Search

Abstract Objectives To develop and evaluate a multi-task deep-learning (DL) model for automated segment-level coronary artery calcium (CAC) scoring on non-contrast computed tomography (CT) for precise localization and quantification of calcifications in the coronary artery tree. Methods This study included 1514 patients (mean age, 60.0 ± 10.2 years; 56.0% female) with stable chest pain from 26 centers participating in the multicenter DISCHARGE trial (NCT02400229). The patients were randomly assigned to a training/validation set (1059) and a test set (455). We developed a multi-task neural network for performing the segmentation of calcifications on the segment level as the main task and the segmentation of coronary artery segment regions with weak annotations as an auxiliary task. Model performance was evaluated using (micro-average) sensitivity, specificity, F1-score, and weighted Cohen’s κ for segment-level agreement based on the Agatston score and performing interobserver variability analysis. Results In the test set of 455 patients with 1797 calcifications, the model assigned 73.2% (1316/1797) to the correct coronary artery segment. The model achieved a micro-average sensitivity of 0.732 (95% CI: 0.710–0.754), a micro-average specificity of 0.978 (95% CI: 0.976–0.980), and a micro-average F1-score of 0.717 (95% CI: 0.695–0.739). The segment-level agreement was good with a weighted Cohen’s κ of 0.808 (95% CI: 0.790–0.824), which was only slightly lower than the agreement between the first and second observer (0.809 (95% CI: 0.798–0.845)). Conclusion Automated segment-level CAC scoring using a multi-task neural network approach showed good agreement on the segment level, indicating that DL has the potential for automated coronary artery calcification classification. Critical relevance statement Multi-task deep learning can perform automated coronary calcium scoring on the segment level with good agreement and may contribute to the development of new and improved calcium scoring methods. Key Points Segment-level coronary artery calcium scoring is a tedious and error-prone task. The proposed multi-task model achieved good agreement with a human observer on the segment level. Deep learning can contribute to the automation of segment-level coronary artery calcium scoring. Graphical Abstract

Abstract Objectives To determine the perspective of final-year medical students on the use of computed tomography (CT) in patients with sepsis. Methods A total of 207 questionnaires were distributed to final-year medical students at a large university medical center, and 113 returned questionnaires met the criteria for inclusion in the analysis. Questions referred to sepsis guidelines, CT indications, and the use of contrast agents. Control variables included a level of practical experience as a final-year student (trimester of student’s practical year) and previous radiological experience. Statistical hypothesis tests such as the Mann-Whitney U test and chi-square test were performed. Results The majority of participating students, 85% (n = 91/107), considered a Systemic Organ Failure Assessment (SOFA) score ≥ 2 as a diagnostic criterion for sepsis. The presence of ≥ 2 positive systemic inflammatory response syndrome (SIRS) criteria was considered relevant for diagnosing sepsis by 34% (n = 34/100). Ninety-nine percent (n = 64/65) of the participants who fully agreed with a SOFA score ≥ 2 being relevant for diagnosing sepsis would also use it as an indication for a CT scan. Seventy-six percent (n = 78/103) of the students rated a known severe allergic reaction to contrast agents as an absolute contraindication for its administration. Ninety-five percent (n = 78/82) considered radiation exposure as problematic in CT examinations, especially in repeat CTs. Conclusion Most final-year medical students were familiar with the sepsis criteria. Still, some referred to outdated diagnostic criteria. Participants saw the ability to plan further patient management based on CT as a major benefit. Most participants were aware of radiation as a risk of CT. Critical relevance statement More detailed knowledge of CT in septic patients should be implemented in the medical curriculum. Retraining of medical students could help increase student confidence potentially improving patient care. Key points 1. Whereas the majority of final-year medical students were familiar with sepsis criteria, some referred to outdated diagnostic criteria. 2. Participants saw the ability to plan further patient management based on CT as a major benefit. 3. Most participants were aware of radiation as a risk of CT. Graphical Abstract

Abstract Magnetic resonance elastography (MRE) for measuring viscoelasticity heavily depends on proper tissue segmentation, especially in heterogeneous organs such as the prostate. Using trained network-based image segmentation, we investigated if MRE data suffice to extract anatomical and viscoelastic information for automatic tabulation of zonal mechanical properties of the prostate. Overall, 40 patients with benign prostatic hyperplasia (BPH) or prostate cancer (PCa) were examined with three magnetic resonance imaging (MRI) sequences: T2-weighted MRI (T2w), diffusion-weighted imaging (DWI), and MRE-based tomoelastography, yielding six independent sets of imaging data per patient (T2w, DWI, apparent diffusion coefficient, MRE magnitude, shear wave speed, and loss angle maps). Combinations of these data were used to train Dense U-nets with manually segmented masks of the entire prostate gland (PG), central zone (CZ), and peripheral zone (PZ) in 30 patients and to validate them in 10 patients. Dice score (DS), sensitivity, specificity, and Hausdorff distance were determined. We found that segmentation based on MRE magnitude maps alone (DS, PG: 0.93 ± 0.04, CZ: 0.95 ± 0.03, PZ: 0.77 ± 0.05) was more accurate than magnitude maps combined with T2w and DWI_b (DS, PG: 0.91 ± 0.04, CZ: 0.91 ± 0.06, PZ: 0.63 ± 0.16) or T2w alone (DS, PG: 0.92 ± 0.03, CZ: 0.91 ± 0.04, PZ: 0.65 ± 0.08). Automatically tabulated MRE values were not different from ground-truth values (P>0.05). In conclusion, MRE combined with Dense U-net segmentation allows tabulation of quantitative imaging markers without manual analysis and independent of other MRI sequences and can thus contribute to PCa detection and classification.