João Mendes
Room in IBEB
1.02
Contacts
E-mail: jpmendes[at]ciencias.ulisboa.pt
Professional networks
Research topics
- Artificial Intelligence
- Breast Cancer
- Medical Imaging
Biography
João Mendes, born in 1998, has a BSc+MSc Degree in Biomedical Engineering and Biophysics from the Faculty of Sciences of the University of Lisbon (FCUL).
João interned at Champalimaud Foundation in the final year of his Bachelor’s degree. There, he studied computational applications for the diagnosis of Pulmonary Embolism.
During his master’s thesis at IBEB, João started working with Artificial Intelligence applied to medical imaging. His work was focused on using Machine Learning models to diagnose Breast Cancer through mammograms. His work resulted in a published scientific paper, and it was presented at an international conference.
At the beginning of 2022, João enrolled in the Biomedical Engineering and Biophysics PhD program at FCUL. His PhD project aims to develop a Multimodal-AI model that can predict the future risk of Breast Cancer development based on normal medical images of the breast. The merit of the project was recognized by Fundação para a Ciência e Tecnologia, which granted him a four-year scholarship for his PhD. So far, João’s work during his PhD has been presented at several national scientific gatherings and resulted in three published scientific papers.
João is currently an Invited Assistant at FCUL.
Publications
Journal publications
(2024) Artificial Intelligence for Hierarchical Tumor Masking Potential Classification in Mammograms, Innovative Practice in Breast Health, p. 100014, Elsevier, doi:10.1016/j.ibreh.2024.100014
(2024) Artificial intelligence on breast cancer risk prediction, Societal Impacts 4, p. 100068, Elsevier, doi:10.1016/j.socimp.2024.100068
(2024) Breast Cancer Molecular Subtype Prediction: A Mammography-Based AI Approach, Biomedicines 12(6), p. 1371, MDPI, doi:10.3390/biomedicines12061371
(2023) Digital Breast Tomosynthesis: Towards Dose Reduction through Image Quality Improvement, Journal of Imaging 9(6), p. 119, MDPI, doi:10.3390/jimaging9060119
(2023) Avoiding Tissue Overlap in 2D Images: Single-Slice DBT Classification Using Convolutional Neural Networks, Tomography 9(1), p. 398-412, MDPI, doi:10.3390/tomography9010032
(2023) Make It Less Complex: Autoencoder for Speckle Noise Removal—Application to Breast and Lung Ultrasound, Journal of Imaging 9(10), p. 217, doi:10.3390/jimaging9100217
(2022) AI in Breast Cancer Imaging: A Survey of Different Applications, Journal of Imaging 8(9), p. 228, MDPI, doi:10.3390/jimaging8090228
(2021) Breast cancer risk assessment: A review on mammography-based approaches, Journal of Imaging 7(6), p. 98, MDPI, doi:10.3390/jimaging7060098