A5025368506- Heart Rate Variability and Autonomic Control
- Non-Invasive Vital Sign Monitoring
- AI in cancer detection
- ECG Monitoring and Analysis
- EEG and Brain-Computer Interfaces
- Blood Pressure and Hypertension Studies
- Radiomics and Machine Learning in Medical Imaging
- Digital Radiography and Breast Imaging
- Cardiovascular and exercise physiology
- Protein Hydrolysis and Bioactive Peptides
- Neural Networks and Applications
- Meat and Animal Product Quality
- Mental Health Research Topics
- Heparin-Induced Thrombocytopenia and Thrombosis
- Advanced Chemical Sensor Technologies
- Medical Image Segmentation Techniques
- Advanced Software Engineering Methodologies
- Cardiovascular Syncope and Autonomic Disorders
- Antiplatelet Therapy and Cardiovascular Diseases
- Fault Detection and Control Systems
- Cardiac electrophysiology and arrhythmias
- Aquaculture Nutrition and Growth
- Cardiac Health and Mental Health
- Cardiovascular Health and Disease Prevention
- Software Engineering Research
Kantonsspital Aarau
2017-2024
Universidade de Vigo
2010-2023
Instituto Nacional de Cardiología
2005-2022
University of Buenos Aires
2022
Consejo Nacional de Investigaciones Científicas y Técnicas
2022
Hospital Universitario de Móstoles
2018
Fundación Renal
2018
Informa (Italy)
2010
Ricardo (United Kingdom)
2009
Inter-American Development Bank
2009
A computerized method to automatically detect malignant masses on digital mammograms based bilateral subtraction identify asymmetries between left and right breast images was developed. After the digitization, in order align border nipple were detected. Images corrected avoid differences brightness due recording procedure. Left subtracted a threshold applied obtain binary image with information of suspicious areas. The regions or delimited by region growing algorithm. Size eccentricity tests...
We have compared three of the best QRS detection algorithms, regarding their results, to check performance and elucidate which get better accuracy. In literature these algorithms were published in a theoretical way, without offering code, so it is difficult its real behaviour over different collections ECG records. This work brings community our source code each algorithm results validation public database. addition, this software was developed as framework order permit inclusion new also...
Background: Burn injuries are a major cause of morbidity and mortality, because the severe local systemic response developed, affecting organics functions. A decline in platelets lymphocyte count compromise immune patient´s outcome. To evaluate usefulness platelet to ratio as biomarker mortality severely burned patients, present research was performed. Methods: descriptive, longitudinal, prospective study carried out at Department Calixto García Hospital, La Habana, from January 2022...
A computerized scheme to detect clustered microcalcifications in digital mammograms has been developed. Detection of individual regions interest (ROIs) was also performed. The were previously classified into fatty and dense, according their breast tissue. most appropriate wavelet basis reconstruction levels selected. To select the basis, 40 profiles decomposed reconstructed using different types functions combinations coefficients. symlets with a length 8 chosen for For dense tissue,...
This paper presents an algorithm for background modeling and foreground detection that uses scaling coefficients, which are defined with a new color model called lightness-red-green-blue (LRGB). They employed to compare two images by finding pixels scaled lightness. Three backgrounds used: 1) verified considered as background; 2) testing tested several times check if they belong the 3) final is combination of (the used in places, where not defined). If pixel matches from previous frames...
This paper proposes a beat detection algorithm specially tailored to be used with 12 channel ECG records. The first obtains positions on each channel, and then combines this information get an improved estimate. process involves two stages: 1) single-channel detection: implemented by improving one of the most popular methods (Pan-Tompkins) developed detect positions; 2) multichannel that obtained in channels. In way, our results clearly improve those method, discarding errors, false...
We have developed a model to simulate clustered microcalcifications on digital mammograms. Wavelet transform techniques were used detect real microcalcifications. A feature analysis process was applied automatically extract the features describing individual simulated and clusters from values of present in mammogram. Subsequently, database created. Clusters this tested for indistinguishability ones. Two radiologists one physicist asked indicate whether either or simulated. The responses...