A5050562159- Functional Brain Connectivity Studies
- Sepsis Diagnosis and Treatment
- Ultrasound in Clinical Applications
- AI in cancer detection
- Ultrasound Imaging and Elastography
- EEG and Brain-Computer Interfaces
- Advanced MRI Techniques and Applications
- Neural dynamics and brain function
- Image and Signal Denoising Methods
- Respiratory Support and Mechanisms
- Mental Health Research Topics
University of Lisbon
2023-2025
The admission of COVID-19 patients to the Intensive Care Unit (ICU) is largely dependent on illness severity, yet no standard criteria exist for this decision. Here, lung ultrasound (LU) data, blood gas analysis (BGA), and clinical parameters from venous tests (VBTs) were used, along with machine-learning (ML) models predict need ICU admission. Data fifty-one patients, including status, collected. information LU was gathered through identification findings (LUFs): B-lines, irregular pleura,...
Ultrasound (US) imaging is used in the diagnosis and monitoring of COVID-19 breast cancer. The presence Speckle Noise (SN) a downside to its usage since it decreases lesion conspicuity. Filters can be remove SN, but they involve time-consuming computation parameter tuning. Several researchers have been developing complex Deep Learning (DL) models (150,000–500,000 parameters) for removal simulated added without focusing on real-world application removing naturally occurring SN from original...
The diagnosis of psychiatric disorders is mostly based on the clinical evaluation patient's signs and symptoms. Deep learning binary-based classification models have been developed to improve but not yet reached practice, in part due heterogeneity such disorders. Here, we propose a normative model autoencoders.We trained our autoencoder resting-state functional magnetic resonance imaging (rs-fMRI) data from healthy controls. was then tested schizophrenia (SCZ), bipolar disorder (BD),...
In the big data era, with a lack of comparable functional neuroimaging data, researchers try to combine heterogeneous different lengths, trimming those same number timepoints (NTPs). However, effects blood-oxygen-level dependent (BOLD) signal on connectivity (FC) are still poorly understood.Resting-state magnetic resonance imaging from thirty healthy subjects were pre-processed for five NTPs, which FC matrices computed. These BOLD correlation binarized several thresholds, excluding weak...