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
Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    Miguel Coimbra
  • Cargo

    Coordenador de TEC4
  • Desde

    15 setembro 1998
  • Nacionalidade

    Portugal
  • Contactos

    +351222094106
    miguel.coimbra@inesctec.pt
003
Publicações

2022

The CirCor DigiScope Dataset: From Murmur Detection to Murmur Classification

Autores
Oliveira, J; Renna, F; Costa, PD; Nogueira, M; Oliveira, C; Ferreira, C; Jorge, A; Mattos, S; Hatem, T; Tavares, T; Elola, A; Rad, AB; Sameni, R; Clifford, GD; Coimbra, MT;

Publicação
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS

Abstract

2022

Artificial Intelligence for Upper Gastrointestinal Endoscopy: A Roadmap from Technology Development to Clinical Practice

Autores
Renna, F; Martins, M; Neto, A; Cunha, A; Libanio, D; Dinis-Ribeiro, M; Coimbra, M;

Publicação
DIAGNOSTICS

Abstract
Stomach cancer is the third deadliest type of cancer in the world (0.86 million deaths in 2017). In 2035, a 20% increase will be observed both in incidence and mortality due to demographic effects if no interventions are foreseen. Upper GI endoscopy (UGIE) plays a paramount role in early diagnosis and, therefore, improved survival rates. On the other hand, human and technical factors can contribute to misdiagnosis while performing UGIE. In this scenario, artificial intelligence (AI) has recently shown its potential in compensating for the pitfalls of UGIE, by leveraging deep learning architectures able to efficiently recognize endoscopic patterns from UGIE video data. This work presents a review of the current state-of-the-art algorithms in the application of AI to gastroscopy. It focuses specifically on the threefold tasks of assuring exam completeness (i.e., detecting the presence of blind spots) and assisting in the detection and characterization of clinical findings, both gastric precancerous conditions and neoplastic lesion changes. Early and promising results have already been obtained using well-known deep learning architectures for computer vision, but many algorithmic challenges remain in achieving the vision of AI-assisted UGIE. Future challenges in the roadmap for the effective integration of AI tools within the UGIE clinical practice are discussed, namely the adoption of more robust deep learning architectures and methods able to embed domain knowledge into image/video classifiers as well as the availability of large, annotated datasets.

2022

The robustness of Random Forest and Support Vector Machine Algorithms to a Faulty Heart Sound Segmentation

Autores
Oliveira, J; Nogueira, DM; Ferreira, CA; Jorge, AM; Coimbra, MT;

Publicação
44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society, EMBC 2022, Glasgow, Scotland, United Kingdom, July 11-15, 2022

Abstract

2022

Identifying the determinants and understanding their effect on the perception of safety, security, and comfort by pedestrians and cyclists: A systematic review

Autores
Ferreira, MC; Costa, PD; Abrantes, D; Hora, J; Felicio, S; Coimbra, M; Dias, TG;

Publicação
TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR

Abstract
The continuous growth of the world population and its agglomeration in urban cities, demand an increasing need for mobility, which in turn contributes to the worsening of traffic congestion and pollution in cities. Therefore, it is necessary to promote active travel, such as walking and cycling. However, this is not an easy task, as pedestrians and cyclists are the most vulnerable link in the system, and low levels of safety, security and comfort can contribute to choosing private cars over active travel. Hence, it is essential to understand the determinants that affect the perceptions of pedestrians and cyclists, in order to support the definition of policies that promote the use of active modes of transport. Thus, this article fills an important gap in the literature by identifying and discussing the objective and subjective determinants that affect the perceptions of safety, security and comfort of pedestrians and cyclists, through a systematic review of the literature published in the last ten years. It followed the PRISMA statement guidelines and checklist, resulting in 68 relevant articles that were carefully analyzed. The results show that the perception of safety is negatively affected by fear of traffic-related injuries, fear of falling related to infra-structure and infrastructure maintenance, and negative behavior of drivers. Regarding security, crime was the major concern of pedestrians and cyclists, either with emphasis on the person or on personal property. With regard to comfort, high levels of air and noise pollution, lack of vege-tation, bad weather conditions, slopes and long commuting distances negatively affected the users' perception. The results also suggest that poor lighting affects all domains, providing a negative perception of safety, security and comfort. Similarly, the presence of people is seen as negatively influencing the perception of safety and comfort, while the absence of people nega-tively impacts the perception of security. Therefore, the findings achieved by this study are key to assist in the definition of transport policies and infrastructure creation in large smart cities. Additionally, new transport policies are proposed and discussed.

2022

Supervised and semi-supervised training of deep convolutional neural networks for gastric landmark detection

Autores
Lopes, I; Silva, A; Coimbra, MT; Ribeiro, MD; Libânio, D; Renna, F;

Publicação
44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society, EMBC 2022, Glasgow, Scotland, United Kingdom, July 11-15, 2022

Abstract

Teses
supervisionadas

2020

Diagnosis of Rheumatic Heart Diseases based in Phonocardiograms and Echocardiograms

Autor
Diogo Marcelo Esterlita Nogueira

Instituição
UP-FCUP

2020

Criação de algoritmos de Deep Learning para identificação de tecidos nas histeroscopias

Autor
Ana Sofia Ferreira Martins

Instituição
UP-FCUP

2020

Changing Perspectives: Interlead Conversion in Electrocardiographic Signals

Autor
Carolina Martins Barbosa Rodrigues Afonso

Instituição
UP-FCUP

2019

Deep Learning techniques in Object Recognition

Autor
Nuno Miguel Santos Marques

Instituição
UP-FCUP

2019

Real-time analysis of vital sign signals for online health monitoring in Unsupervised environments

Autor
Can Ye

Instituição
UP-FCUP