A5036253149- Radiomics and Machine Learning in Medical Imaging
- ECG Monitoring and Analysis
- Explainable Artificial Intelligence (XAI)
- AI in cancer detection
- Cardiac electrophysiology and arrhythmias
- Image Retrieval and Classification Techniques
- Brain Tumor Detection and Classification
- Blockchain Technology Applications and Security
- Machine Learning in Materials Science
- Generative Adversarial Networks and Image Synthesis
- Medical Imaging and Analysis
Universidade Nova de Lisboa
2021-2025
Administração Regional de Saúde de Lisboa e Vale do Tejo
2024
Weatherford College
2021
Adrenal lesions are common findings in abdominal imaging, with adrenal adenomas being the most frequent type. Accurate detection of is essential to avoid unnecessary diagnostic procedures and treatments. However, conventional imaging-based evaluation relies heavily on expertise radiologists can be complicated by pseudo-lesions, overlapping imaging features, suboptimal techniques. To address these challenges, we propose an end-to-end machine learning pipeline that integrates deep...
In clinical practice, every decision should be reliable and explained to the stakeholders. The high accuracy of deep learning (DL) models pose a great advantage, but fact that they function as black-boxes hinders their applications. Hence, explainability methods became important provide explanation DL models. this study, two datasets with electrocardiogram (ECG) image representations six heartbeats were built, one given label last heartbeat other first heartbeat. Each dataset was used train...
The lack of labelled medical data still poses as one the biggest issues when creating Deep Learning models in field. Modern augmentation techniques like generation synthetic images have gained a special interest. In recent years there has been significant improvement GANs. StyleGAN2 achieves impressive results natural images. StyleGAN2-ADA was created to respond training an image synthesis model, which is very frequent Some works used styleGAN generate melanomas, breast cancer histological...
Current computer vision models require a significant amount of annotated data to improve their performance in particular task. However, obtaining the required is challenging, especially medicine. Hence, augmentation techniques play crucial role. In recent years, generative have been used create artificial medical images, which shown promising results. This study aimed use state-of-the-art model, StyleGAN3, generate realistic synthetic abdominal magnetic resonance images. These images will be...
Abstract Background: Deep Learning (DL) models are able to produce accurate results in various areas. However, the medical field is specially sensitive, because every decision should be reliable and explained stakeholders. Thus, high accuracy of DL pose a great advantage, but fact that they function as black-box hinders their application sensitive fields, given not explainable per se . Hence, explainability methods became important provide explaination problems. In this work, we trained...