A novel imaging biomarker for prediction of cerebrovascular ischemic events: Pericarotid fat density.

BACKGROUND: To investigate the relationship between pericarotid fat density measured in carotid CTA and vulnerable carotid plaque. METHODS: This retrospective study included 374 participants who underwent carotid CTA between June 1, 2021, and December 1, 2021 (234 males, median age 68 years [interquartile range: 61-75]). Two groups, symptomatic and asymptomatic, were defined based on either diffusion-weighted MRI or a clinical history of acute ischemia or TIA within 6 months before or after CTA. The relationship between pericarotid fat density and cerebrovascular ischemic events was assessed using receiver operating characteristic analysis and binary logistic regression analysis. RESULTS: In the symptomatic group (n = 135), mean pericarotid fat density (-63.3 ± 21.7 vs. -81.7 ± 16.9 HU, respectively; p < 0.001) and median maximum plaque thickness (4 [interquartile range: 3-6] vs. 3.7 [interquartile range: 2.6-4.7] mm, respectively; p = 0.002) were higher, while plaque density (42.1 ± 19.6 vs. 50.6 ± 20.4 HU, respectively; p = 0.001) was lower compared to the asymptomatic group. Pericarotid fat density (OR: 1.038, 95% CI: 1.023-1.053, p < 0.001) was identified as an independent predictor for symptomatic patients. The optimal cut-off value for pericarotid fat density predicting symptomatic patients was estimated as -74 HU (area under the curve: 0.753, 95% CI:0.699-0.808, p < 0.001). Inter-reader agreement for pericarotid fat density was found to be almost perfect (intraclass correlation coefficient: 0.818, 95% CI: 0.770-0.856, p < 0.001). CONCLUSION: Pericarotid fat density may serve as an imaging biomarker in predicting acute cerebrovascular ischemic events.

Elevating healthcare through artificial intelligence: analyzing the abdominal emergencies data set (TR_ABDOMEN_RAD_EMERGENCY) at TEKNOFEST-2022.

OBJECTIVES: The artificial intelligence competition in healthcare at TEKNOFEST-2022 provided a platform to address the complex multi-class classification challenge of abdominal emergencies using computer vision techniques. This manuscript aimed to comprehensively present the methodologies for data preparation, annotation procedures, and rigorous evaluation metrics. Moreover, it was conducted to introduce a meticulously curated abdominal emergencies data set to the researchers. METHODS: The data set underwent a comprehensive central screening procedure employing diverse algorithms extracted from the e-Nabiz (Pulse) and National Teleradiology System of the Republic of Türkiye, Ministry of Health. Full anonymization of the data set was conducted. Subsequently, the data set was annotated by a group of ten experienced radiologists. The evaluation process was executed by calculating F1 scores, which were derived from the intersection over union values between the predicted bounding boxes and the corresponding ground truth (GT) bounding boxes. The establishment of baseline performance metrics involved computing the average of the highest five F1 scores. RESULTS: Observations indicated a progressive decline in F1 scores as the threshold value increased. Furthermore, it could be deduced that class 6 (abdominal aortic aneurysm/dissection) was relatively straightforward to detect compared to other classes, with class 5 (acute diverticulitis) presenting the most formidable challenge. It is noteworthy, however, that if all achieved outcomes for all classes were considered with a threshold of 0.5, the data set's complexity and associated challenges became pronounced. CONCLUSION: This data set's significance lies in its pioneering provision of labels and GT-boxes for six classes, fostering opportunities for researchers. CLINICAL RELEVANCE STATEMENT: The prompt identification and timely intervention in cases of emergent medical conditions hold paramount significance. The handling of patients' care can be augmented, while the potential for errors is minimized, particularly amidst high caseload scenarios, through the application of AI. KEY POINTS: • The data set used in artificial intelligence competition in healthcare (TEKNOFEST-2022) provides a 6-class data set of abdominal CT images consisting of a great variety of abdominal emergencies. • This data set is compiled from the National Teleradiology System data repository of emergency radiology departments of 459 hospitals. • Radiological data on abdominal emergencies is scarce in literature and this annotated competition data set can be a valuable resource for further studies and new AI models.

Association of diaphragm thickness and density measured on chest CT with disease severity in COVID-19 patients.

INTRODUCTION: A decrease in muscle mass of the diaphragm could be a significant risk factor for pneumonia. The aim of our study was to evaluate whether diaphragm thickness (DT) and density measured on chest computed tomography (CT) were associated with clinical course and mortality in adult patients with coronavirus disease 2019 (COVID-19) in emergency department admission. METHODS: We retrospectively analyzed 404 patients with a positive polymerase chain reaction test for COVID-19 and pneumonia findings on chest CT between September 1 and November 1, 2020. Bilateral DT measurements were performed at the level of the celiac artery origin, and the total mean diaphragm thickness (TMDT) was estimated. Hemidiaphragm density was measured at the level of the celiac artery origin. The relationship between demographic characteristics, comorbidities, TMDT, mean hemidiaphragm density (MHD) and clinical outcomes was investigated using the logistic regression analyses. The reliability of the measurement of the two observers was evaluated by intraclass correlation analyses. RESULTS: Intraclass correlation analyses demonstrated almost perfect inter-observer agreement for TMDT and substantial agreement for MHD. There was a statistically significant relationship between the presence of a thinner diaphragm and mortality (p < 0.001). Bilateral diaphragm densities were lower in the patients with severe disease and mortality (p < 0.001). The threshold values of TMDT were 3.67 mm and 3.47 mm for the prediction of ICU admission and mortality, respectively. TMDT (odds ratio [OR]: 0.634, 95% confidence interval [CI]: 0.447-0.901), age (OR: 1.053, 95% CI: 1.027-1.081) and MHD (OR: 0.920, 95% CI: 0.883-0.959) were found to be independent predictors for severe disease in the multivariable model. In addition, MHD (OR: 0.883, 95% CI: 0.827-0.942) and age (OR: 1.040, 95% CI: 1.003-1.078) were independent risk factors for mortality. CONCLUSION: Our study demonstrated that a low diaphragm thickness and density measured on chest CT were associated with severe disease in patients with COVID-19 and could be evaluated as poor prognostic markers.

Shear wave elastography for the evaluation of testicular salvage after testicular torsion.

The aim of this study was to assess the utility of shear wave elastography in the follow-up of testicular detorsion, evaluate long-term outcomes, and explore its relationship with parameters such as tissue stiffness values, pain duration, and torsion type. Elastography examinations were independently performed by two radiologists to evaluate patients who presented to our hospital for follow-up after being diagnosed with testicular torsion and age-matched controls. Inter-observer variability of the mean testicular tissue elasticity was excellent (Intraclass correlation coefficient: 0.939, p < 0.001). Median time between testicular detorsion and follow-up ultrasound examination was 18 months (range, 11-36 months). Torsion side, torsion degree, and pain duration were recorded, and testicular volumes were calculated. The study population comprised 24 patients (48 testes) with a mean age of 21.1 ± 7.8 years. The mean testicular volume was measured as 12.3 ± 5.4 ml for the testicular salvage group, 13.9 ± 3.8 ml for the contralateral testes, and 13.7 ± 2.7 ml for the control group (p = 0.553). The mean testicular speed mode values were higher in the testicular salvage group (1.34 ± 1.21 m/s) compared with the contralateral testes group (1.00 ± 0.08 m/s), and the control group (1.01 ± 0.06 m/s), however there was no statistically significant difference between the three groups (p = 0.861). While testicular atrophy was detected in three patients, an intraparenchymal wedge-shaped focal hypoechoic area developed after torsion in a further three patients. The elastography examination for focal hypoechoic areas revealed an increase or decrease in tissue stiffness compared to the normal parenchyma. The tissue stiffness values of the testicular salvage group were higher in complete torsion compared to incomplete torsion. The elastography method contributes to other imaging methods in distinguishing focal lesion areas that can be seen after testicular torsion from malignant conditions. Elastography presents as a feasible and practical complementary modality for the follow-up of testicular salvage after torsion.

Prognostic utility of pulmonary artery and ascending aorta diameters derived from computed tomography in COVID-19 patients.

AIM: Chest computed tomography (CT) imaging plays a diagnostic and prognostic role in Coronavirus disease 2019 (COVID-19) patients. This study aimed to investigate and compare predictive capacity of main pulmonary artery diameter (MPA), ascending aorta diameter (AAo), and MPA-to-AAo ratio to determine in-hospital mortality in COVID-19 patients. MATERIALS AND METHODS: This retrospective study included 255 hospitalized severe or critical COVID-19 patients. MPA was measured at the level of pulmonary artery bifurcation perpendicular to the direction of the vessel through transverse axial images and AAo was measured by using the same CT slice at its maximal diameter. MPA-to-AAo ratio was calculated by division of MPA to AAo. RESULTS: Multivariate logistic regression model yielded MPA ≥29.15 mm (OR: 4.95, 95% CI: 2.01-12.2, p = 0.001), MPA (OR: 1.28, 95% CI: 1.13-1.46, p < 0.001), AAo (OR: .90, 95% CI: .81-.99, p = 0.040), and MPA-to-AAo ratio ≥.82 (OR: 4.67, 95% CI: 1.86-11.7, p = 0.001) as independent predictors of in-hospital mortality. Time-dependent multivariate Cox-proportion regression model demonstrated MPA ≥29.15 mm (HR: 1.96, 95% CI: 1.03-3.90, p = 0.047) and MPA (HR: 1.08, 95% CI: 1.01-1.17, p = 0.048) as independent predictors of in-hospital mortality, whereas AAo and MPA-to-AAo ratio did not reach statistical significance. CONCLUSION: Pulmonary artery enlargement strongly predicts in-hospital mortality in hospitalized COVID-19 patients. MPA, which can be calculated easily from chest CT imaging, can be beneficial in the prognostication of these patients.

Acute myocarditis associated with COVID-19 infection.

We present the case of a 20-year-old male patient without previous history of cardiovascular disease who was admitted to our hospital with a new onset febrile sensation and chest pain. Chest computed tomography revealed a subpleural consolidation with a halo of ground-glass opacification. Blood tests revealed elevated levels of markers of myocyte necrosis (troponin I and creatine kinase-MB). Nasopharyngeal swab was positive for COVID-19. Cardiac MRI showed myocardial edema and late gadolinium enhancement compatible with myocarditis associated with COVID-19 infection. This case showed that acute myocarditis can be the initial presentation of patients with COVID-19 infection.

Ankara bombing: distribution of injury patterns with radiological imaging.

PURPOSE: To describe and explain the blast injuries and imaging findings in the Ankara terrorist explosion that took place on October 10, 2015. MATERIAL AND METHODS: A total of 77 patients who underwent radiologic imaging were classified as primary, secondary, tertiary, and quaternary, according to the injury type. The patients were evaluated based on body regions, such as head and neck, thorax, abdomen, lower extremity, and upper extremity. RESULTS: Blast lung injury was identified in one patient and tympanic membrane perforation in seven patients, as the primary injury. Sixty-two of 77 patients had secondary blast injuries caused by shrapnel. The blast injuries were observed in the head and neck (16/77, 20.7%), thorax (11/77, 14.2%), abdomen (16/77, 20.7%), lower extremity (48/77, 62.3%), and upper extremity (5/77, 6.4%). Vascular injuries were seen in eight cases, of which seven were in the lower extremities. CONCLUSIONS: The most common blast injury pattern was of a secondary type in the current study. Lower extremities were the significantly more affected body region, probably due to the bomb exploding at ground level. In mass casualty events, radiologic imaging is located at the centre of patient management.

Short-term outcomes of the iCover balloon-expandable covered stent for iliac artery lesions.

PURPOSE: To describe the short-term follow-up results of the recently introduced iCover balloon-expandable covered stents for iliac artery lesions. METHODS: All consecutive patients treated with iCover balloon-expandable covered stents between March 2022 and August 2023 were retrospectively reviewed. The primary endpoint was target lesion revascularization (TLR) at 6 months. Secondary endpoints included major adverse events, freedom from TLR throughout the follow-up period, primary and secondary patency, and clinical and technical success. RESULTS: In the study population of 40 adult patients (87.5% men, mean age: 63.5 ± 11 years), the mean follow-up period was 6.2 ± 2.8 months. A total of 98 stents of various sizes were implanted. The technical success rate was 100%. Freedom from TLR was 95.8% [95%, confidence interval (CI): 95%- 96.6%], the primary patency rate was 91.7% (95%, CI: 89.8%-93.6%), and the secondary patency rate was 95.8% (95%, CI: 95%-96.6%) at 6 months. The all-cause mortality rate was 5%. CONCLUSION: These real-world data demonstrate a high technical and clinical success rate, a high 6-month primary patency rate, and a low requirement for TLR. These are promising indicators for the safety and efficacy of iCover stents. CLINICAL SIGNIFICANCE: Balloon-expandable covered stents are frequently used in iliac artery atherosclerotic disease. This study shows that the short-term follow-up results of the new iCover stent are satisfactory, indicating its safety and efficacy.

Evaluating GPT-4o's Performance in the Official European Board of Radiology Exam: A Comprehensive Assessment.

RATIONALE AND OBJECTIVES: This study aims to evaluate the performance of generative pre-trained transformer (GPT)-4o in the complete official European Board of Radiology (EBR) exam, designed to assess radiology knowledge, skills, and competence. MATERIALS AND METHODS: Questions based on text, image, or video and in the format of multiple choice, free-text reporting, or image annotation were uploaded into GPT-4o using standardized prompting. The results were compared to the average scores of radiologists taking the exam in real time. RESULTS: In Part 1 (multiple response questions and short cases), GPT-4o outperformed both the radiologists' average scores and the maximum pass score (70.2% vs. 58.4% and 60%, respectively). In Part 2 (clinically oriented reasoning evaluation), the performance of GPT-4o was below both the radiologists' average scores and the minimum pass score (52.9% vs. 66.1% and 55%, respectively). The accuracy on questions involving ultrasound images was higher compared to other imaging modalities (accuracy rate, 87.5-100%). For video-based questions, the performance was 50.6%. The model achieved the highest accuracy on most likely diagnosis questions but showed lower accuracy in free-text reporting and direct anatomical assessment in images (100% vs. 31% and 28.6%, respectively). CONCLUSION: The abilities of GPT-4o in the official EBR exam are particularly noteworthy. This study demonstrates the potential of large language models to assist radiologists in assessing and managing cases from diagnosis to treatment or follow-up recommendations, even with zero-shot prompting.

The prognostic role of perirenal fat tissue in non-metastatic renal cell carcinoma.

PURPOSE: The aim of this study was to evaluate the impact of perirenal fat volume and perirenal fat density on prognosis in surgically treated non-metastatic renal cell carcinomas (RCC). METHODS AND MATERIALS: All consecutive patients who underwent partial or total nephrectomy surgery between March 2019 and December 2021 were assessed. Measurements of perirenal fat volume and perirenal fat density were performed on computed tomography (CT) images. The relationship between progression and perirenal fat parameters was evaluated using ROC analysis, Cox regression analysis, and Kaplan-Meier analysis. RESULTS: In the study population comprising 118 patients diagnosed with RCC (74.6% male, mean age of 59.1 ± 11.8 years), the median follow-up duration was 43 months (interquartile range: 33-51 months). Perirenal fat volume (AUC: 0.669, 95% CI 0.538-0.799, p = 0.011) and perirenal fat density (AUC: 0.680, 95% CI 0.558-0.803, p = 0.007) demonstrated acceptable discrimination performance in predicting progression. There was a significant association between high perirenal fat volume and high perirenal fat density with poor progression-free survival (HR: 1.007, 95% CI 1.003-1.011, p = 0.001 vs. HR: 1.084, 95% CI 1.033-1.137, p = 0.001; respectively). CONCLUSION: High perirenal fat volume and high perirenal fat density are independent predictors for poor progression-free survival. Perirenal fat parameters, easily obtainable from preoperative CT images, may serve as potential tools in predicting the prognosis of non-metastatic RCC.

Effect of sarcopenia on mortality in acute stroke patients receiving endovascular treatment.

BACKGROUND: To investigate the effect of sarcopenia on mortality in patients with acute ischemic stroke caused by anterior circulation large artery occlusion who underwent endovascular treatment. METHODS: Acute ischemic stroke patients (n = 194) treated with mechanical thrombectomy who underwent chest computed tomography between 2019 and 2022 (median age, 69 [interquartile range: 61-77], 95 females, 99 males) were evaluated retrospectively. The cross-sectional area and density of the pectoralis muscle [pectoralis muscle area (PMA) and pectoralis muscle density (PMD)] at the level of the aortic arch and the erector spinae muscle at the T12 level [erector spinae muscle area (ESMA) and erector spinae muscle density (ESMD)] were measured. The association between skeletal muscle parameters and mortality outcomes was investigated using the receiver operating characteristic (ROC) curve and multivariable logistic regression analyses. RESULTS: The 90-day mortality rate was 32% in the study population (n = 62). The ROC analysis revealed that ESMD [area under the curve (AUC): 0.765] and PMD (AUC: 0.759) performed best in the prediction of 90-day mortality. In the multivariable logistic regression analysis, PMD [odds ratio (OR): 0.896; 95% confidence interval (CI): 0.846-0.948; p < 0.001], ESMA (OR: 0.929; 95% CI: 0.878-0.983; p = 0.011), and ESMD (OR: 0.947; 95% CI: 0.913-0.983; p = 0.004), but not PMA, were independent risk factors for 90-day mortality. CONCLUSION: PMD, ESMA, and ESMD may be risk factors for 90-day mortality after mechanical thrombectomy for acute ischemic stroke.

Unveiling the potential of strain elastography in perihilar cholangiocarcinoma biopsies.

PURPOSE: This study was conducted to investigate the effectiveness of strain elastography in guiding precise and sufficient tissue sampling for perihilar cholangiocarcinoma (CCA) biopsies. METHODS: Our retrospective analysis included 23 liver biopsies conducted between March 2019 and July 2022 for suspected perihilar CCA. An experienced radiologist performed the biopsies via an ultrasound machine with elastography configuration. Tissue stiffness color maps were used for guiding when the biopsies were performed. Strain index value calculations were made by radiologists on recorded images. RESULTS: Patient demographics revealed a mean age of 65.17 ± 9.25 years, with a gender distribution of six females and 17 males. Gray-scale examinations unveiled diverse echogenic characteristics in liver lesions. Elastography-guided biopsies demonstrated no need for repeats, while gray-scale biopsies necessitated re-biopsy in four patients, resulting in cholangiocarcinoma diagnosis (P = 0.037). Strain index values showcased strong inter- and intra-observer agreements (P < 0.001). Notably, no post-biopsy complications emerged in either study group. CONCLUSION: The diagnostic advantage of elastography, particularly in enhancing accuracy in challenging isoechoic lesions, was demonstrated, although the substantial overlap between strain index values of benign and malignant liver masses limits clinical usefulness of this technique.

Ground level falls: computed tomography findings and clinical outcomes by age groups.

BACKGROUND: This study aimed to determine injury patterns in ground level falls (GLFs) and investigate the effect of age on the severity of injury. METHODS: We retrospectively identified 4,712 patients who presented to a Level 1 trauma center due to GLFs and analyzed the data of 1,214 patients who underwent computed tomography (CT). Demographics, torso examination findings, and injuries detected on CT were recorded. To investigate the effect of age on injury severity, the patients were grouped as those aged <65 and ≥65 years. RESULTS: The mean age was 57 years, and 55.20% of the patients were female. The mortality rate was 0.50%. Injury was detected in 489 (40.30%) patients on CT. Fractures were the most common injury type. Traumatic intracranial hemorrhage was detected in 32 (2.60%) patients. Only three (0.20%) of the 63 patients with rib fractures had concomitant lung injury. The negative predictive value of the physical examination (PE) was 95.80% for chest injury. Intra-abdominal injury was not detected in any of the 116 patients who underwent abdominal CT. Hospitalization was also higher in the ≥65-year group (p<0.001). All mortalities (n=6) were seen in patients aged ≥65 years. CONCLUSION: Our results indicate that GLFs cause more injuries in the elderly, resulting in more hospitalizations and mortality. Normal PE findings may reduce the need for whole-body CT in GLF patients who are conscious, cooperative, and oriented.

The effects of smoking cessation on the ratios of neutrophil/lymphocyte, platelet/lymphocyte, mean platelet volume/lymphocyte and monocyte/high-density lipoprotein cholesterol.

The amount of smoking, level of smoking addiction and smoking cessation have effects on blood cells, blood lipid levels, neutrophil/lymphocyte ratio (NLR), platelet/lymphocyte ratio (PLR), mean platelet volume (MPV)/lymphocyte ratio (MPVLR) and monocyte/high- density lipoprotein (HDL) ratio (MHR). Methods In this self-controlled experimental study, we included individuals who applied to a smoking cessation clinic and quit smoking. Their sociodemographic and clinical characteristics, the amount of cigarettes consumed (pack/year), their Fagerstrom test for nicotine dependence (FTND) results, haemogram values before and 6 months after quitting smoking, NLR, PLR, MPVLR, MHR and blood lipid levels before and after the treatment were compared retrospectively. Results The mean (SD) age of the 239 individuals who participated in the study was 41.7 (10.9) years and 55.2% of them were women. Their mean FTND score was 7.06 (2.0), and most of them (47.7%) had a very high level of addiction. After the smoking cessation treatment, their neutrophil, platelet, MPV, red cell distribution width, platelet distribution width (PDW), cholesterol, triglyceride, low- density lipoprotein, NLR, PLR, MPVLR, MHR and HDL values increased (p<0.05). The amount of smoking and level of dependence were negatively correlated with HDL, and positively correlated with other parameters. Conclusion After smoking cessation, in addition to dyslipidaemia, the NLR, PLR, MPVLR and MHR values also decreased, and the difference was found to correlate with the level of addiction and the amount of smoking.

Investigation of the relationship of the number, localization, and displacement of rib fractures with intrathoracic structures and abdominal solid organ complications using computed tomography.

PURPOSE: This study aimed at evaluating the fracture properties, intrathoracic structures, and abdominal solid organ complications in patients with traumatic rib fractures. METHODS: Chest CT images of 305 patients were retrospectively evaluated to determine the number and level of rib fractures and measure the magnitude of displacement. The relationship of rib fractures and displacement patterns with intrathoracic structures and abdominal solid organ complications was investigated. RESULTS: The fractures were most located in the fifth, sixth, and seventh ribs. The mean age of the patients with displaced fractures was statistically significantly higher than the non-displaced fracture group with pneumothorax, hemothorax or lung injury. RibScore was statistically significantly higher in patients with pneumothorax, hemothorax, and lung parenchyma injury, as well as those with liver, spleen, and kidney injury. Hepatic, splenic, and renal injuries were markedly higher in patients with displaced fractures, but this was not statistically significant. Spleen and kidney injuries were statistically significantly more frequent among the patients with the fractures of the 10th to 12th ribs. The rib fracture displacement cut-off values for pneumothorax, hemothorax, and lung injury were found to be 2.18 mm, 2.32 mm, and 2.82 mm, respectively. CONCLUSION: The presence of a displaced rib fracture is a strong predictor of intrathoracic complications. A more careful intrathoracic evaluation of rib fractures with more than 2 mm displacement will contribute to patient management.

Sarcopenia and Its Prognostic Role on Hospitalization and In-Hospital Mortality in Coronavirus Disease 2019 Patients with At Least One Cardiovascular Risk Factor.

BACKGROUND: The coronavirus disease 2019 infection is a global pandemic that has affected the whole world population. We aimed to evaluate the prognostic role of cross-sectional area, muscle index, and muscle attenuation values in computed tomography-based skeletal groups [erector spinae muscle, pectoralis muscle, and total skeletal muscle] of patients hospitalized for coronavirus disease 2019 and with at least 1 cardiovascular risk factor. METHODS: A total of 232 patients with coronavirus disease 2019 and at least 1 cardiovascular risk factor were enrolled in the study, retrospectively. The cross-sectional area, muscle index, and attenuation of erector spine muscle, pectoralis muscle, and total skeletal muscle were automatically measured on computed tomography images. The study population was assigned into tertiles on the basis of the total SMcsa index. The relationship between the values obtained and the length of hospital stay, admission to intensive care unit, the need for invasive mechani cal ventilation, and mortality was investigated. RESULTS: Admission to intensive care unit, need for invasive mechanical ventilation, and mor tality were higher at tertile 3 groups than in the other groups (all P values <.001). Statistically, all muscle measurements were significantly lower in tertile 3 (P <.001). Diabetes mellitus, hypertension, and total SMcsa index were predictors of in-hospital mortality in patients with coronavirus disease 2019 on the basis of Cox regression analysis. In the Kaplan-Meier analysis for the proportion of survivors relative to the total SMcsa index, tertile 3 had the highest mortal ity (survival rates 57%, P < .001). CONCLUSIONS: Sarcopenia and attendant cardiovascular comorbidities can effectively assess dis ease severity and predict outcome in patients with coronavirus disease 2019.

The predictive value of epicardial fat volume for clinical severity of COVID-19.

Introduction: Epicardial adipose tissue serves as a source of inflammatory cytokines and mediators. Cytokine storm is an important cause of morbidity and mortality in coronavirus disease 2019 (COVID-19). Objectives: To investigate the association between epicardial fat volume (EFV), inflammatory biomarkers and clinical severity of COVID-19. Methods: This retrospective study included 101 patients who were infected with COVID-19. Serum inflammatory biomarkers including C-reactive protein (CRP), interleukin-6 (IL-6), procalcitonin (PCT) and ferritin levels were measured. Computed tomography images were analyzed and semi-automated measurements for EFV were obtained. The primary composite endpoint was admission to the intensive care unit (ICU) or death. Results: The primary composite endpoint occurred in 25.1% (n=26) of patients (mean age 64.8±14.8 years, 14 male). A total of 10 patients died. EFV, CRP, PCT, ferritin and IL-6 levels were significantly higher in ICU patients. Moreover, a positive correlation was determined between EFV and CRP (r: 0.494, p<0.001), PCT (r: 0.287, p=0.005), ferritin (r: 0.265, p=0.01) and IL-6 (r: 0.311, p=0.005). On receiver operating characteristic analysis, patients with EFV >102 cm3 were more likely to have severe complications. In multivariate logistic regression analysis, EFV independently predicted admission to the ICU at a significant level (OR: 1.02, 95% CI: 1.01-1.03, p=0.025). Conclusion: EFV and serum CRP, IL-6, PCT and ferritin levels can effectively assess disease severity and predict the outcome in patients with COVID-19. EFV is an independent predictor of admission to the ICU in hospitalized COVID-19 patients.

Introdução: O tecido adiposo epicárdico é fonte de citocinas inflamatórias e mediadores. A tempestade de citocinas é uma importante causa de morbilidade e mortalidade na doença coronavírus 2019 (COVID-19). Objetivos: Investigar a associação entre volume adiposo epicárdico (VAE), biomarcadores inflamatórios e gravidade clínica da COVID-19. Métodos: Este estudo retrospetivo incluiu 101 doentes infetados com COVID-19. Foram avaliados biomarcadores inflamatórios séricos, incluindo os níveis de proteína C-reativa (PCR), de interleucina-6 (IL-6), de procalcitonina (PCT) e de ferritina. Foram analisadas imagens de tomografia computorizada (TC) e foram obtidas medições semi-automáticas do VAE. O endpoint primário composto foi a admissão na unidade de cuidados intensivos (UCI) ou morte. Resultados: O endpoint primário ocorreu em 25,1% (n=26) dos doentes (idade média 64,8±14,8 anos, 14 homens). Um total de 10 doentes morreu. Os níveis de VAE, PCR, PCT, ferritina e IL-6 foram significativamente superiores nos doentes internados na UCI. Além disso, verificou-se uma correlação positiva entre o VAE e a PCR (r: 0,494, p<0,001), PCT (r: 0,287, p=0,005), ferritina (r: 0,265, p=0,01) e IL-6 (r: 0,311, p=0,005). Na análise de regressão logistica multivariada, os doentes com VAE>102 cm3 tinham maior probabilidade de ter complicações graves. Conclusão: O VAE e os níveis séricos de PCR, IL-6, PCT e ferritina podem avaliar a gravidade da doença e prever o resultado em doentes com COVID-19. O VAE constitui um fator preditivo na admissão dos doentes hospitalizados com COVID-19 numa UCI.

Artificial Intelligence in Healthcare Competition (TEKNOFEST-2021): Stroke Data Set.

OBJECTIVE: The artificial intelligence competition in healthcare was organized for the first time at the annual aviation, space, and technology festival (TEKNOFEST), Istanbul/Türkiye, in September 2021. In this article, the data set preparation and competition processes were explained in detail; the anonymized and annotated data set is also provided via official website for further research. MATERIALS AND METHODS: Data set recorded over the period covering 2019 and 2020 were centrally screened from the e-Pulse and Teleradiology System of the Republic of Türkiye, Ministry of Health using various codes and filtering criteria. The data set was anonymized. The data set was prepared, pooled, curated, and annotated by 7 radiologists. The training data set was shared with the teams via a dedicated file transfer protocol server, which could be accessed using private usernames and passwords given to the teams under a nondisclosure agreement signed by the representative of each team. RESULTS: The competition consisted of 2 stages. In the first stage, teams were given 192 digital imaging and communications in medicine images that belong to 1 of 3 possible categories namely, hemorrhage, ischemic, or non-stroke. Teams were asked to classify each image as either stroke present or absent. In the second stage of the competition, qualifying 36 teams were given 97 digital imaging and communications in medicine images that contained hemorrhage, ischemia, or both lesions. Among the employed methods, Unet and DeepLabv3 were the most frequently observed ones. CONCLUSION: Artificial intelligence competitions in healthcare offer good opportunities to collect data reflecting various cases and problems. Especially, annotated data set by domain experts is more valuable.