A5074953921- AI in cancer detection
- Advanced Neuroimaging Techniques and Applications
- Functional Brain Connectivity Studies
- Advanced MRI Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Medical Image Segmentation Techniques
- Industrial Vision Systems and Defect Detection
- Image Retrieval and Classification Techniques
- Gene expression and cancer classification
- Atmospheric and Environmental Gas Dynamics
- dental development and anomalies
- Orthodontics and Dentofacial Orthopedics
- Augmented Reality Applications
- Atmospheric aerosols and clouds
- Advanced Optical Sensing Technologies
- Surface Roughness and Optical Measurements
- Infrared Thermography in Medicine
- Spectroscopy and Laser Applications
- Scientific Computing and Data Management
- Water Quality Monitoring Technologies
- Imbalanced Data Classification Techniques
- Meteorological Phenomena and Simulations
- Aging, Health, and Disability
- 3D Surveying and Cultural Heritage
- Dental Radiography and Imaging
Instituto Politecnico de Setubal
2022-2025
University of Minho
2016-2024
Commissariat à l'Énergie Atomique et aux Énergies Alternatives
2018-2024
CEA Paris-Saclay
2019-2024
Centre d'Acquisition et de Traitement des Images
2024
Cognitive Neuroimaging Lab
2024
Universidad de Guadalajara
2001-2024
Instituto Politécnico Nacional
2024
Centro de Computação Gráfica
2016-2022
Centre National de la Recherche Scientifique
2021-2022
Feature extraction is a fundamental step when mammography image analysis addressed using learning based approaches. Traditionally, problem dependent handcrafted features are used to represent the content of images. An alternative approach successfully applied in other domains use neural networks automatically discover good features. This work presents an evaluation convolutional learn for mass lesions before feeding them classification stage. Experimental results showed that this suitable...
This document describes the aggregation and anonymization process applied to initial version of Google COVID-19 Community Mobility Reports (published at http://google.com/covid19/mobility on April 2, 2020), a publicly available resource intended help public health authorities understand what has changed in response work-from-home, shelter-in-place, other recommended policies aimed flattening curve pandemic. Our is designed ensure that no personal data, including an individual's location,...
Human brain connectivity is extremely complex and variable across subjects. While long association projection bundles are stable have been deeply studied, short present higher inter-subject variability few studies carried out to adequately describe the structure, shape reproducibility of these bundles. However, their analysis crucial in order understand function better characterize human connectome. In this work, we propose an automatic method identify reproducible superficial white matter,...
Human electroencephalogram (EEG) has been divided in bands established by visual inspection that frequently do not correspond with EEG generators nor functional meaning of rhythms. Power spectra from wakefulness, stage 2, 4 and paradoxical sleep 8 young adults were submitted to Principal Component Analyses investigate which frequencies covaried together. Two identical eigenvectors identified for 2 4: 1 Hz 5 15 (87.95 84.62 % the total variance respectively). extracted PS: 9 10 (81.62%...
Orthodontic-induced external apical root resorption (EARR) is a complex phenotype determined by poorly defined mechanical and patient intrinsic factors. The aim of this work was to construct multifactorial integrative model, including clinical genetic susceptibility factors, analyze the risk developing common orthodontic complication.This retrospective study included 195 patients. Using multiple-linear regression where dependent variable maximum% (%EARRmax) for each patient, we assessed...
Visual computing technologies have an important role in manufacturing and production, particularly new Industry 4.0 scenarios with intelligent machines, human-robot collaboration learning factories. In this article, we explore challenges examples on how the fusion of graphics, vision media can enhance operators context.
Nowadays, numerous organisations of different dimensions and business sectors operate in highly challenging dynamic environments, wherein the supporting information systems (IS) are becoming increasingly complex. In this context, assistive tools capable tackling such complexity have potential to aid users improving their performance effectiveness, as well streamline businesses’ processes promote entrepreneurial-level competitivity. Following line research, a web-based speech-to-term...
Fully homomorphic encryption (FHE) is an scheme which enables computation on encrypted data without revealing the underlying data. While there have been many advances in field of FHE, developing programs using FHE still requires expertise cryptography. In this white paper, we present a fully transpiler that allows developers to convert high-level code (e.g., C++) works unencrypted into operates Thus, our makes transformations possible Our builds Google's open-source XLS SDK...
A study was made to examine the suitability of three different micrometeorological methods for estimating evapotranspiration from selected areas native vegetation in west-central Florida and estimate annual those areas. Evapotranspiration estimated using energy- balance Bowen ratio eddy correlation methods. Potential computed Penman equation. The energy-balance method used diurnal evapotrans- piration at unforested sites yielded reasonable results; however, measurements indicated that...
This paper proposed a comprehensive algorithm for building machine learning classifiers Breast Cancer diagnosis based on the suitable combination of feature selection methods that provide high performance over Area Under receiver operating characteristic Curve (AUC). The new developed method allows both exploring and ranking search spaces image-based features, selecting subsets optimal features feeding Machine Learning Classifiers (MLCs). was evaluated using six mammography-based datasets...
Interleukin-1 beta (IL1B) pathway is a key player in orthodontic-induced external apical root resorption (EARR). The aim of this work was to identify the genes related IL1 as possible candidate for EARR, which might be included an integrative predictive model complex phenotype.Using stepwise multiple linear regression model, 195 patients who had undergone orthodontic treatment were assessed clinical and genetic factors associated with %EARRmax (maximum %EARR value obtained each patient)....
Replacing lung cancer as the most commonly diagnosed globally, breast (BC) today accounts for 1 in 8 diagnoses and a total of 2.3 million new cases both sexes combined. An estimated 685,000 women died from BC 2020, corresponding to 16% or every 6 deaths women. represents quarter females by far 2020. However, when detected early stages disease, treatment methods have proven be very effective increasing life expectancy and, many cases, patients fully recover. Several medical imaging...
Historical and cultural building conservation is nowadays limited to high value buildings only receive financial support when serious issues arise. HeritageCARE project willing shift this mentality, towards "prevention better than the cure". New technologies are able such motivation by improving inspector work during their inspection routine. In that regard, mixed reality will be explored offer easy efficient interaction while remaining focused on task at hand. Moreover, integration with...