Impact of the COVID-19 pandemic on patients with hepatocellular carcinoma in the West of Scotland: a cohort study.

OBJECTIVE: The COVID-19 pandemic had an undoubted impact on the provision of elective and emergency cancer care, including the diagnosis and management of patients with hepatocellular carcinoma (HCC). Our aim was to determine the effects of the COVID-19 pandemic on patients with HCC in the West of Scotland. DESIGN: This was a retrospective audit of a prospectively collated database of patients presented to the West of Scotland Multidisciplinary Team (MDT) between April and October 2020 (during the pandemic), comparing baseline demographics, characteristics of disease at presentation, diagnostic workup, treatment and outcomes with patients from April to October 2019 (pre pandemic). RESULTS: There was a 36.5% reduction in new cases referred to the MDT during the pandemic. Patients presented at a significantly later Barcelona Cancer Liver Clinic stage (24% stage D during the pandemic, 9.5% pre pandemic, p<0.001) and with a significantly higher Child-Pugh Score (46% Child-Pugh B/C during the pandemic vs 27% pre pandemic, p<0.001). We observed a reduction in overall survival (OS) among all patients with a median OS during the pandemic of 6 months versus 17 months pre pandemic (p=0.048). CONCLUSION: The impact of the COVID-19 pandemic is likely to have contributed to a reduction in the presentation of new cases and survival among patients with HCC in the West of Scotland. The reason for this is likely multifactorial, but disruption of standard care is likely to have played a significant role. Resources should be provided to address the backlog and ensure there are robust investigation and management pathways going forward.

An Artificial Neural Network for Nasogastric Tube Position Decision Support.

Purpose: To develop and validate a deep learning model for detection of nasogastric tube (NGT) malposition on chest radiographs and assess model impact as a clinical decision support tool for junior physicians to help determine whether feeding can be safely performed in patients (feed/do not feed). Materials and Methods: A neural network ensemble was pretrained on 1 132 142 retrospectively collected (June 2007-August 2019) frontal chest radiographs and further fine-tuned on 7081 chest radiographs labeled by three radiologists. Clinical relevance was assessed on an independent set of 335 images. Five junior emergency medicine physicians assessed chest radiographs and made feed/do not feed decisions without and with artificial intelligence (AI)-generated NGT malposition probabilities placed above chest radiographs. Decisions from the radiologists served as ground truths. Model performance was evaluated using receiver operating characteristic analysis. Agreement between junior physician and radiologist decision was determined using the Cohen κ coefficient. Results: In the testing set, the ensemble achieved area under the receiver operating characteristic curve values of 0.82 (95% CI: 0.78, 0.86), 0.77 (95% CI: 0.71, 0.83), and 0.98 (95% CI: 0.96, 1.00) for satisfactory, malpositioned, and bronchial positions, respectively. In the clinical evaluation set, mean interreader agreement for feed/do not feed decisions among junior physicians was 0.65 ± 0.03 (SD) and 0.77 ± 0.13 without and with AI support, respectively. Mean agreement between junior physicians and radiologists was 0.53 ± 0.05 (unaided) and 0.65 ± 0.09 (AI-aided). Conclusion: A simple classifier for NGT malposition may help junior physicians determine the safety of feeding in patients with NGTs.Keywords: Neural Networks, Feature Detection, Supervised Learning, Machine Learning Supplemental material is available for this article. Published under a CC BY 4.0 license.

Development and prospective validation of COVID-19 chest X-ray screening model for patients attending emergency departments.

Chest X-rays (CXRs) are the first-line investigation in patients presenting to emergency departments (EDs) with dyspnoea and are a valuable adjunct to clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to facilitate rapid triage of CXRs for further patient testing and/or isolation. In this work we develop an AI algorithm, CovIx, to differentiate normal, abnormal, non-COVID-19 pneumonia, and COVID-19 CXRs using a multicentre cohort of 293,143 CXRs. The algorithm is prospectively validated in 3289 CXRs acquired from patients presenting to ED with symptoms of COVID-19 across four sites in NHS Greater Glasgow and Clyde. CovIx achieves area under receiver operating characteristic curve for COVID-19 of 0.86, with sensitivity and F1-score up to 0.83 and 0.71 respectively, and performs on-par with four board-certified radiologists. AI-based algorithms can identify CXRs with COVID-19 associated pneumonia, as well as distinguish non-COVID pneumonias in symptomatic patients presenting to ED. Pre-trained models and inference scripts are freely available at https://github.com/beringresearch/bravecx-covid .

Feasibility of a quality improvement project to increase adherence to evidence-based pulmonary embolism diagnosis in the emergency department.

BACKGROUND: Many evidence-based clinical decision tools are available for the diagnosis of pulmonary embolism (PE). However, these clinical decision tools have had suboptimal uptake in the everyday clinical practice in emergency departments (EDs), despite numerous implementation efforts. We aimed to test the feasibility of a multi-faceted intervention to implement an evidence-based PE diagnosis protocol. METHODS: We conducted an interrupted time series study in three EDs in Ontario, Canada. We enrolled consecutive adult patients accessing the ED with suspected PE from January 1, 2018, to February 28, 2020. Components of the intervention were as follows: clinical leadership endorsement, a new pathway for PE testing, physician education, personalized confidential physician feedback, and collection of patient outcome information. The intervention was implemented in November 2019. We identified six criteria for defining the feasibility outcome: successful implementation of the intervention in at least two of the three sites, capturing data on ≥ 80% of all CTPAs ordered in the EDs, timely access to electronic data, rapid manual data extraction with feedback preparation before the end of the month ≥ 80% of the time, and time required for manual data extraction and feedback preparation ≤ 2 days per week in total. RESULTS: The intervention was successfully implemented in two out of three sites. A total of 5094 and 899 patients were tested for PE in the period before and after the intervention, respectively. We captured data from 90% of CTPAs ordered in the EDs, and we accessed the required electronic data. The manual data extraction and individual emergency physician audit and feedback were consistently finalized before the end of each month. The time required for manual data extraction and feedback preparation was ≤ 2 days per week (14 h). CONCLUSIONS: We proved the feasibility of implementing an evidence-based PE diagnosis protocol in two EDs. We were not successful implementing the protocol in the third ED. REGISTRATION: The study was not registered.

Diagnostic Accuracy of Single-Phase Computed Tomography Texture Analysis for Prediction of LI-RADS v2018 Category.

OBJECTIVE: The aim of this study was to determine if texture analysis can classify liver observations likely to be hepatocellular carcinoma based on the Liver Imaging Reporting and Data System (LI-RADS) using single portal venous phase computed tomography. METHODS: This research ethics board-approved retrospective cohort study included 64 consecutive LI-RADS observations. Individual observation texture analysis features were compared using Kruskal-Wallis and 2 sample t tests. Logistic regression was used for prediction of LI-RADS group. Diagnostic accuracy was assessed using receiver operating characteristic curves and Youden method. RESULTS: Multiple texture features were associated with LI-RADS including the mean HU (P = 0.003), median (P = 0.002), minimum (P = 0.010), maximum (P = 0.013), standard deviation (P = 0.009), skewness (P = 0.007), and entropy (P < 0.001). On logistic regression, LI-RADS group could be predicted with area under the curve, sensitivity, and specificity of 0.98, 96%, and 100%, respectively. CONCLUSIONS: Texture analysis features on portal venous phase computed tomography can identify liver observations likely to be hepatocellular carcinoma, which may preclude the need to recall some patients for additional multiphase imaging.

Hypovascular pancreas head adenocarcinoma: CT texture analysis for assessment of resection margin status and high-risk features.

OBJECTIVES: To determine if CT texture analysis features are associated with hypovascular pancreas head adenocarcinoma (PHA) postoperative margin status, nodal status, grade, lymphovascular invasion (LVI), and perineural invasion (PNI). METHODS: This Research Ethics Board-approved retrospective cohort study included 131 consecutive patients with resected PHA. Tumors were segmented on preoperative contrast-enhanced CT. Tumor diameter and texture analysis features including mean, minimum and maximum Hounsfield units, standard deviation, skewness, kurtosis, and entropy and gray-level co-occurrence matrix (GLCM) features correlation and dissimilarity were extracted. Two-sample t test and logistic regression were used to compare parameters for prediction of margin status, nodal status, grade, LVI, and PNI. Diagnostic accuracy was assessed using receiver operating characteristic curves and Youden method was used to establish cutpoints. RESULTS: Margin status was associated with GLCM correlation (p = 0.012) and dissimilarity (p = 0.003); nodal status was associated with standard deviation (p = 0.026) and entropy (p = 0.031); grade was associated with kurtosis (p = 0.031); LVI was associated with standard deviation (p = 0.047), entropy (p = 0.026), and GLCM correlation (p = 0.033) and dissimilarity (p = 0.011). No associations were found for PNI (p > 0.05). Logistic regression yielded an area under the curve of 0.70 for nodal disease, 0.70 for LVI, 0.68 for grade, and 0.65 for margin status. Optimal sensitivity/specificity was as follows: nodal disease 73%/72%, LVI 72%/65%, grade 55%/83%, and margin status 63%/66%. CONCLUSIONS: CT texture analysis features demonstrate fair diagnostic accuracy for assessment of hypovascular PHA nodal disease, LVI, grade, and postoperative margin status. Additional research is rapidly needed to identify these high-risk features with better accuracy. KEY POINTS: • CT texture analysis features are associated with pancreas head adenocarcinoma postoperative margin status which may help inform treatment decisions as a negative resection margin is required for cure. • CT texture analysis features are associated with pancreas head adenocarcinoma nodal disease, a poor prognostic feature. • Indicators of more aggressive pancreas head adenocarcinoma biology including tumor grade and LVI can be diagnosed using CT texture analysis with fair accuracy.

Pseudoembryo associated with pseudogestational sac: A novel sonographic finding in ectopic pregnancy.

In this case report, we present a case of a hitherto undescribed "pseudoembryo" appearance in a fluid-filled endometrial cavity in ectopic pregnancy. Knowledge of this sonographic finding is clinically important, since the presence of a "pseudoembryo" could lead to the misidentification of a pseudogestational sac as an intrauterine pregnancy in the setting of ectopic pregnancy. This paper discuss reviews the pseudogestational sac and imaging findings which differentiate it from a true intrauterine gestation.

The role of elastography in evaluating thyroid nodules: a literature review and meta-analysis.

To appraise the literature for studies involving the use of elastography to diagnose thyroid nodule pathology. Two independent reviewers performed a systematic review of the English medical literature for studies involving elastography diagnosing thyroid nodule pathology. Data gleaned from this process was used in a meta-analysis to summarise the results. Thirty-eight studies were used in the meta-analysis totalling 5,942 thyroid nodules examined with elastography. The pooled results were sensitivity = 87.0 % (95 % confidence intervals (CI) = 86.2-87.9 %), specificity = 80.6 % (CI = 79.5-81.6 %), positive predictive value (PPV) = 48.9 % (CI = 47.6-50.2 %), negative predictive value (NPV) = 96.7 % (CI = 96.2-97.1 %), diagnostic accuracy = 81.7 % (CI = 80.7-82.7 %). Subgroup analysis of the data is also presented. Elastography has its limitations in the diagnosis of thyroid nodules; however, its high NPV is increasingly being used as an important investigation and may allow a reduction in the number of hemi-thyroidectomies with benign pathology. Subgroup analysis suggests that elastography techniques where compressive force is performed in a non-user-dependant method results in improved final results.

An analysis of intraoperative versus post-operative dosimetry with CT, CT-MRI fusion and XMR for the evaluation of permanent prostate brachytherapy implants.

BACKGROUND AND PURPOSE: To assess the agreement between intraoperative and post-operative dosimetry and to identify factors that influence dose calculations of prostate brachytherapy implants. MATERIALS AND METHODS: Patients treated with prostate brachytherapy implants underwent post-operative CT and XMR (combined X-ray and MR) imaging. Dose-volume histograms were calculated from CT, XMR and CT-MR fusion data and compared with intraoperative values for two observers. Multiple linear regression models assessed the influences of intraoperative D90, gland oedema, gland volume, source loss and migration, and implanted activity/volume prostate on post-operative D90. RESULTS: Forty-nine patients were studied. The mean D90 differences (95% confidence limits) between intraoperative and post-operative CT, XMR and CT-MR fusion assessments were: 11 Gy (-22, 45), 18 Gy (-13, 49) and 20 Gy (-17, 58) for Observer 1; and 15 Gy (-34, 63), 13 Gy (-29, 55) and 14 Gy (-27, 54) for Observer 2. Multiple linear regression modelling showed that the observed oedema and intraoperative D90 were significant independent variables for the prediction of post-operative D90 values for both observers using all modalities. CONCLUSION: This is the first study to report Bland-Altman agreement analysis between intraoperative and post-operative dosimetry. Agreement is poor. Post-operative dosimetry is dependent on the intraoperative D90 and the subjectively outlined gland volume.