Cookies Policy
We use cookies to improve our site and your experience. By continuing to browse our site you accept our cookie policy. Find out More
Close
  • Menu
Facts & Numbers
000
Presentation

Biomedical Engineering Research

At C-BER our main goals are the creation of interdisciplinary knowledge enabling innovation and technology transfer with economic impact; and also the development of products, tools and methods for the prevention and early detection of different types of diseases, aging-related impairments, or for human rehabilitation, physical therapy or functional assessment.

We also seek to contribute to the development of advanced neuro-technologies at the frontier of engineering and neurology, and to promote strategic partnerships with clinical partners, research institutes, and fostering international cooperation.

Our R&D activity is developed in three different areas: BioInstrumentation, Biomedical Imaging and NeuroEngineering.

Latest News
Networked Intelligent Systems

INESC TEC develops smart optical technology for the distinction and detection of cancer cells

An article published in one of Nature's scientific journals shows that iLoF (Lab on Fiber) intelligent device is a promising technology to identify cancer cells with different profiles

12th March 2020

Networked Intelligent Systems

«Best Practical Paper Award» for INESC TEC research on retinopathy screening

“EyeWeS: Weakly Supervised Pre-Trained Convolutional Neural Networks for Diabetic Retinopathy Detection” is the title of the scientific article that earned the Best Practical Paper Award at the MVA 2019 (International Conference on Machine Vision Applications) held in Tokyo, Japan.

14th February 2020

Networked Intelligent Systems

INESC TEC has its first patent granted in China

INESC TEC has a patent granted in China for the first time. The accomplishment was achieved with the C4Mir technology ("Control Module for Multiple Mixed-Signal Resources Management"), which had already seen its patent applications be granted in Europe, USA, South Korea and Japan.

30th December 2019

Networked Intelligent Systems

INESC TEC and CHUSJ develop a technology to diagnose pulmonary nodules

INESC TEC and the São João University Hospital (CHUSJ) developed a system for the diagnosis of pulmonary nodules. The innovation has been already tested in the radiology department of that hospital and allows the detection, characterisation and determination of the malignancy of pulmonary nodules.

30th December 2019

Computer Science

INESC TEC article among the most cited articles in the scientific journal PLOS ONE

An INESC TEC paper in the area of medical image analysis is among the 10% most cited papers in the scientific journal PLOS One of 2017. With the participation of researchers from the Centre for Biomedical Engineering Research (C-BER) and the Centre for Telecommunications and Multimedia (CTM), the paper describes a method for automatic classification of histology images of breast tissue biopsy into four classes: normal tissue, with benign lesions, with carcinoma in situ or invasive carcinoma.

18th December 2019

Interest Topics
020

Featured Projects

BioNanoTech

Serviços de apoio técnico - iLoF spin-off

2020-2021

MRI_Simulator

Aluguer do Simulador de Ressonância Magnética à Faculdade de Psicologia e de Ciências da Educação da Universidade do Porto

2019-2020

WalkingPAD

Patient education on a quantified supervised home-based exercise therapy to improve walking ability in patients with peripheral arterial disease and intermittent claudication

2019-2021

Serv_Neuro

Consultoria Insignals Neurotech no âmbito do programa EIT Health Startups Meets Pharma 2019

2019-2019

LUCAS

Lung cancer screening - A non-invasive methodology for early diagnosis

2018-2021

PERFECT

Perceptual equivalence in virtual reality for authentic training

2018-2020

TexBoost

Less Commodities more Specialities

2017-2020

LNDetector

Automatic Detection, Segmentation and Classification of Pulmonary Nodules System in Computed Tomography Images

2016-2019

SCREEN-DR

Image Analysis and Machine Learning Platform for Innovation in Diabetic Retinopathy Screening

2016-2020

Bio-Early

Projeto Vital Sticker no âmbito do Contrato Programa

2015-2018

NanoStima-RL5

NanoSTIMA - Advanced Methodologies for Computer-Aided Detection and Diagnosis

2015-2019

NanoStima-RL1

NanoSTIMA - Macro-to-Nano Human Sensing Technologies

2015-2019

SMILES

SMILES - Smart, Mobile, Intelligent and Large scale Sensing and analytics

2015-2019

VR2Market

VR2Market: Towards a Mobile Wearable Health Surveillance Product for First Response and other Hazardous Professions

2014-2019

STePMotion

Spatio-temporal components of the processing of sensorial and motor information

2014-2015

EcoDrive

Inteligent Eco Driving and Fleet Management

2014-2015

Re-Learning

Human motor re-learning by sensor information fusion

2014-2015

VitalResponder2

Intelligent management of critical events of stress, fatigue and smoke intoxication in forest firefighting

2013-2015

ASD-MD

Movement Disorders in Autistic Spectrum Disorders

2013-2015

HERMES

Interactive system for digital content consumers

2013-2015

Team
003

Laboratories

Biomedical Imaging Laboratory

Neuroengineering and Advanced Human Sensing Laboratory

BioInstrumentation Lab

Publications

C-BER Publications

View all Publications

2019

Using Soft Attention Mechanisms to Classify Heart Sounds

Authors
Oliveira, J; Nogueira, DM; Ramos, C; Renna, F; Ferreira, CA; Coimbra, MT;

Publication
2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

Abstract

2019

Active Contours Based Segmentation and Lesion Periphery Analysis for Characterization of Skin Lesions in Dermoscopy Images

Authors
Riaz, F; Naeem, S; Nawaz, R; Coimbra, M;

Publication
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS

Abstract
This paper proposes a computer assisted diagnostic system for the detection of melanoma in dermoscopy images. Clinical findings have concluded that in case of melanoma, the lesion borders exhibit differential structures such as pigment networks and streaks as opposed to normal skin spots, which have smoother borders. We aim at validating these findings by performing segmentation of the skin lesions followed by an extraction of the peripheral region of the lesion that is subjected to feature extraction and classification for detecting melanoma. For segmentation, we propose a novel active contours based method that takes an initial lesion contour followed by the usage of Kullback-Leibler divergence between the lesion and skin to fit a curve to the lesion boundaries. After segmentation of the lesion, its periphery is extracted to detect melanoma using image features that are based on local binary patterns. For validation of our algorithms, we have used the publicly available PH2 and ISIC dermoscopy datasets. An extensive experimental analysis reveals two important findings: 1) the proposed segmentation method mimics the ground truth data; and 2) the most significant melanoma characteristics in the lesion actually lie on the lesion periphery.

2019

Virtual M-Mode for Echocardiography: A New Approach for the Segmentation of the Anterior Mitral Leaflet

Authors
Sultan, MS; Martins, N; Costa, E; Veiga, D; Ferreira, MJ; Mattos, S; Coimbra, MT;

Publication
IEEE J. Biomedical and Health Informatics

Abstract

2019

A Subject-Driven Unsupervised Hidden Semi-Markov Model and Gaussian Mixture Model for Heart Sound Segmentation

Authors
Oliveira, J; Renna, F; Coimbra, M;

Publication
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING

Abstract
The analysis of heart sounds is a challenging task, due to the quick temporal onset between successive events and the fact that an important fraction of the information carried by phonocardiogram (PCG) signals lies in the inaudible part of the human spectrum. For these reasons, computer-aided analysis of the PCG can dramatically improve the quantity of information recovered from such signals. In this paper, a hidden semi-Markov model (HSMM) is used to automatically segment PCG signals. In the proposed models, the emission probability distributions are approximated via Gaussian mixture model (GMM) priors. The choice of GMM emission probability distributions allow to apply re-estimation routines to automatically adjust the HSMM emission probability distributions to each subject. Building on the proposed method for fine tuning emission distributions, a novel subject-driven unsupervised heart sound segmentation algorithm is proposed and validated over the publicly available PhysioNet dataset. Perhaps surprisingly, the proposed unsupervised method achieved results in line with state-of-the-art supervised approaches, when applied to long heart sounds.

2019

Adaptive Sojourn Time HSMM for Heart Sound Segmentation

Authors
Oliveira, J; Renna, F; Mantadelis, T; Coimbra, M;

Publication
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS

Abstract
Heart sounds are difficult to interpret due to events with very short temporal onset between them (tens of milliseconds) and dominant frequencies that are out of the human audible spectrum. Computer-assisted decision systems may help but they require robust signal processing algorithms. In this paper, we propose a new algorithm for heart sound segmentation using a hidden semi-Markov model. The proposed algorithm infers more suitable sojourn time parameters than those currently suggested by the state of the art, through a maximum likelihood approach. We test our approach over three different datasets, including the publicly available PhysioNet and Pascal datasets. We also release a pediatric dataset composed of 29 heart sounds. In contrast with any other dataset available online, the annotations of the heart sounds in the released dataset contain information about the beginning and the ending of each heart sound event. Annotations were made by two cardiopulmonologists. The proposed algorithm is compared with the current state of the art. The results show a significant increase in segmentation performance, regardless the dataset or the methodology presented. For example, when using the PhysioNet dataset to train and to evaluate the HSMMs, our algorithm achieved average an F-score of 92% compared to 89% achieved by the algorithm described in [D.B. Springer, L. Tarassenko, and G. D. Clifford, "Logistic regressionHSMM-based heart sound segmentation," IEEE Transactions on Biomedical Engineering, vol. 63, no. 4, pp. 822-832, 2016]. In this sense, the proposed approach to adapt sojourn time parameters represents an effective solution for heart sound segmentation problems, even when the training data does not perfectly express the variability of the testing data.

Facts & Figures

32Proceedings in indexed conferences

2018

1Book Chapters

2018

19Papers in indexed journals

2018

Contacts