Ana Maria Mendonça

My name is Ana Maria Mendonça and I am currently Associate Professor at the Department of Electrical and Computer Engineering (DEEC) of the Faculty of Engineering of the University of Porto (FEUP), where I got my PhD in 1994. I was a researcher at the Institute for Biomedical Engineering (INEB) until 2014, but since 2015 I am a senior researcher at INESC. At INEB, I was a member of the Board of Directors and afterwards President of the Board.

In my management activities in higher education and research, I was a member of the Executive Board of DEEC and more recently Deputy Director of FEUP. At INEB, I was a member of the Institute's Board of Directors, initially as a member and later as President of the Board.

I was an elected member of FEUP's Scientific Council and am currently a member of the school's Pedagogical Council. I was a member of the scientific committee of several academic programmes and, currently, I am the Director of the First Degree and the Master Degree in BioEngineering, of the Biomedical Engineering Master and the Doctoral Programme in Biomedical Engineering.

I have been collaborating as a research and also as responsible in several research projects, mostly dedicated to the development of image analysis and classification methodologies aiming at extracting essential information from medical images in order to support the diagnosis process. Past work has been mostly devoted to three main areas: retinal pathologies, lung diseases and genetic disorders, but ongoing work is mainly focused on the development of Computer-Aided Diagnosis systems in Ophthalmology and Radiology.

Domains

Biomedical Engineering Research Artificial Intelligence Bioengineering

Projects

NanoStima-RL5

The goal of CAD-RL5 is to develop advanced capabilities for computer-aided detection and diagnosis (CAD). This requires research on innovative methodologies for CAD development, that will make it possible to go from ad hoc engineering approaches, driven by direct expert knowledge, to more automated approaches, driven by the intrinsic structure of data, knowledge discovery and expert supervision. Problems tackled will be generic in the sense that appropriate outcomes can be applied universally to medical imaging practices. The developed method will enable lab demonstrations of several clinical problems where the research team has relevant experience (e.g. radiology, ophthalmology and ultrasound imaging). Project Information Sheet (PT)

NanoSTIMA - Advanced Methodologies for Computer-Aided Detection and Diagnosis

TAMI

The aim of the project TAMI is to create a new platform for commercial, scientific and academic use that will provide "consumers" access to results and explanations of registered diagnostic orders, filtered data sets access for investigators or scientists and a knowledge base for academic purposes. In order to achieve such objective, the project will be based on the following specific objectives involving the development of research in the following areas: a) quantitative methods to objectively assess and compare different explanations of the automatic decisions; b) methods to generate better explanations, providing variety in the explanations, adapting the explanations to who will consume them and explaining multimodal decisions; c) novel visualization solutions for interpretations of decisions based on imagiological data. In order to accomplish that, TAMI will use clinical data, from structured to image data, in order to design and validate interpretable machine learning models. During the project, different multimodal settings will be tested to enable a better understanding of the AI-based decisions. Moreover, the algorithms will be designed to generate self-explanatory AIbased decisions, minimise bias, and act ethically in their context. Proof-of-concepts and demonstrators of how to integrate the researched explainable AI into workflows of cervical cancer treatment, pathology detection in chest X-Ray images in a screening environment, and glaucoma detection in retinal fundus images will be developed to validate the algorithmic solutions.

View all projects

Publications

Human versus Artificial Intelligence: Validation of a Deep Learning Model for Retinal Layer and Fluid Segmentation in Optical Coherence Tomography Images from Patients with Age-Related Macular Degeneration

Miranda, M;Santos-Oliveira, J;Mendonca, AM;Sousa, V;Melo, T;Carneiro, A;

2024

DIAGNOSTICS

Automated image label extraction from radiology reports - A review

Pereira, SC;Mendonca, AM;Campilho, A;Sousa, P;Lopes, CT;

2024

ARTIFICIAL INTELLIGENCE IN MEDICINE

Confident-CAM: Improving Heat Map Interpretation in Chest X-Ray Image Classification

Rocha, J;Mendonça, AM;Pereira, SC;Campilho, A;

2023

IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023, Istanbul, Turkiye, December 5-8, 2023

STERN: Attention-driven Spatial Transformer Network for abnormality detection in chest X-ray images

Rocha, J;Pereira, SC;Pedrosa, J;Campilho, A;Mendonça, AM;

2024

ARTIFICIAL INTELLIGENCE IN MEDICINE

View all publications

Supervised theses

A Reinforcement Learning-based inspection of the offshore windmills using multiple aerial unmanned vehicles

Francisco Soares Pinto da Silva Neves

D - 2024

UP-FEUP

Centres

Biomedical Engineering Research

The impact that science and innovation can have on the prevention, early detection, and support for the diagnosis of various types of diseases is fully explored at our Centre for Biomedical Engineering Research (C-BER). Guided by an interdisciplinary approach that prioritises technology transfer with economic impact—through the creation of new systems, tools, and methods related to disease diagnosis and monitoring, ageing, human rehabilitation, physiotherapy, and functional assessment—our researchers are dedicated to developing advanced technologies positioned at the intersection of engineering, medicine and health, and general well-being. Promoting strategic partnerships with clinical partners, research institutes, and encouraging international cooperation is one of the centre’s key priorities. Its research is structured across three distinct areas: Biomedical Imaging, Bioinstrumentation, and Neuroengineering.