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

Sobre

Miguel Coimbra, licenciado em Engenharia Eletrotécnica e de Computadores (Faculdade de Engenharia da Universidade do Porto) e doutorado em Engenharia Electrónica (Queen Mary, University of London), é Professor Catedrático no Departamento de Ciência de Computadores da Faculdade de Ciências da Universidade do Porto. É vogal do Conselho Executivo da Faculdade de Ciências da Universidade do Porto desde abril de 2019, coordenador da linha TEC4Health do INESC TEC desde janeiro de 2019, e coordenador do laboratório BioImaging Lab do INESC TEC desde janeiro de 2022. Foi presidente do Portugal Chapter da IEEE Engineering in Medicine and Biology Society entre 2018 e 2022. Foi um dos fundadores em 2007 da Delegação do Porto do Instituto de Telecomunicações, da qual foi coordenador entre 2015 e 2019. Nesta criou e coordenou entre 2008 e 2014 o grupo de Interactive Multimedia. Foi diretor entre 2014 e 2016 do Mestrado em Informática Médica da Universidade do Porto, e co-fundador em 2013 da IS4H – Interactive Systems for Healthcare, uma empresa spin-off da Universidade do Porto, onde licencia e vende produtos baseados nas tecnologias interativas de auscultação desenvolvidas pela sua equipa.

A nível de atividade científica liderou ou participou em múltiplos projetos na interface entre a ciência de computadores e a saúde, nomeadamente em cardiologia, gastroenterologia e reumatologia, com colaborações atuais e passadas com instituições de saúde em Portugal, Brasil (Pernambuco, Paraíba, Minas Gerais, São Paulo), Alemanha e Suécia. Os quase 15 anos de experiência em ciência de computadores, mais concretamente na área da informática para a saúde (visão computacional, processamento de sinal biomédico, interação pessoa-máquina), levaram ao desenvolvimento e instalação de sistemas para a colheita e análise de sinais de auscultação, processamento de imagens de ecocardiografia para rastreio de febre reumática, monitorização de stress e fadiga de bombeiros em ação, análise de imagem endoscópica para deteção de cancro, sistemas de apoio à decisão para cápsula endoscópica, e quantificação de padrões de movimento 3D para epilepsia, entre outros. É (co)-autor de um total de 133 publicações científicas, incluindo 3 capítulos em livros e 29 artigos em revista, sendo 25 destes em revistas de primeiro quartil, 17 dos quais nas prestigiadas IEEE Transactions. A nível de formação avançada já terminou com sucesso a orientação de 4 investigadores de pós-doutoramento, 6 estudantes de doutoramento e 47 estudantes de mestrado. Durante os últimos 13 anos atraiu e geriu mais de 2M€ de financiamento para investigação, distribuídos por um total de 16 projetos nacionais ou internacionais onde atuou como investigador principal do projeto ou como líder da equipa de investigação da sua instituição.


Detalhes

Detalhes

  • Nome

    Miguel Coimbra
  • Cargo

    Coordenador de TEC4
  • Desde

    15 setembro 1998
  • Nacionalidade

    Portugal
  • Contactos

    +351222094106
    miguel.coimbra@inesctec.pt
006
Publicações

2024

Separation of the Aortic and Pulmonary Components of the Second Heart Sound via Alternating Optimization

Autores
Renna, F; Gaudio, A; Mattos, S; Plumbley, MD; Coimbra, MT;

Publicação
IEEE ACCESS

Abstract
An algorithm for blind source separation (BSS) of the second heart sound (S2) into aortic and pulmonary components is proposed. It recovers aortic (A2) and pulmonary (P2) waveforms, as well as their relative delays, by solving an alternating optimization problem on the set of S2 sounds, without the use of auxiliary ECG or respiration phase measurement data. This unsupervised and data-driven approach assumes that the A2 and P2 components maintain the same waveform across heartbeats and that the relative delay between onset of the components varies according to respiration phase. The proposed approach is applied to synthetic heart sounds and to real-world heart sounds from 43 patients. It improves over two state-of-the-art BSS approaches by 10% normalized root mean-squared error in the reconstruction of aortic and pulmonary components using synthetic heart sounds, demonstrates robustness to noise, and recovery of splitting delays. The detection of pulmonary hypertension (PH) in a Brazilian population is demonstrated by training a classifier on three scalar features from the recovered A2 and P2 waveforms, and this yields an auROC of 0.76.

2023

Beyond Heart Murmur Detection: Automatic Murmur Grading From Phonocardiogram

Autores
Elola, A; Aramendi, E; Oliveira, J; Renna, F; Coimbra, MT; Reyna, MA; Sameni, R; Clifford, GD; Rad, AB;

Publicação
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS

Abstract
Objective: Murmurs are abnormal heart sounds, identified by experts through cardiac auscultation. The murmur grade, a quantitative measure of the murmur intensity, is strongly correlated with the patient's clinical condition. This work aims to estimate each patient's murmur grade (i.e., absent, soft, loud) from multiple auscultation location phonocardiograms (PCGs) of a large population of pediatric patients from a low-resource rural area. Methods: The Mel spectrogram representation of each PCG recording is given to an ensemble of 15 convolutional residual neural networks with channel-wise attention mechanisms to classify each PCG recording. The final murmur grade for each patient is derived based on the proposed decision rule and considering all estimated labels for available recordings. The proposed method is cross-validated on a dataset consisting of 3456 PCG recordings from 1007 patients using a stratified ten-fold cross-validation. Additionally, the method was tested on a hidden test set comprised of 1538 PCG recordings from 442 patients. Results: The overall cross-validation performances for patient-level murmur gradings are 86.3% and 81.6% in terms of the unweighted average of sensitivities and F1-scores, respectively. The sensitivities (and F1-scores) for absent, soft, and loud murmurs are 90.7% (93.6%), 75.8% (66.8%), and 92.3% (84.2%), respectively. On the test set, the algorithm achieves an unweighted average of sensitivities of 80.4% and an F1-score of 75.8%. Conclusions: This study provides a potential approach for algorithmic pre-screening in low-resource settings with relatively high expert screening costs. Significance: The proposed method represents a significant step beyond detection of murmurs, providing characterization of intensity, which may provide an enhanced classification of clinical outcomes.

2023

The selection of an optimal segmentation region in physiological signals

Autores
Oliveira, J; Carvalho, M; Nogueira, D; Coimbra, M;

Publicação
INTERNATIONAL TRANSACTIONS IN OPERATIONAL RESEARCH

Abstract
Physiological signals are often corrupted by noisy sources. Usually, artificial intelligence algorithms analyze the whole signal, regardless of its varying quality. Instead, experienced cardiologists search for a high-quality signal segment, where more accurate conclusions can be draw. We propose a methodology that simultaneously selects the optimal processing region of a physiological signal and determines its decoding into a state sequence of physiologically meaningful events. Our approach comprises two phases. First, the training of a neural network that then enables the estimation of the state probability distribution of a signal sample. Second, the use of the neural network output within an integer program. The latter models the problem of finding a time window by maximizing a likelihood function defined by the user. Our method was tested and validated in two types of signals, the phonocardiogram and the electrocardiogram. In phonocardiogram and electrocardiogram segmentation tasks, the system's sensitivity increased on average from 95.1% to 97.5% and from 78.9% to 83.8%, respectively, when compared to standard approaches found in the literature.

2023

Colonoscopic Polyp Detection with Deep Learning Assist

Autores
Neto, A; Couto, D; Coimbra, MT; Cunha, A;

Publicação
Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2023, Volume 4: VISAPP, Lisbon, Portugal, February 19-21, 2023.

Abstract
Colorectal cancer is the third most common cancer and the second cause of cancer-related deaths in the world. Colonoscopic surveillance is extremely important to find cancer precursors such as adenomas or serrated polyps. Identifying small or flat polyps can be challenging during colonoscopy and highly dependent on the colonoscopist's skills. Deep learning algorithms can enable improvement of polyp detection rate and consequently assist to reduce physician subjectiveness and operation errors. This study aims to compare YOLO object detection architecture with self-attention models. In this study, the Kvasir-SEG polyp dataset, composed of 1000 colonoscopy annotated still images, were used to train (700 images) and validate (300images) the performance of polyp detection algorithms. Well-defined architectures such as YOLOv4 and different YOLOv5 models were compared with more recent algorithms that rely on self-attention mechanisms, namely the DETR model, to understand which technique can be more helpful and reliable in clinical practice. In the end, the YOLOv5 proved to be the model achieving better results for polyp detection with 0.81 mAP, however, the DETR had 0.80 mAP proving to have the potential of reaching similar performances when compared to more well-established architectures. © 2023 by SCITEPRESS - Science and Technology Publications, Lda.

2023

Assisted probe guidance in cardiac ultrasound: A review

Autores
Ferraz, S; Coimbra, M; Pedrosa, J;

Publicação
FRONTIERS IN CARDIOVASCULAR MEDICINE

Abstract
Echocardiography is the most frequently used imaging modality in cardiology. However, its acquisition is affected by inter-observer variability and largely dependent on the operator's experience. In this context, artificial intelligence techniques could reduce these variabilities and provide a user independent system. In recent years, machine learning (ML) algorithms have been used in echocardiography to automate echocardiographic acquisition. This review focuses on the state-of-the-art studies that use ML to automate tasks regarding the acquisition of echocardiograms, including quality assessment (QA), recognition of cardiac views and assisted probe guidance during the scanning process. The results indicate that performance of automated acquisition was overall good, but most studies lack variability in their datasets. From our comprehensive review, we believe automated acquisition has the potential not only to improve accuracy of diagnosis, but also help novice operators build expertise and facilitate point of care healthcare in medically underserved areas.

Teses
supervisionadas

2023

Deep Learning Algorithms for Anatomical Landmark Detection

Autor
Miguel Lopes Martins

Instituição
UP-FCUP

2023

Echocardiography Automatic Image Quality Enhancement Using Generative Adversarial Networks

Autor
Teresa Isabel da Silva Corado

Instituição
UP-FEUP

2023

Advising Diabetes’ self-management supported by user data in a mobile platform

Autor
Diogo Roberto de Melo e Diogo Machado

Instituição
UP-FCUP

2023

A Multi-Caller Pipeline to maximize the output of Somatic Exome Sequencing Analysis

Autor
Inês Sofia Pinheiro Marques

Instituição
UP-FCUP

2023

Real time tracking of padel game movements, statistics and points

Autor
João Pedro Andrade Ferreira

Instituição
UP-FCUP