The Quantitative Bio-Imaging Lab focuses on the development of rapid imaging, motion correction, deep learning-based reconstruction and quantification approaches for Magnetic Resonance Imaging and Optical Imaging for a broad spectrum of application fields, such as cardiology, oncology and marine biology.

Optical Imaging 
We are developing Optical Projection Tomography and Lightsheet microscopy tools (hardware & software) for imaging live developing organisms and large cleared samples.  Our research is also focused on the development of accelerated acquisition approaches, image reconstruction methods and light propagation models.

Cardiac MRI
Our research is also focused on the development of accelerated acquisition, undersampled reconstruction and motion correction techniques for free-breathing cardiac Magnetic Resonance Imaging (MRI) for diagnosing cardiovascular disease. We are particularly interested in the application of these methods to 3D whole-heart cardiac MRI and quantitative first-pass myocardial perfusion and their translation into clinical practice.

Deep Learning 
Our active research projects aim to develop deep learning-based methods for image reconstruction from accelerated scans, automated detection, segmentation and classification tasks for diagnosis, prognosis, and therapy response prediction.

Educational Resources 
QBI hosts educational courses in the area of biomedical imaging, which mix didactic lectures with hands-on tutorials and programming exercises covering, for example, the principles of tomography.

  Join our team! QBI is welcoming candidates for the 2027 PhD Scholarships funded by FCT (Regular and Non-Academic Lines).
🔬  MSc / PhD Research Opportunity - 𝗢𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 𝟯𝗗 𝗢𝗽𝘁𝗶𝗰𝗮𝗹 𝗜𝗺𝗮𝗴𝗶𝗻𝗴 𝗳𝗼𝗿 𝗙𝗮𝘀𝘁 𝗠𝗲𝘀𝗼𝘀𝗰𝗼𝗽𝗶𝗰 𝗜𝗺𝗮𝗴𝗶𝗻𝗴
💻 MSc / PhD Research Opportunity - 𝗔𝗜 𝗳𝗼𝗿 𝗖𝗮𝗿𝗱𝗶𝗼𝘃𝗮𝘀𝗰𝘂𝗹𝗮𝗿 𝗥𝗶𝘀𝗸 𝗶𝗻 𝗠𝗲𝗻𝗼𝗽𝗮𝘂𝘀𝗲 
 

👀 Looking for an internship, MSc or PhD research project? E-mail your application (topic of interest, motivation letter, CV and academic transcript) to tmcorreia@ualg.pt. 

Alumni 

David Palecek Optical Tomography in Python - open-source hardware and software

Marcos Obando Model-based Deep Learning Methods for Accelerated Optical Projection Tomography 

Catarina Carvalho Quantitative MRI parameter mapping with extended phase graphs and recurrent inference machines

Pedro Osório Implementation of a deep-learning based tool for automatic Cardiac MR planning: DeepCardioPlanner

Catarina Lourenço Deep Learning Tools for Outcome Prediction in Atrial Fibrillation from Cardiac MRI 

Juna Santos DeepPlanner4Cardio: An automatic multi-view planning tool for Cardiac MRI

Miguel Amil The use of diffusion models in the reconstruction of accelerated MRI acquisitions

Dinis Matias Accelerating Cardiac Magnetic Resonance T1-mapping using deep learning 

Gonçalo Monteiro Enabling automatic analysis of quantitative cardiac magnetic resonance imaging maps using deep learning 

Diogo Aguiar Unveiling the secrets of shark development with lightsheet microscopy

Diogo Neves Histological assessment of the effects of ocean acidification on the olfactory epithelium of the gilthead seabream (Sparus aurata) 

Alexandre Gomes Artificial Intelligence for Cardiac Magnetic Resonance Imaging: Estimating Biomarkers for Automated Assessment of Cardiovascular Disease

Suellen Ferraz Automated MRI reporting using multimodal large language models 

Lukas Christmann Sample preparation techniques for fluorescence microscopy 

Visitors

Elisa Moya-Sáez Motion correction for perfusion cardiac MRI

Elena Martín-González Physics-informed self-supervised deep learning reconstruction for accelerated first-pass perfusion cardiac MRI