A5023172800- Phonocardiography and Auscultation Techniques
- ECG Monitoring and Analysis
- Music and Audio Processing
- Healthcare Technology and Patient Monitoring
- Electronic Health Records Systems
- Machine Learning in Healthcare
- Spectroscopy and Chemometric Analyses
- Radiomics and Machine Learning in Medical Imaging
- EEG and Brain-Computer Interfaces
- AI in cancer detection
- Currency Recognition and Detection
- Biomedical Text Mining and Ontologies
- Nursing Diagnosis and Documentation
INESC TEC
2017-2025
Universidade do Porto
2021-2025
Centro de Genética Clínica
2024
Instituto Superior de Engenharia do Porto
2019
Polytechnic Institute of Porto
2019
Cardiac auscultation is one of the most cost-effective techniques used to detect and identify many heart conditions. Computer-assisted decision systems based on can support physicians in their decisions. Unfortunately, application such clinical trials still minimal since them only aim presence extra or abnormal waves phonocardiogram signal, i.e., a binary ground truth variable (normal vs abnormal) provided. This mainly due lack large publicly available datasets, where more detailed...
Cardiac auscultation is the key exam to screen cardiac diseases both in developed and developing countries. A heart sound procedure can detect presence of murmurs point a diagnosis, thus it an important first-line assessment also cost-effective tool. The design automatic recommendation systems based on play role boosting accuracy pervasiveness screening tools. One such as step, consists detecting fundamental states, process known segmentation. faulty segmentation or wrong estimation rate...
Cardiac auscultation is the key screening procedure to detect and identify cardiovascular diseases (CVDs). One of many steps automatically CVDs using auscultation, concerns detection delimitation heart sound boundaries, a process known as segmentation. Whether include or not segmentation step in signal classification pipeline nowadays topic discussion. Up our knowledge, outcome algorithm has been used almost exclusively align different segments according heartbeat. In this paper, need for...
Recently, soft attention mechanisms have been successfully used in a wide variety of applications such as the generation image captions, text translation, etc. This mechanism attempts to mimic visual cortex human brain by not analyzing all objects scene equally, but looking for clues (or salient features) which might give more compact representation environment. In doing so, can process information quickly and without overloading. Having learned this lesson, paper, we try make bridge from...
Physiological signals, such as the electrocardiogram and phonocardiogram are very often corrupted by noisy sources. Usually, artificial intelligent algorithms analyze signal regardless of its quality. On other hand, physicians use a completely orthogonal strategy. They do not assess entire recording, instead they search for segment where fundamental abnormal waves easily detected, only then prognostic is attempted. Inspired this fact, new algorithm that automatically selects an optimal...
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 methodology that simultaneously selects optimal processing region physiological and determines decoding into state sequence physiologically meaningful events. Our approach comprises two...