Bence Fejér
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bence Fejér has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Pál Maurovich-Horvat
MTA-SE Cardiovascular Imaging Research Group, Department of Radiology, Medical Imaging Centre, Semmelweis University, Hungary
4 shared publications - Béla Merkely
Heart and Vascular Center, Semmelweis University , Budapest
3 shared publications - Adam Domonkos Tarnoki
Medical Imaging Centre, Semmelweis University, 1082 Budapest, Hungary
2 shared publications - Andrea Ágnes Molnár
Heart and Vascular Center, Semmelweis University, Budapest, Hungary
2 shared publications - Anna Sára Kardos
Medical Imaging Centre, Semmelweis University , Budapest , Hungary
2 shared publications - Balázs Futácsi
Medical Imaging Centre, Semmelweis University , Budapest , Hungary
2 shared publications
Latest Publications
- Open Access
- 30 November 2021
- Published by Oxford University Press (OUP) in British Journal of Radiology
- Vol. 95 (1129) , 20210759
The diagnostic performance of deep-learning-based CT severity score to identify COVID-19 pneumonia
Objective: To determine the diagnostic accuracy of a deep-learning (DL)-based algorithm using chest computed tomography (CT) scans for the rapid diagnosis of coronavirus disease 2019 (COVID-19), as compared to the reference standard reverse-transcription polymerase chain reaction (RT-PCR) test. Methods: In this retrospective analysis, data of COVID-19 suspected patients who underwent RT-PCR and chest CT examination for the diagnosis of COVID-19 were assessed. By quantifying the affected area of the lung parenchyma, severity score was evaluated for each lobe of the lung with the DL-based algorithm. The diagnosis was based on the total lung severity score ranging from 0 to 25. The data were randomly split into a 40% training set and a 60% test set. Optimal cut-off value was determined using Youden-index method on the training cohort. Results: A total of 1259 patients were enrolled in this study. The prevalence of RT-PCR positivity in the overall investigated period was 51.5%. As compared to RT-PCR, sensitivity, specificity, positive predictive value, negative predictive value and accuracy on the test cohort were 39.0%, 80.2%, 68.0%, 55.0% and 58.9%, respectively. Regarding the whole data set, when adding those with positive RT-PCR test at any time during hospital stay or “COVID-19 without virus detection”, as final diagnosis to the true positive cases, specificity increased from 80.3% to 88.1% and the positive predictive value increased from 68.4% to 81.7%. Conclusion: DL-based CT severity score was found to have a good specificity and positive predictive value, as compared to RT-PCR. This standardized scoring system can aid rapid diagnosis and clinical decision making. Advances in knowledge: DL-based CT severity score can detect COVID-19-related lung alterations even at early stages, when RT-PCR is not yet positive.
- 30 November 2021
- Published by Oxford University Press (OUP) in British Journal of Radiology
- Vol. 95 (1129) , 20210759
Open AccessThe diagnostic performance of deep-learning-based CT severity score to identify COVID-19 pneumonia
Objective: To determine the diagnostic accuracy of a deep-learning (DL)-based algorithm using chest computed tomography (CT) scans for the rapid diagnosis of coronavirus disease 2019 (COVID-19), as compared to the reference standard reverse-transcription polymerase chain reaction (RT-PCR) test. Methods: In this retrospective analysis, data of COVID-19 suspected patients who underwent RT-PCR and chest CT examination for the diagnosis of COVID-19 were assessed. By quantifying the affected area of the lung parenchyma, severity score was evaluated for each lobe of the lung with the DL-based algorithm. The diagnosis was based on the total lung severity score ranging from 0 to 25. The data were randomly split into a 40% training set and a 60% test set. Optimal cut-off value was determined using Youden-index method on the training cohort. Results: A total of 1259 patients were enrolled in this study. The prevalence of RT-PCR positivity in the overall investigated period was 51.5%. As compared to RT-PCR, sensitivity, specificity, positive predictive value, negative predictive value and accuracy on the test cohort were 39.0%, 80.2%, 68.0%, 55.0% and 58.9%, respectively. Regarding the whole data set, when adding those with positive RT-PCR test at any time during hospital stay or “COVID-19 without virus detection”, as final diagnosis to the true positive cases, specificity increased from 80.3% to 88.1% and the positive predictive value increased from 68.4% to 81.7%. Conclusion: DL-based CT severity score was found to have a good specificity and positive predictive value, as compared to RT-PCR. This standardized scoring system can aid rapid diagnosis and clinical decision making. Advances in knowledge: DL-based CT severity score can detect COVID-19-related lung alterations even at early stages, when RT-PCR is not yet positive.
- Open Access
- 1 November 2021
- Published by MDPI AG in Tomography
- Vol. 7 (4) , 697-710
The Predictive Role of Artificial Intelligence-Based Chest CT Quantification in Patients with COVID-19 Pneumonia
We sought to analyze the prognostic value of laboratory and clinical data, and an artificial intelligence (AI)-based algorithm for Coronavirus disease 2019 (COVID-19) severity scoring, on CT-scans of patients hospitalized with COVID-19. Moreover, we aimed to determine personalized probabilities of clinical deterioration. Data of symptomatic patients with COVID-19 who underwent chest-CT-examination at the time of hospital admission between April and November 2020 were analyzed. COVID-19 severity score was automatically quantified for each pulmonary lobe as the percentage of affected lung parenchyma with the AI-based algorithm. Clinical deterioration was defined as a composite of admission to the intensive care unit, need for invasive mechanical ventilation, use of vasopressors or in-hospital mortality. In total 326 consecutive patients were included in the analysis (mean age 66.7 ± 15.3 years, 52.1% male) of whom 85 (26.1%) experienced clinical deterioration. In the multivariable regression analysis prior myocardial infarction (OR = 2.81, 95% CI = 1.12–7.04, p = 0.027), immunodeficiency (OR = 2.08, 95% CI = 1.02–4.25, p = 0.043), C-reactive protein (OR = 1.73, 95% CI = 1.32–2.33, p < 0.001) and AI-based COVID-19 severity score (OR = 1.08; 95% CI = 1.02–1.15, p = 0.013) appeared to be independent predictors of clinical deterioration. Personalized probability values were determined. AI-based COVID-19 severity score assessed at hospital admission can provide additional information about the prognosis of COVID-19, possibly serving as a useful tool for individualized risk-stratification.
- 1 November 2021
- Published by MDPI AG in Tomography
- Vol. 7 (4) , 697-710
Open AccessThe Predictive Role of Artificial Intelligence-Based Chest CT Quantification in Patients with COVID-19 Pneumonia
We sought to analyze the prognostic value of laboratory and clinical data, and an artificial intelligence (AI)-based algorithm for Coronavirus disease 2019 (COVID-19) severity scoring, on CT-scans of patients hospitalized with COVID-19. Moreover, we aimed to determine personalized probabilities of clinical deterioration. Data of symptomatic patients with COVID-19 who underwent chest-CT-examination at the time of hospital admission between April and November 2020 were analyzed. COVID-19 severity score was automatically quantified for each pulmonary lobe as the percentage of affected lung parenchyma with the AI-based algorithm. Clinical deterioration was defined as a composite of admission to the intensive care unit, need for invasive mechanical ventilation, use of vasopressors or in-hospital mortality. In total 326 consecutive patients were included in the analysis (mean age 66.7 ± 15.3 years, 52.1% male) of whom 85 (26.1%) experienced clinical deterioration. In the multivariable regression analysis prior myocardial infarction (OR = 2.81, 95% CI = 1.12–7.04, p = 0.027), immunodeficiency (OR = 2.08, 95% CI = 1.02–4.25, p = 0.043), C-reactive protein (OR = 1.73, 95% CI = 1.32–2.33, p < 0.001) and AI-based COVID-19 severity score (OR = 1.08; 95% CI = 1.02–1.15, p = 0.013) appeared to be independent predictors of clinical deterioration. Personalized probability values were determined. AI-based COVID-19 severity score assessed at hospital admission can provide additional information about the prognosis of COVID-19, possibly serving as a useful tool for individualized risk-stratification.
- Open Access
- 19 June 2021
- Published by Akademiai Kiado Zrt. in Imaging
- Vol. 13 (1) , 25-36
CT texture analysis of abdominal lesions – Part II: Tumors of the Kidney and Pancreas
It has been proven in a few early studies that radiomic analysis offers a promising opportunity to detect or differentiate between organ lesions based on their unique texture parameters. Recently, the utilization of CT texture analysis (CTTA) has been receiving significant attention, especially for response evaluation and prognostication of different oncological diagnoses. In this review article, we discuss the unique ability of radiomics and its subfield CTTA to diagnose lesions in the pancreas and kidney. We review studies in which CTTA was used for the classification of histology grades in pancreas and kidney tumors. We also review the role of radiogenomics in the prediction of the molecular and genetic subtypes of pancreatic tumors. Furthermore, we provide a short report on recent advancements of radiomic analysis in predicting prognosis and survival of patients with pancreatic and renal cancers.
- 19 June 2021
- Published by Akademiai Kiado Zrt. in Imaging
- Vol. 13 (1) , 25-36
Open AccessCT texture analysis of abdominal lesions – Part II: Tumors of the Kidney and Pancreas
It has been proven in a few early studies that radiomic analysis offers a promising opportunity to detect or differentiate between organ lesions based on their unique texture parameters. Recently, the utilization of CT texture analysis (CTTA) has been receiving significant attention, especially for response evaluation and prognostication of different oncological diagnoses. In this review article, we discuss the unique ability of radiomics and its subfield CTTA to diagnose lesions in the pancreas and kidney. We review studies in which CTTA was used for the classification of histology grades in pancreas and kidney tumors. We also review the role of radiogenomics in the prediction of the molecular and genetic subtypes of pancreatic tumors. Furthermore, we provide a short report on recent advancements of radiomic analysis in predicting prognosis and survival of patients with pancreatic and renal cancers.
- Open Access
Overlapping Genetic Background of Coronary Artery and Carotid/Femoral Atherosclerotic Calcification
Background and objectives: Multivessel atherosclerosis and its genetic background are under-investigated, although atherosclerosis is seldom local and still causes high mortality. Alternative methods to assess coronary calcification (CAC) might incorporate genetic links between different arteries’ atherosclerotic involvement, however, co-occurrences of coronary calcification have not been investigated in twins yet. Materials and Methods: We assessed the heritability of radio morphologically distinct atherosclerotic plaque types in coronary (non-enhanced CT, Agatston score), carotid, and femoral arteries (B-mode ultrasound) in 190 twin subjects (60 monozygotic, 35 dizygotic pairs). Four-segment scores were derived in order to assess the dissemination of the distinct plaque types in the carotid and femoral arteries taking bilaterality into account. We calculated the genetic correlation between phenotypically correlating plaque types in these arteries. Results: CAC and dissemination of calcified plaques in the carotid and femoral arteries (4S_hyper) were moderately heritable (0.67 [95% CI: 0.37–1] and 0.69 [95% CI: 0.38–1], respectively) when adjusted for age and sex. Hypoechoic plaques in the carotid and femoral arteries showed no heritability, while mixed plaques showed intermediate heritability (0.50 [95% CI: 0–0.76]). Age and sex-adjusted phenotypic correlation between CAC and 4segm_hyper was 0.48 [95% CI: 0.30–0.63] and the underlying genetic correlation was 0.86 [95% CI: 0.42–1]. Conclusions: Calcification of atherosclerotic plaques is moderately heritable in all investigated arteries and significant overlapping genetic factors can be attributed to the phenotypical resemblance of coronary and carotid or femoral atherosclerotic calcification. Our findings support the idea of screening extracoronary arteries in asymptomatic individuals. We also propose a hypothesis about primarily carotid-coronary and femoral-coronary atherosclerosis as two distinct genetic predispositions to co-localization.
Open AccessOverlapping Genetic Background of Coronary Artery and Carotid/Femoral Atherosclerotic Calcification
Background and objectives: Multivessel atherosclerosis and its genetic background are under-investigated, although atherosclerosis is seldom local and still causes high mortality. Alternative methods to assess coronary calcification (CAC) might incorporate genetic links between different arteries’ atherosclerotic involvement, however, co-occurrences of coronary calcification have not been investigated in twins yet. Materials and Methods: We assessed the heritability of radio morphologically distinct atherosclerotic plaque types in coronary (non-enhanced CT, Agatston score), carotid, and femoral arteries (B-mode ultrasound) in 190 twin subjects (60 monozygotic, 35 dizygotic pairs). Four-segment scores were derived in order to assess the dissemination of the distinct plaque types in the carotid and femoral arteries taking bilaterality into account. We calculated the genetic correlation between phenotypically correlating plaque types in these arteries. Results: CAC and dissemination of calcified plaques in the carotid and femoral arteries (4S_hyper) were moderately heritable (0.67 [95% CI: 0.37–1] and 0.69 [95% CI: 0.38–1], respectively) when adjusted for age and sex. Hypoechoic plaques in the carotid and femoral arteries showed no heritability, while mixed plaques showed intermediate heritability (0.50 [95% CI: 0–0.76]). Age and sex-adjusted phenotypic correlation between CAC and 4segm_hyper was 0.48 [95% CI: 0.30–0.63] and the underlying genetic correlation was 0.86 [95% CI: 0.42–1]. Conclusions: Calcification of atherosclerotic plaques is moderately heritable in all investigated arteries and significant overlapping genetic factors can be attributed to the phenotypical resemblance of coronary and carotid or femoral atherosclerotic calcification. Our findings support the idea of screening extracoronary arteries in asymptomatic individuals. We also propose a hypothesis about primarily carotid-coronary and femoral-coronary atherosclerosis as two distinct genetic predispositions to co-localization.
- 1 June 2017
- Published by Elsevier in European Journal of Internal Medicine
- Vol. 41, 44-48
Heritability of the femoral intima media thickness
- 1 June 2017
- Published by Elsevier in European Journal of Internal Medicine
- Vol. 41, 44-48
Heritability of the femoral intima media thickness