CT Scanning in Suspected Stroke or Head Trauma: Is it Worth Going the Extra Mile and Including the Chest to Screen for COVID-19 Infection?

BACKGROUND AND PURPOSE: Chest CT may be used as a tool for rapid coronavirus disease 2019 (COVID-19) detection. Our aim was to investigate the value of additional chest CT for detection of coronavirus 19 (COVID-19) in patients who undergo head CT for suspected stroke or head trauma in a COVID-19-endemic region. MATERIALS AND METHODS: Our study included 27 patients (mean age, 74 years; range, 54-90 years; 20 men) who underwent head CT for suspected stroke (n = 21) or head trauma (n = 6), additional chest CT for COVID-19 detection, and real-time reverse transcriptase polymerase chain reaction testing in a COVID-19-endemic region. Sensitivity, specificity, and negative and positive predictive values of chest CT in detecting COVID-19 were calculated. RESULTS: Final neurologic diagnoses were ischemic stroke (n = 11), brain contusion (n = 5), nontraumatic intracranial hemorrhage (n = 2), brain metastasis (n = 1), and no primary neurologic disorder (n = 8). Symptoms of possible COVID-19 infection (ie, fever, cough, and/or shortness of breath) were present in 20 of 27 (74%) patients. Seven of 27 patients (26%) had real-time reverse transcriptase polymerase chain reaction confirmed-COVID-19 infection. Chest CT results were 6 true-positives, 15 true-negatives, 5 false-positives, and 1 false-negative. Diagnostic performance values of chest CT were a sensitivity of 85.7%, specificity of 75.0%, negative predictive value of 93.8%, and positive predictive value of 54.6%. CONCLUSIONS: The sensitivity of additional chest CT is fairly high. However, a negative result does not exclude COVID-19. The positive predictive value is poor. Correlation of chest CT results with epidemiologic history and clinical presentation, along with real-time reverse transcriptase polymerase chain reaction, is needed for confirmation.

Interactive 3D U-net for the segmentation of the pancreas in computed tomography scans.

The increasing incidence of pancreatic cancer will make it the second deadliest cancer in 2030. Imaging based early diagnosis and image guided treatment are emerging potential solutions. Artificial intelligence (AI) can help provide and improve widespread diagnostic expertise and accurate interventional image interpretation. Accurate segmentation of the pancreas is essential to create annotated data sets to train AI, and for computer assisted interventional guidance. Automated deep learning segmentation performance in pancreas computed tomography (CT) imaging is low due to poor grey value contrast and complex anatomy. A good solution seemed a recent interactive deep learning segmentation framework for brain CT that helped strongly improve initial automated segmentation with minimal user input. This method yielded no satisfactory results for pancreas CT, possibly due to a sub-optimal neural network architecture. We hypothesize that a state-of-the-art U-net neural network architecture is better because it can produce a better initial segmentation and is likely to be extended to work in a similar interactive approach. We implemented the existing interactive method, iFCN, and developed an interactive version of U-net method we call iUnet. The iUnet is fully trained to produce the best possible initial segmentation. In interactive mode it is additionally trained on a partial set of layers on user generated scribbles. We compare initial segmentation performance of iFCN and iUnet on a 100CT dataset using dice similarity coefficient analysis. Secondly, we assessed the performance gain in interactive use with three observers on segmentation quality and time. Average automated baseline performance was 78% (iUnet) versus 72% (FCN). Manual and semi-automatic segmentation performance was: 87% in 15 min. for manual, and 86% in 8 min. for iUNet. We conclude that iUnet provides a better baseline than iFCN and can reach expert manual performance significantly faster than manual segmentation in case of pancreas CT. Our novel iUnet architecture is modality and organ agnostic and can be a potential novel solution for semi-automatic medical imaging segmentation in general.

Guidelines for MR imaging in rectal cancer: Europe versus United States.

The aim of this study was to compare and contrast recently published guidelines for staging and reporting of MR imaging in rectal cancer from the European Society of Gastrointestinal and Abdominal Radiology and the North American Society of Abdominal Radiology. These guidelines were assessed on the presence of consensus and disagreement. Items were compared by two reviewers, and items with agreement and disagreement between the guidelines were identified and are presented in the current paper. Differences between guidelines are discussed to offer insights in practice variations between both continents and among expert centers, which to some extent may explain the differences between guidelines.