Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Sobre
Download foto HD

Sobre

Nasci no Porto, Portugal, em agosto de 1988. Conclui o Mestrado Integrado em Bioengenharia - Engenharia Biomédica, da Faculdade de Engenharia da Universidade do Porto, Portugal, em 2012, onde neste momento estou a trabalhar num projecto de doutoramento em engenharia biomédica. O objectivo do projecto é a contribuição para a caracterização das alterações motoras, nomeadamente da marcha, numa doença neurologica rara, a Polineuropatia Amiloidotica Familiar. O trabalho está a ser desenvolvido sob orientação do Professor João Paulo Silva Cunha, no C-BER.

Tópicos
de interesse
Detalhes

Detalhes

001
Publicações

2021

Supporting the Assessment of Hereditary Transthyretin Amyloidosis Patients Based On 3-D Gait Analysis and Machine Learning

Autores
Vilas-Boas, MdC; Rocha, AP; Cardoso, MN; Fernandes, JM; Coelho, T; Cunha, JPS;

Publicação
IEEE Transactions on Neural Systems and Rehabilitation Engineering

Abstract

2021

Video-EEG and PerceptTM PC Deep Brain Neurostimulator Fine-Grained Synchronization for Multimodal Neurodata Analysis

Autores
Lopes, EM; Vilas Boas, MD; Rego, R; Santos, A; Cunha, JPS;

Publicação
2021 10TH INTERNATIONAL IEEE/EMBS CONFERENCE ON NEURAL ENGINEERING (NER)

Abstract
Adaptive Deep Brain Stimulation has recently emerged to tackle conventional DBS limitations by measuring disease fluctuations and to adapt stimulation parameter accordingly. In early 2020, Medtronic launched in the European Union the first certified DBS neurostimulator capable of simultaneously stimulate and read signals from the deep brain structures, the PerceptTMPC. In epilepsy, the most common target brain structure is the Anterior Nucleus of Thalamus and the Local Field Potentials analysis requires prior synchronization of data recorded from the Percept PC with video-Electroencephalography (vEEG) equipment. Fine-grained synchronization (sub-second resolution) is mandatory for multimodal neurodata analysis and may be achieved by aligning artefacts perceived in both systems. In this work we study two methods aiming for neurodata streams clock synchronization: one based on DBS stimulation artefacts and another on tapping maneuver artefacts. For this purpose, we studied the data collected from the first epileptic patient that underwent 1-week vEEG-PerceptTMPC monitoring at a Hospital monitoring unit. We found that tapping maneuver-based methodology allowed a more accurate synchronization in relation to the stimulation artefact-based method (0.56s vs. 2.07s absolute average uncertainty). This method was also more complete one since tapping timestamps can be determined by video timeframes and do not require a prior identification of artefacts in EEG data by clinicians.

2021

Supporting the Assessment of Hereditary Transthyretin Amyloidosis Patients Based On 3-D Gait Analysis and Machine Learning

Autores
Vilas Boas, MD; Rocha, AP; Cardoso, MN; Fernandes, JM; Coelho, T; Cunha, JPS;

Publicação
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING

Abstract
Hereditary Transthyretin Amyloidosis (vATTR-V30M) is a rare and highly incapacitating sensorimotor neuropathy caused by an inherited mutation (Val30Met), which typically affects gait, among other symptoms. In this context, we investigated the possibility of using machine learning (ML) techniques to build a model(s) that can be used to support the detection of the Val30Met mutation (possibility of developing the disease), as well as symptom onset detection for the disease, given the gait characteristics of a person. These characteristics correspond to 24 gait parameters computed from 3-D body data, provided by a Kinect v2 camera, acquired from a person while walking towards the camera. To build the model(s), different ML algorithms were explored: k-nearest neighbors, decision tree, random forest, support vector machines (SVM), and multilayer perceptron. For a dataset corresponding to 66 subjects (25 healthy controls, 14 asymptomatic mutation carriers, and 27 patients) and several gait cycles per subject, we were able to obtain a model that distinguishes between controls and vATTR-V30M mutation carriers (with or without symptoms) with a mean accuracy of 92% (SVM). We also obtained a model that distinguishes between asymptomatic and symptomatic carriers with a mean accuracy of 98% (SVM). These results are very relevant, since this is the first study that proposes a ML approach to support vATTR-V30M patient assessment based on gait, being a promising foundation for the development of a computer-aided diagnosis tool to help clinicians in the identification and follow-up of this disease. Furthermore, the proposed method may also be used for other neuropathies.

2020

Subject Identification Based on Gait Using a RGB-D Camera

Autores
Rocha, AP; Fernandes, JM; Choupina, HMP; Vilas Boas, MC; Cunha, JPS;

Publicação
Advances in Intelligent Systems and Computing

Abstract
Biometric authentication (i.e., verification of a given subject’s identity using biological characteristics) relying on gait characteristics obtained in a non-intrusive way can be very useful in the area of security, for smart surveillance and access control. In this contribution, we investigated the possibility of carrying out subject identification based on a predictive model built using machine learning techniques, and features extracted from 3-D body joint data provided by a single low-cost RGB-D camera (Microsoft Kinect v2). We obtained a dataset including 400 gait cycles from 20 healthy subjects, and 25 anthropometric measures and gait parameters per gait cycle. Different machine learning algorithms were explored: k-nearest neighbors, decision tree, random forest, support vector machines, multilayer perceptron, and multilayer perceptron ensemble. The algorithm that led to the model with best trade-off between the considered evaluation metrics was the random forest: overall accuracy of 99%, class accuracy of 100±Â0%, and F 1 score of 99±Â2%. These results show the potential of using a RGB-D camera for subject identification based on quantitative gait analysis. © 2020, Springer Nature Switzerland AG.

2020

IHandU: A novel quantitative wrist rigidity evaluation device for deep brain stimulation surgery

Autores
Murias Lopes, E; Vilas Boas, MD; Dias, D; Rosas, MJ; Vaz, R; Silva Cunha, JP;

Publicação
Sensors (Switzerland)

Abstract
Deep brain stimulation (DBS) surgery is the gold standard therapeutic intervention in Parkinson’s disease (PD) with motor complications, notwithstanding drug therapy. In the intraoperative evaluation of DBS’s efficacy, neurologists impose a passive wrist flexion movement and qualitatively describe the perceived decrease in rigidity under different stimulation parameters and electrode positions. To tackle this subjectivity, we designed a wearable device to quantitatively evaluate the wrist rigidity changes during the neurosurgery procedure, supporting physicians in decision-making when setting the stimulation parameters and reducing surgery time. This system comprises a gyroscope sensor embedded in a textile band for patient’s hand, communicating to a smartphone via Bluetooth and has been evaluated on three datasets, showing an average accuracy of 80%. In this work, we present a system that has seen four iterations since 2015, improving on accuracy, usability and reliability. We aim to review the work done so far, outlining the iHandU system evolution, as well as the main challenges, lessons learned, and future steps to improve it. We also introduce the last version (iHandU 4.0), currently used in DBS surgeries at São João Hospital in Portugal. © 2020 by the authors.