Long COVID and the cardiovascular system—elucidating causes and cellular mechanisms in order to develop targeted diagnostic and therapeutic strategies: a joint Scientific Statement of the ESC Working Groups on Cellular Biology of the Heart and Myocardial and Pericardial Diseases

Cardiovascular Research, Год журнала: 2022, Номер 119(2), С. 336 - 356

Опубликована: Июль 25, 2022

Abstract Long COVID has become a world-wide, non-communicable epidemic, caused by long-lasting multiorgan symptoms that endure for weeks or months after SARS-CoV-2 infection already subsided. This scientific document aims to provide insight into the possible causes and therapeutic options available cardiovascular manifestations of long COVID. In addition chronic fatigue, which is common symptom COVID, patients may present with chest pain, ECG abnormalities, postural orthostatic tachycardia, newly developed supraventricular ventricular arrhythmias. Imaging heart vessels provided evidence chronic, post-infectious perimyocarditis consequent left right failure, arterial wall inflammation, microthrombosis in certain patient populations. Better understanding underlying cellular molecular mechanisms will aid development effective treatment strategies its manifestations. A number have been proposed, including those involving direct effects on myocardium, microthrombotic damage endothelium, persistent inflammation. Unfortunately, existing circulating biomarkers, coagulation, inflammatory markers, are not highly predictive either presence outcome when measured 3 infection. Further studies needed understand mechanisms, identify specific guide future preventive treatments address sequelae.

Язык: Английский

---

The Transformation of Healthcare Through AI-Driven Diagnostics

Advances in medical technologies and clinical practice book series, Год журнала: 2024, Номер unknown, С. 250 - 264

Опубликована: Апрель 15, 2024

This chapter delves into the transformative effects of artificial intelligence (AI) on healthcare diagnostics, focusing accuracy, efficiency, and predictability. The thorough analysis is organized around main thematic parts. opens with an informative review AI's role in laying groundwork for understanding how AI technologies, such as machine learning deep learning, transform medical diagnostic processes. history procedures explored, emphasizing transition from old methods to current era AI-driven approaches. Finally, this presents a investigation diagnostics impact healthcare's future. Covering present applications, problems, future possibilities, it adds greater discussion integration healthcare. It emphasizes importance responsible collaborative growth transformational subject.

Язык: Английский

---

Segmentation-Based Classification Deep Learning Model Embedded with Explainable AI for COVID-19 Detection in Chest X-ray Scans

Diagnostics, Год журнала: 2022, Номер 12(9), С. 2132 - 2132

Опубликована: Сен. 2, 2022

Background and Motivation: COVID-19 has resulted in a massive loss of life during the last two years. The current imaging-based diagnostic methods for detection multiclass pneumonia-type chest X-rays are not so successful clinical practice due to high error rates. Our hypothesis states that if we can have segmentation-based classification rate <5%, typically adopted 510 (K) regulatory purposes, system be adapted settings. Method: This study proposes 16 types deep learning-based systems automatic, rapid, precise COVID-19. segmentation networks, namely UNet UNet+, along with eight models, VGG16, VGG19, Xception, InceptionV3, Densenet201, NASNetMobile, Resnet50, MobileNet, were applied select best-suited combination networks. Using cross-entropy function, performance was evaluated by Dice, Jaccard, area-under-the-curve (AUC), receiver operating characteristics (ROC) validated using Grad-CAM explainable AI framework. Results: best performing model UNet, which exhibited accuracy, loss, AUC 96.35%, 0.15%, 94.88%, 90.38%, 0.99 (p-value <0.0001), respectively. UNet+Xception, precision, recall, F1-score, 97.45%, 97.46%, 97.43%, 0.998 outperformed existing models. mean improvement UNet+Xception over all remaining studies 8.27%. Conclusion: is viable option as (error <5%) holds true thus adaptable practice.

Язык: Английский

---

COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans

Diagnostics, Год журнала: 2022, Номер 12(6), С. 1482 - 1482

Опубликована: Июнь 16, 2022

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

Язык: Английский

---

COVID-19 Diagnosis: A Review of Rapid Antigen, RT-PCR and Artificial Intelligence Methods

Bioengineering, Год журнала: 2022, Номер 9(4), С. 153 - 153

Опубликована: Апрель 3, 2022

As of 27 December 2021, SARS-CoV-2 has infected over 278 million persons and caused 5.3 deaths. Since the outbreak COVID-19, different methods, from medical to artificial intelligence, have been used for its detection, diagnosis, surveillance. Meanwhile, fast efficient point-of-care (POC) testing self-testing kits become necessary in fight against COVID-19 assist healthcare personnel governments curb spread virus. This paper presents a review various types detection diagnostic technologies, surveillance approaches that or proposed. The provided this article should be beneficial researchers field health policymakers at large.

Язык: Английский

---

International Union of Angiology (IUA) consensus paper on imaging strategies in atherosclerotic carotid artery imaging: From basic strategies to advanced approaches

Atherosclerosis, Год журнала: 2022, Номер 354, С. 23 - 40

Опубликована: Июнь 28, 2022

Язык: Английский

---

Dual-Source Photon-Counting Computed Tomography—Part I: Clinical Overview of Cardiac CT and Coronary CT Angiography Applications

Journal of Clinical Medicine, Год журнала: 2023, Номер 12(11), С. 3627 - 3627

Опубликована: Май 23, 2023

The photon-counting detector (PCD) is a new computed tomography technology (photon-counting tomography, PCCT) that provides substantial benefits for cardiac and coronary artery imaging. Compared with conventional CT, PCCT has multi-energy capability, increased spatial resolution soft tissue contrast near-null electronic noise, reduced radiation exposure, optimization of the use agents. This promises to overcome several limitations traditional CT angiography (CCT/CCTA) including reduction in blooming artifacts heavy calcified plaques or beam-hardening patients stents, more precise assessment degree stenosis plaque characteristic thanks its better resolution. Another potential application double-contrast agent characterize myocardial tissue. In this current overview existing literature, we describe strengths, limitations, recent applications, promising developments employing CCT.

Язык: Английский

---

Artificial Intelligence in the Differential Diagnosis of Cardiomyopathy Phenotypes

Diagnostics, Год журнала: 2024, Номер 14(2), С. 156 - 156

Опубликована: Янв. 10, 2024

Artificial intelligence (AI) is rapidly being applied to the medical field, especially in cardiovascular domain. AI approaches have demonstrated their applicability detection, diagnosis, and management of several diseases, enhancing disease stratification typing. Cardiomyopathies are a leading cause heart failure life-threatening ventricular arrhythmias. Identifying etiologies fundamental for diagnostic pathway these muscle requiring integration various data, including personal family history, clinical examination, electrocardiography, laboratory investigations, as well multimodality imaging, making diagnosis challenging. In this scenario, has its capability capture subtle connections from multitude multiparametric datasets, enabling discovery hidden relationships data handling more complex tasks than traditional methods. This review aims present comprehensive overview main concepts related subset. Additionally, we existing literature on AI-based models differential cardiomyopathy phenotypes, finally examine advantages limitations approaches.

Язык: Английский

---

Spectral Photon-Counting Computed Tomography: Technical Principles and Applications in the Assessment of Cardiovascular Diseases

Journal of Clinical Medicine, Год журнала: 2024, Номер 13(8), С. 2359 - 2359

Опубликована: Апрель 18, 2024

Spectral Photon-Counting Computed Tomography (SPCCT) represents a groundbreaking advancement in X-ray imaging technology. The core innovation of SPCCT lies its photon-counting detectors, which can count the exact number incoming x-ray photons and individually measure their energy. first part this review summarizes key elements technology, such as energy binning, weighting, material decomposition. Its energy-discriminating ability to increase contrast between different tissues, elimination electronic noise, correction beam-hardening artifacts. Material decomposition provides valuable insights into specific elements’ composition, concentration, distribution. capability operate three or more regimes allows for differentiation several agents, facilitating quantitative assessments with thresholds within diagnostic range. second brief overview applications assessment various cardiovascular disease processes. support study myocardial blood perfusion enable enhanced tissue characterization identification manner that was previously unattainable.

Язык: Английский

---

Cardiovascular Applications of Photon-Counting CT Technology: A Revolutionary New Diagnostic Step

Journal of Cardiovascular Development and Disease, Год журнала: 2023, Номер 10(9), С. 363 - 363

Опубликована: Авг. 25, 2023

Photon-counting computed tomography (PCCT) is an emerging technology that can potentially transform clinical CT imaging. After a brief description of the PCCT technology, this review summarizes its main advantages over conventional CT: improved spatial resolution, signal and contrast behavior, reduced electronic noise artifacts, decreased radiation dose, multi-energy capability with material discrimination. Moreover, by providing overview existing literature, highlights how benefits have been harnessed to enhance broaden diagnostic capabilities for cardiovascular applications, including detection coronary artery calcifications, evaluation plaque extent composition, stents, assessment myocardial tissue characteristics perfusion.

Язык: Английский

---