A5016100261- Brain Tumor Detection and Classification
- Radiomics and Machine Learning in Medical Imaging
- Medical Image Segmentation Techniques
- Advanced Neural Network Applications
- Advanced MRI Techniques and Applications
- Semantic Web and Ontologies
- AI-based Problem Solving and Planning
- AI in cancer detection
- Logic, Reasoning, and Knowledge
- Medical Imaging Techniques and Applications
- Anatomy and Medical Technology
- Advanced Neuroimaging Techniques and Applications
- Functional Brain Connectivity Studies
- Generative Adversarial Networks and Image Synthesis
- Craniofacial Disorders and Treatments
- Medical Imaging and Analysis
- Advanced Database Systems and Queries
- Intelligent Tutoring Systems and Adaptive Learning
- Cell Image Analysis Techniques
- Data Stream Mining Techniques
- Surgical Simulation and Training
- Machine Learning and Data Classification
- Colorectal Cancer Screening and Detection
- Acute Ischemic Stroke Management
- Multi-Agent Systems and Negotiation
University of Minho
2016-2025
Universidade Federal de Juiz de Fora
2024
Universidade Federal do Ceará
2024
University of Duisburg-Essen
2024
Polytechnic Institute of Cávado and Ave
2022
Deloitte (United Kingdom)
2021
Hospital de São João
2017-2019
University of Évora
2013
Hospital de Santo António
2004
Among brain tumors, gliomas are the most common and aggressive, leading to a very short life expectancy in their highest grade. Thus, treatment planning is key stage improve quality of oncological patients. Magnetic resonance imaging (MRI) widely used technique assess these but large amount data produced by MRI prevents manual segmentation reasonable time, limiting use precise quantitative measurements clinical practice. So, automatic reliable methods required; however, spatial structural...
Diffusion Tensor Imaging (DTI) studies are increasingly popular among clinicians and researchers as they provide unique insights into brain network connectivity. However, in order to optimize the use of DTI, several technical methodological aspects must be factored in. These include decisions on: acquisition protocol, artifact handling, data quality control, reconstruction algorithm visualization approaches, quantitative analysis methodology. Furthermore, researcher and/or clinician also...
Performance of models highly depend not only on the used algorithm but also data set it was applied to. This makes comparison newly developed tools to previously published approaches difficult. Either researchers need implement others' algorithms first, establish an adequate benchmark their data, or a direct new and old techniques is infeasible. The Ischemic Stroke Lesion Segmentation (ISLES) challenge, which has ran now consecutively for 3 years, aims address this problem comparability....
In developed countries, the second leading cause of death is stroke, whose most common type ischemic stroke. The preferred diagnosis procedure involves acquisition multi-modal Magnetic Resonance Imaging. Besides detecting and locating stroke lesion, Imaging captures blood flow dynamics that guides physician in forecasting risks benefits revascularization procedure. However, decision process an intricate task due to variability lesion sizes, shapes, locations, as well complexity underlying...
Fully Convolutional Networks have been achieving remarkable results in image semantic segmentation, while being efficient. Such efficiency from the capability of segmenting several voxels a single forward pass. So, there is direct spatial correspondence between unit feature map and voxel same location. In convolutional layer, kernel spans over all channels extracts information them. We observe that linear recombination maps by increasing number followed compression may enhance their...
Breast cancer is the most prevalent in world and fifth-leading cause of cancer-related death. Treatment effective early stages. Thus, a need to screen considerable portions population crucial. When screening procedure uncovers suspect lesion, biopsy performed assess its potential for malignancy. This usually using real-time Ultrasound (US) imaging. work proposes visualization system US breast biopsy. It consists an application running on AR glasses that interact with computer application....
The transformation of healthcare organizations is essential to address their inherent complexity and dynamic nature. This study emphasizes the role Data Science, with incorporation Artificial Intelligence tools, in enabling data-driven interconnected management strategies. To achieve this, a thermodynamic approach Knowledge Representation Reasoning was employed, capturing workers’ perceptions work environment through structured questionnaires. Over several months, entropic efficiency...
Magnetic Resonance Imaging is the preferred imaging modality for assessing brain tumors, and segmentation necessary diagnosis treatment planning. Thus, robust automatic methods are required. Machine learning proposals where model learned from data quite successful. Hierarchical approaches firstly segment whole tumor, followed by intra-tumor tissue identification. However, results comparing it with single stages needed, as state of art also achieved all-at-once strategies. Currently, fully...
Abstract Patient-specific craniofacial implants are used to repair skull bone defects after trauma or surgery. Currently, cranial designed and produced by third-party suppliers, which is usually time-consuming expensive. Recent advances in additive manufacturing made the in-hospital in-operation-room fabrication of personalized feasible. However, still manufactured external companies. To facilitate an optimized workflow, fast automatic implant highly desirable. Data-driven approaches, such...
Deep Learning is the state-of-the-art technology for segmenting brain tumours. However, this requires a lot of high-quality data, which difficult to obtain, especially in medical field. Therefore, our solutions address problem by using unconventional mechanisms data augmentation. Generative adversarial networks and registration are used massively increase amount available samples training three different deep learning models tumour segmentation, first task BraTS2023 challenge. The model...
In this article, we present a brain tumor database collection comprising 23,049 samples, with each sample including four different types of MRI scans: FLAIR, T1, T1ce, and T2. Additionally, one or two segmentation masks (ground truth) are provided for sample. The first mask is the raw output from registration process all while second mask, particularly synthetic post-processed version first, designed to simplify interpretation optimize it network training. These samples have been acquired...
The proliferation of classification-capable artificial intelligence (AI) across a wide range domains (e.g., agriculture, construction, etc.) has been allowed to optimize and complement several tasks, typically operationalized by humans. computational training that allows providing such support is frequently hindered various challenges related datasets, including the scarcity examples imbalanced class distributions, which have detrimental effects on production accurate models. For proper...
Abstract The field of AI Ethics has recently gained considerable attention, yet much the existing academic research lacks practical and objective contributions for development ethical systems. This systematic literature review aims to identify map metrics documented in between January 2018 June 2023, specifically focusing on principles outlined Guidelines Trustworthy AI. was based 66 articles retrieved from Scopus World Science databases. were categorized their alignment with seven...