULTS

The Remote Assessment of Lung Disease and Impact on Physical and Mental Health (RALPMH) study provides a unique opportunity to assess the use of remote monitoring in the evaluation of lung disorders. The study started in the middle of June 2021. The data collection apparatus, questionnaires, and wearable integrations were setup and tested by the clinical teams prior to the start of recruitment. While recruitment is ongoing, real-time exacerbation identification models are currently being constructed. The models will be pretrained daily on data of previous days, but the inference will be run in real time.

CONCLUSIONS

The RALPMH study will provide a reference infrastructure for remote monitoring of lung diseases. It specifically involves information regarding the feasibility and acceptability of remote monitoring and the potential of real-time data collection and analysis in the context of chronic lung disorders. It will help plan and inform decisions in future studies in the area of respiratory health.

TRIAL REGISTRATION

ISRCTN Registry ISRCTN16275601; https://www.isrctn.com/ISRCTN16275601.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/28873.

ROSE: radiology, obstruction, symptoms and exposure - a Delphi consensus definition of the association of COPD and bronchiectasis by the EMBARC Airways Working Group

INTRODUCTION

The coexistence of COPD and bronchiectasis seems to be common and associated with a worse prognosis than for either disease individually. However, no definition of this association exists to guide researchers and clinicians.

METHODS

We conducted a Delphi survey involving expert pulmonologists and radiologists from Europe, Turkey and Israel in order to define the "COPD- [bronchiectasis] BE association".A panel of 16 experts from EMBARC selected 35 statements for the survey after reviewing scientific literature. Invited participants, selected on the basis of expertise, geographical and sex distribution, were asked to express agreement on the statements. Consensus was defined as a score of ≥6 points (scale 0 to 9) in ≥70% of answers across two scoring rounds.

RESULTS

102 (72.3%) out of 141 invited experts participated in the first round. Their response rate in the second round was 81%. The final consensus definition of "COPD-BE association" was: "The coexistence of (1) specific radiological findings (abnormal bronchial dilatation, airways visible within 1 cm of pleura and/or lack of tapering sign in ≥1 pulmonary segment and in >1 lobe) with (2) an obstructive pattern on spirometry ([forced expiratory volume in 1 s] FEV1/[forced vital capacity] FVC <0.7), (3) at least two characteristic symptoms (cough, expectoration, dyspnoea, fatigue, frequent infections) and (4) current or past exposure to smoke (≥10 pack-years) or other toxic agents (biomass, etc.)". These criteria form the acronym "ROSE" (Radiology, Obstruction, Symptoms, Exposure).

CONCLUSIONS

The Delphi process formulated a European consensus definition of "COPD-BE association". We hope this definition will have broad applicability across clinical practice and research in the future.