A5085369510- Cardiac Imaging and Diagnostics
- Advanced MRI Techniques and Applications
- Medical Image Segmentation Techniques
- Medical Imaging Techniques and Applications
- Cerebrovascular and Carotid Artery Diseases
- Coronary Interventions and Diagnostics
- ECG Monitoring and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Non-Invasive Vital Sign Monitoring
- COVID-19 diagnosis using AI
- Optical Coherence Tomography Applications
- Cardiovascular Function and Risk Factors
- Cardiovascular Health and Disease Prevention
- Advanced X-ray and CT Imaging
- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare
- Heart Rate Variability and Autonomic Control
- Biomedical Text Mining and Ontologies
- Digital Radiography and Breast Imaging
- Metal Forming Simulation Techniques
- Cardiac Valve Diseases and Treatments
- Electronic Health Records Systems
- Retinal Imaging and Analysis
- Metallurgy and Material Forming
- Medical Imaging and Analysis
Universidade de São Paulo
2014-2024
Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo
2001-2024
Hospital do Coração
2002-2024
Hospital São Paulo
2023
Hospital Universitário da Universidade de São Paulo
1989-2023
Instituto do Coração
2001-2022
Universidade Federal do ABC
2022
NYU Langone Health
2022
Weatherford College
2021
Informatica (South Korea)
2021
Each year, about 500 natural disasters kill approximately 70,000 people and affect more than 200 million worldwide. In the aftermath of such events, large quantities supplies are needed to provide relief aid affected. CARE International is one largest humanitarian organizations that disaster survivors. The most vital issues in response agility mobilizing effectiveness distributing them. To improve response, a research group from Georgia Institute Technology collaborated with develop model...
Coronavirus disease (COVID-19) survivors exhibit multisystemic alterations after hospitalization. Little is known about long-term imaging and pulmonary function of hospitalized patients intensive care unit (ICU) who survive COVID-19. We aimed to investigate consequences COVID-19 on the respiratory system discharged from hospital ICU identify risk factors associated with chest computed tomography (CT) lesion severity.A prospective cohort study admitted a tertiary in Brazil...
Pneumonia is one of the leading causes childhood mortality worldwide. Chest X-ray (CXR) can aid diagnosis pneumonia, but in case low contrast images, it important to include computational tools specialists. Deep learning an alternative because identify patterns automatically, even low-resolution images. We propose herein a convolutional neural network (CNN) architecture with different training strategies towards detecting pneumonia on CXRs and distinguishing its subforms bacteria virus. also...
The Electrocardiogram (ECG) is a low-cost exam commonly used to diagnose abnormalities in the cardiac cycle. Over years, scientific community has investigated automatic classification of ECG signals driven by advanced Machine Learning (ML) techniques. Despite recent advances, annotating large and diverse datasets support training ML techniques still very time-consuming error-prone. Indeed, whose does not require extensive well-annotated are becoming even more prominent. Therefore, it...
COVID-19 lung sequelae can impact the course of patient lives. We investigated evolution pulmonary abnormalities in post-COVID-19 patients 18-24 months after hospital discharge.
Abstract Objetive: Hypertension, a leading contributor to cardiovascular morbidity, underscores the need for accurate and continuous blood pressure (BP) monitoring. Photoplethysmography (PPG) emerges as promising approach BP However, precision of estimates derived from PPG signals has been subject ongoing debate, requiring comprehensive evaluation their efficacy. This paper aims provide potentials limitations regarding estimation single-site signals. Approach: We developed calibration-based...
To describe the implementation of a Tele-ICU program during COVID-19 pandemic, as well to and analyze results first four months operation program.This was descriptive observational study program, followed by retrospective analysis clinical data patients with admitted ICUs between April July 2020.The implemented over four-week period proved be feasible pandemic. Participants were trained remotely, had an evidence-based design, objective being standardize care for COVID-19. More than 100,000...
Many applications require storing, managing, and retrieving complex data, such as multidimensional vectors images in databases. In this paper, we propose MIGUE-Sim, a system to quickly execute exact Range kNN similarity queries Postgres. The are expressed following straightforward, SQL-compatible representation seamlessly integrated into the language, whereas executes each query using just native resources of MIGUE-Sim uses Postgres's Cube extension perform faster, GIST R-Tree index...
Carotid vessel ultrasound imaging is a reliable noninvasive technique to measure the arterial morphology. Lumen Diameter (LD), intima-media thickness (IMT) of far wall, and plaque presence can be reliably determined using B-mode ultrasound. In order carotid IMT as well any other more complex quantitative indices morphology, it necessary identify lumen-intima media-adventitia borders in images. this paper we describe an automatic approach LD based on active contour improved by multiresolution...
The objective was to study the response of cortisol and prolactin (PRL) specific stimuli in systemic lupus erythematosus (SLE). We measured insulin-induced hypoglycemia PRL thyrotropin releasing hormone (TRH) seven patients with active untreated SLE ten paired control subjects. All were women regular menstrual cycles. With exception two patients, they had never received corticosteroids before study. basal serum levels (12.5 2.4 μg/dl) (10.7 1.0 ng/ml) group not significantly different from...
Accumulated evidence suggests that prolactin (PRL) is an important immunoregulator and might have a role in the pathogenesis of systemic lupus erythematosus (SLE). Moreover, PRL-like molecule secreted by normal human lymphocytes acts as autocrine growth factor for lymphoproliferation. The objective this study was to explore peptide production peripheral blood mononuclear cells (PBMC) from patients with SLE. We investigated PRL secretion PBMC six female SLE nine subjects (5 women 4 men)....
In this paper we present an approach for creating complete shape representations from a single depth image robot grasping. We introduce algorithms completing partial point clouds based on the analysis of symmetry and extrusion patterns in observed shapes. Identified are used to generate mesh object, which is, turn, grasp planning. The allows robots predict objects include invisible regions into planning step. show that identification patterns, such as extrusions, can be fast generation...
This paper presents the extract-transform-and-load (ETL) process from Electronic Patient Records (ePR) at Heart Institute (InCor) to OMOP Common Data Model (CDM) format. We describe initial database characterization, relational source mappings, selection filters, data transformations and patient de-identification using open-source OHDSI tools SQL scripts. evaluate resulting InCor-CDM by recreating same cohort a previous reference study (over original source) comparing cohorts' descriptive...