Advanced search in Research products
Research products
arrow_drop_down
Searching FieldsTerms
Any field
arrow_drop_down
includes
arrow_drop_down
Include:
The following results are related to COVID-19. Are you interested to view more results? Visit OpenAIRE - Explore.
18 Research products, page 1 of 2

  • COVID-19
  • Research data
  • Research software
  • Other research products
  • 2022-2022
  • HU
  • English
  • SZTE Publicatio Repozitórium - SZTE - Repository of Publications
  • COVID-19

10
arrow_drop_down
Relevance
arrow_drop_down
  • Open Access English
    Authors: 
    Nzimande Ntombifuthi P.; El Tantawi Maha; Zuñiga Roberto Ariel Abeldaño; Opoku-Sarkodie Richmond; Brown Brandon; Ezechi Oliver C.; Uzochukwu Benjamin S. C.; Ellakany Passent; Aly Nourhan M.; Nguyen Annie Lu; +1 more
    Country: Hungary
  • Open Access English
    Authors: 
    Agarwal Mohit; Agarwal Sushant; Saba Luca; Chabert Gian Luca; Gupta Suneet; Carriero Alessandro; Pasche Alessio; Danna Pietro; Mehmedovic Armin; Faa Gavino; +6 more
    Country: Hungary

    COVLIAS 1.0: an automated lung segmentation was designed for COVID-19 diagnosis. It has issues related to storage space and speed. This study shows that COVLIAS 2.0 uses pruned AI (PAI) networks for improving both storage and speed, wiliest high performance on lung segmentation and lesion localization.ology: The proposed study uses multicenter ∼9,000 CT slices from two different nations, namely, CroMed from Croatia (80 patients, experimental data), and NovMed from Italy (72 patients, validation data). We hypothesize that by using pruning and evolutionary optimization algorithms, the size of the AI models can be reduced significantly, ensuring optimal performance. Eight different pruning techniques (i) differential evolution (DE), (ii) genetic algorithm (GA), (iii) particle swarm optimization algorithm (PSO), and (iv) whale optimization algorithm (WO) in two deep learning frameworks (i) Fully connected network (FCN) and (ii) SegNet were designed. COVLIAS 2.0 was validated using "Unseen NovMed" and benchmarked against MedSeg. Statistical tests for stability and reliability were also conducted.Pruning algorithms (i) FCN-DE, (ii) FCN-GA, (iii) FCN-PSO, and (iv) FCN-WO showed improvement in storage by 92.4%, 95.3%, 98.7%, and 99.8% respectively when compared against solo FCN, and (v) SegNet-DE, (vi) SegNet-GA, (vii) SegNet-PSO, and (viii) SegNet-WO showed improvement by 97.1%, 97.9%, 98.8%, and 99.2% respectively when compared against solo SegNet. AUC > 0.94 (p 0.86 (p < 0.0001) on NovMed data set for all eight EA model. PAI <0.25 s per image. DenseNet-121-based Grad-CAM heatmaps showed validation on glass ground opacity lesions.Eight PAI networks that were successfully validated are five times faster, storage efficient, and could be used in clinical settings.

  • Open Access English
    Authors: 
    Suri Jasjit S.; Agarwal Sushant; Chabert Gian Luca; Carriero Alessandro; Paschè Alessio; Danna Pietro S. C.; Saba Luca; Mehmedovic Armin; Faa Gavino; Singh Inder M.; +5 more
    Country: Hungary

    The previous COVID-19 lung diagnosis system lacks both scientific validation and the role of explainable artificial intelligence (AI) for understanding lesion localization. This study presents a cloud-based explainable AI, the "COVLIAS 2.0-cXAI" system using four kinds of class activation maps (CAM) models.Our cohort consisted of ~6000 CT slices from two sources (Croatia, 80 COVID-19 patients and Italy, 15 control patients). COVLIAS 2.0-cXAI design consisted of three stages: (i) automated lung segmentation using hybrid deep learning ResNet-UNet model by automatic adjustment of Hounsfield units, hyperparameter optimization, and parallel and distributed training, (ii) classification using three kinds of DenseNet (DN) models (DN-121, DN-169, DN-201), and (iii) validation using four kinds of CAM visualization techniques: gradient-weighted class activation mapping (Grad-CAM), Grad-CAM++, score-weighted CAM (Score-CAM), and FasterScore-CAM. The COVLIAS 2.0-cXAI was validated by three trained senior radiologists for its stability and reliability. The Friedman test was also performed on the scores of the three radiologists.The ResNet-UNet segmentation model resulted in dice similarity of 0.96, Jaccard index of 0.93, a correlation coefficient of 0.99, with a figure-of-merit of 95.99%, while the classifier accuracies for the three DN nets (DN-121, DN-169, and DN-201) were 98%, 98%, and 99% with a loss of ~0.003, ~0.0025, and ~0.002 using 50 epochs, respectively. The mean AUC for all three DN models was 0.99 (p < 0.0001). The COVLIAS 2.0-cXAI showed 80% scans for mean alignment index (MAI) between heatmaps and gold standard, a score of four out of five, establishing the system for clinical settings.The COVLIAS 2.0-cXAI successfully showed a cloud-based explainable AI system for lesion localization in lung CT scans.

  • Open Access English
    Authors: 
    Kupai Krisztina; Várkonyi Tamás; Török Szilvia; Gáti Viktória; Czimmerer Zsolt; Puskás László; Szebeni Gábor;
    Country: Hungary

    Type 2 diabetes mellitus (T2DM) is one of the world’s leading causes of death and life-threatening conditions. Therefore, we review the complex vicious circle of causes responsible for T2DM and risk factors such as the western diet, obesity, genetic predisposition, environmental factors, and SARS-CoV-2 infection. The prevalence and economic burden of T2DM on societal and healthcare systems are dissected. Recent progress on the diagnosis and clinical management of T2DM, including both non-pharmacological and latest pharmacological treatment regimens, are summarized. The treatment of T2DM is becoming more complex as new medications are approved. This review is focused on the non-insulin treatments of T2DM to reach optimal therapy beyond glycemic management. We review experimental and clinical findings of SARS-CoV-2 risks that are attributable to T2DM patients. Finally, we shed light on the recent single-cell-based technologies and multi-omics approaches that have reached breakthroughs in the understanding of the pathomechanism of T2DM.

  • Open Access English
    Authors: 
    Tekeli Tamás; Dénes Attila; Röst Gergely;
    Country: Hungary
  • Open Access English
    Authors: 
    Achim Alexandru; Kákonyi Kornél; Jambrik Zoltán; Ruzsa Zoltán;
    Country: Hungary

    Several coronavirus disease-19 (COVID-19)-associated complications are being increasingly reported, including arterial and venous thrombo-embolic events that may lead to amputation of the affected limbs. So far, acute upper limb ischaemia (ULI) has been reported only in critically ill patients.Herein, we aimed to present a case of a 29-year-old, otherwise healthy male volleyball player, with acute ischaemic signs in the upper extremity who was diagnosed with COVID-19 1 month before the ischaemic event. It has been shown that volleyball players experience repetitive stress that involves their hands and, in particular, their fingers. Repetitive trauma can lead to local vascular abnormalities, such as reduced capillarization and lower resting blood flow that can lead to pain and cold digits, but never acute ULI.To our knowledge, this is the first case of such a hypercoagulable synergistic mechanism that leads to a high thrombus burden. Intra-arterial local thrombolysis and percutaneous transluminal angioplasty failed to succeed, and percutaneous large-bore embolectomy with the Indigo Aspiration System (Penumbra Inc., CA, USA) was deemed necessary.

  • Open Access English
    Authors: 
    Szekanecz Zoltán; Balog Attila; Constantin Tamás; Czirják László; Géher Pál; Kovács László; Kumánovics Gábor; Nagy György; Rákóczi Éva; Szamosi Szilvia; +2 more
    Country: Hungary
  • Open Access English
    Authors: 
    Mészáros Enikő; Bodor Attila; Szierer Ádám; Kovács Etelka; Perei Katalin; Tölgyesi Csaba; Bátori Zoltán; Feigl Gábor;
    Country: Hungary
  • Open Access English
    Authors: 
    Folayan, Morenike Oluwatoyin; Ibigbami, Olanrewaju; Brown, Brandon; El Tantawi, Maha; Uzochukwu, Benjamin; Ezechi, Oliver; Aly, Nourhan M.; Abeldaño, Giuliana Florencia; Ara, Eshrat; Ayanore, Martin Amogre; +5 more
    Country: Hungary

    The aim of the study was to assess if there were signifcant diferences in the adoption of COVID-19 risk preventive behaviors and experience of food insecurity by people living with and without HIV in Nigeria. This was a cross-sectional study that recruited a convenience sample of 4471 (20.5% HIV positive) adults in Nigeria. Binary logistic regression analysis was conducted to test the associations between the explanatory variable (HIV positive and non-positive status) and the outcome variables—COVID-19 related behavior changes (physical distancing, isolation/quarantine, working remotely) and food insecurity (hungry but did not eat, cut the size of meals/skip meals) controlling for age, sex at birth, COVID-19 status, and medical status of respondents. Signifcantly fewer people living with HIV (PLWH) reported a positive COVID-19 test result; and had lower odds of practicing COVID-19 risk preventive behaviors. In comparison with those living without HIV, PLWH had higher odds of cutting meal sizes as a food security measure (AOR: 3.18; 95% CI 2.60–3.88) and lower odds of being hungry and not eating (AOR: 0.24; 95% CI 0.20–0.30). In conclusion, associations between HIV status, COVID-19 preventive behaviors and food security are highly complex and warrant further in-depth to unravel the incongruities identifed.

  • Open Access English
    Authors: 
    Hudak, Anett; Veres, Gábor; Letoha, Annamária; Szilák, László; Letoha, Tamás;
    Country: Hungary
Advanced search in Research products
Research products
arrow_drop_down
Searching FieldsTerms
Any field
arrow_drop_down
includes
arrow_drop_down
Include:
The following results are related to COVID-19. Are you interested to view more results? Visit OpenAIRE - Explore.
18 Research products, page 1 of 2
  • Open Access English
    Authors: 
    Nzimande Ntombifuthi P.; El Tantawi Maha; Zuñiga Roberto Ariel Abeldaño; Opoku-Sarkodie Richmond; Brown Brandon; Ezechi Oliver C.; Uzochukwu Benjamin S. C.; Ellakany Passent; Aly Nourhan M.; Nguyen Annie Lu; +1 more
    Country: Hungary
  • Open Access English
    Authors: 
    Agarwal Mohit; Agarwal Sushant; Saba Luca; Chabert Gian Luca; Gupta Suneet; Carriero Alessandro; Pasche Alessio; Danna Pietro; Mehmedovic Armin; Faa Gavino; +6 more
    Country: Hungary

    COVLIAS 1.0: an automated lung segmentation was designed for COVID-19 diagnosis. It has issues related to storage space and speed. This study shows that COVLIAS 2.0 uses pruned AI (PAI) networks for improving both storage and speed, wiliest high performance on lung segmentation and lesion localization.ology: The proposed study uses multicenter ∼9,000 CT slices from two different nations, namely, CroMed from Croatia (80 patients, experimental data), and NovMed from Italy (72 patients, validation data). We hypothesize that by using pruning and evolutionary optimization algorithms, the size of the AI models can be reduced significantly, ensuring optimal performance. Eight different pruning techniques (i) differential evolution (DE), (ii) genetic algorithm (GA), (iii) particle swarm optimization algorithm (PSO), and (iv) whale optimization algorithm (WO) in two deep learning frameworks (i) Fully connected network (FCN) and (ii) SegNet were designed. COVLIAS 2.0 was validated using "Unseen NovMed" and benchmarked against MedSeg. Statistical tests for stability and reliability were also conducted.Pruning algorithms (i) FCN-DE, (ii) FCN-GA, (iii) FCN-PSO, and (iv) FCN-WO showed improvement in storage by 92.4%, 95.3%, 98.7%, and 99.8% respectively when compared against solo FCN, and (v) SegNet-DE, (vi) SegNet-GA, (vii) SegNet-PSO, and (viii) SegNet-WO showed improvement by 97.1%, 97.9%, 98.8%, and 99.2% respectively when compared against solo SegNet. AUC > 0.94 (p 0.86 (p < 0.0001) on NovMed data set for all eight EA model. PAI <0.25 s per image. DenseNet-121-based Grad-CAM heatmaps showed validation on glass ground opacity lesions.Eight PAI networks that were successfully validated are five times faster, storage efficient, and could be used in clinical settings.

  • Open Access English
    Authors: 
    Suri Jasjit S.; Agarwal Sushant; Chabert Gian Luca; Carriero Alessandro; Paschè Alessio; Danna Pietro S. C.; Saba Luca; Mehmedovic Armin; Faa Gavino; Singh Inder M.; +5 more
    Country: Hungary

    The previous COVID-19 lung diagnosis system lacks both scientific validation and the role of explainable artificial intelligence (AI) for understanding lesion localization. This study presents a cloud-based explainable AI, the "COVLIAS 2.0-cXAI" system using four kinds of class activation maps (CAM) models.Our cohort consisted of ~6000 CT slices from two sources (Croatia, 80 COVID-19 patients and Italy, 15 control patients). COVLIAS 2.0-cXAI design consisted of three stages: (i) automated lung segmentation using hybrid deep learning ResNet-UNet model by automatic adjustment of Hounsfield units, hyperparameter optimization, and parallel and distributed training, (ii) classification using three kinds of DenseNet (DN) models (DN-121, DN-169, DN-201), and (iii) validation using four kinds of CAM visualization techniques: gradient-weighted class activation mapping (Grad-CAM), Grad-CAM++, score-weighted CAM (Score-CAM), and FasterScore-CAM. The COVLIAS 2.0-cXAI was validated by three trained senior radiologists for its stability and reliability. The Friedman test was also performed on the scores of the three radiologists.The ResNet-UNet segmentation model resulted in dice similarity of 0.96, Jaccard index of 0.93, a correlation coefficient of 0.99, with a figure-of-merit of 95.99%, while the classifier accuracies for the three DN nets (DN-121, DN-169, and DN-201) were 98%, 98%, and 99% with a loss of ~0.003, ~0.0025, and ~0.002 using 50 epochs, respectively. The mean AUC for all three DN models was 0.99 (p < 0.0001). The COVLIAS 2.0-cXAI showed 80% scans for mean alignment index (MAI) between heatmaps and gold standard, a score of four out of five, establishing the system for clinical settings.The COVLIAS 2.0-cXAI successfully showed a cloud-based explainable AI system for lesion localization in lung CT scans.

  • Open Access English
    Authors: 
    Kupai Krisztina; Várkonyi Tamás; Török Szilvia; Gáti Viktória; Czimmerer Zsolt; Puskás László; Szebeni Gábor;
    Country: Hungary

    Type 2 diabetes mellitus (T2DM) is one of the world’s leading causes of death and life-threatening conditions. Therefore, we review the complex vicious circle of causes responsible for T2DM and risk factors such as the western diet, obesity, genetic predisposition, environmental factors, and SARS-CoV-2 infection. The prevalence and economic burden of T2DM on societal and healthcare systems are dissected. Recent progress on the diagnosis and clinical management of T2DM, including both non-pharmacological and latest pharmacological treatment regimens, are summarized. The treatment of T2DM is becoming more complex as new medications are approved. This review is focused on the non-insulin treatments of T2DM to reach optimal therapy beyond glycemic management. We review experimental and clinical findings of SARS-CoV-2 risks that are attributable to T2DM patients. Finally, we shed light on the recent single-cell-based technologies and multi-omics approaches that have reached breakthroughs in the understanding of the pathomechanism of T2DM.

  • Open Access English
    Authors: 
    Tekeli Tamás; Dénes Attila; Röst Gergely;
    Country: Hungary
  • Open Access English
    Authors: 
    Achim Alexandru; Kákonyi Kornél; Jambrik Zoltán; Ruzsa Zoltán;
    Country: Hungary

    Several coronavirus disease-19 (COVID-19)-associated complications are being increasingly reported, including arterial and venous thrombo-embolic events that may lead to amputation of the affected limbs. So far, acute upper limb ischaemia (ULI) has been reported only in critically ill patients.Herein, we aimed to present a case of a 29-year-old, otherwise healthy male volleyball player, with acute ischaemic signs in the upper extremity who was diagnosed with COVID-19 1 month before the ischaemic event. It has been shown that volleyball players experience repetitive stress that involves their hands and, in particular, their fingers. Repetitive trauma can lead to local vascular abnormalities, such as reduced capillarization and lower resting blood flow that can lead to pain and cold digits, but never acute ULI.To our knowledge, this is the first case of such a hypercoagulable synergistic mechanism that leads to a high thrombus burden. Intra-arterial local thrombolysis and percutaneous transluminal angioplasty failed to succeed, and percutaneous large-bore embolectomy with the Indigo Aspiration System (Penumbra Inc., CA, USA) was deemed necessary.

  • Open Access English
    Authors: 
    Szekanecz Zoltán; Balog Attila; Constantin Tamás; Czirják László; Géher Pál; Kovács László; Kumánovics Gábor; Nagy György; Rákóczi Éva; Szamosi Szilvia; +2 more
    Country: Hungary
  • Open Access English
    Authors: 
    Mészáros Enikő; Bodor Attila; Szierer Ádám; Kovács Etelka; Perei Katalin; Tölgyesi Csaba; Bátori Zoltán; Feigl Gábor;
    Country: Hungary
  • Open Access English
    Authors: 
    Folayan, Morenike Oluwatoyin; Ibigbami, Olanrewaju; Brown, Brandon; El Tantawi, Maha; Uzochukwu, Benjamin; Ezechi, Oliver; Aly, Nourhan M.; Abeldaño, Giuliana Florencia; Ara, Eshrat; Ayanore, Martin Amogre; +5 more
    Country: Hungary

    The aim of the study was to assess if there were signifcant diferences in the adoption of COVID-19 risk preventive behaviors and experience of food insecurity by people living with and without HIV in Nigeria. This was a cross-sectional study that recruited a convenience sample of 4471 (20.5% HIV positive) adults in Nigeria. Binary logistic regression analysis was conducted to test the associations between the explanatory variable (HIV positive and non-positive status) and the outcome variables—COVID-19 related behavior changes (physical distancing, isolation/quarantine, working remotely) and food insecurity (hungry but did not eat, cut the size of meals/skip meals) controlling for age, sex at birth, COVID-19 status, and medical status of respondents. Signifcantly fewer people living with HIV (PLWH) reported a positive COVID-19 test result; and had lower odds of practicing COVID-19 risk preventive behaviors. In comparison with those living without HIV, PLWH had higher odds of cutting meal sizes as a food security measure (AOR: 3.18; 95% CI 2.60–3.88) and lower odds of being hungry and not eating (AOR: 0.24; 95% CI 0.20–0.30). In conclusion, associations between HIV status, COVID-19 preventive behaviors and food security are highly complex and warrant further in-depth to unravel the incongruities identifed.

  • Open Access English
    Authors: 
    Hudak, Anett; Veres, Gábor; Letoha, Annamária; Szilák, László; Letoha, Tamás;
    Country: Hungary