Search results

Information session content This session will address how a research result can be valorized through an entrepreneurial project thanks to the Win4SO program; and how Proof of Concept (POC) funding enables the development of a proof of concept on which an entrepreneurial project can be based. Who is this information session for? All researchers. Presentation Laurent Galas, EDER project coordinator, MIRVALIS Time and place of training The information session will take place on Monday 13/01/2025 from 12:45pm to 2pm at ADRE - NARC room, rue de Bruxelles, 55. Discover Midis de l'ADRE

Information session content Data management and protection have become an inescapable requirement of research. This training course will focus on the legal requirements for personal data protection in the specific field of scientific research. The aim is to explain how to approach and implement these requirements from the researcher's point of view. It will also provide an overview of the tools in place at the University of Namur. Who is this information session for? All researchers. Presentation Karen Rosier, Data Protection Officer Time and place of training The information session will take place on WEDNESDAY 05/27/2025 from 12:45pm to 2pm at ADRE - NARC room, rue de Bruxelles, 55. Discover Midis de l'ADRE

Information session content Data management and protection have become an inescapable requirement of research. This training course will focus on the legal requirements for personal data protection in the specific field of scientific research. The aim is to explain how to approach and implement these requirements from the researcher's point of view. It will also provide an overview of the tools in place at the University of Namur. Who is this information session for? All researchers. Presentation Karen Rosier, Data Protection Officer Time and place of training The information session will take place on WEDNESDAY 05/27/2025 from 12:45pm to 2pm at ADRE - NARC room, rue de Bruxelles, 55. Discover Midis de l'ADRE

Information session content This session covers the essentials of communicating with the press. It covers the following points:Scientific/media relationship: Why you need the press, why it needs youTools for reaching the pressSucceeding in your media appearanceUNamur in the media Who is this information session for? All researchers. Presentation Noëlle Joris, press officer for UNamur's Communications Administration. Time and place of training The information session will take place on Monday 14/04/2025 from 12:45pm to 2pm at ADRE - NARC room, rue de Bruxelles, 55. Discover Midis de l'ADRE

Information session content This session covers the essentials of communicating with the press. It covers the following points:Scientific/media relationship: Why you need the press, why it needs youTools for reaching the pressSucceeding in your media appearanceUNamur in the media Who is this information session for? All researchers. Presentation Noëlle Joris, press officer for UNamur's Communications Administration. Time and place of training The information session will take place on Monday 14/04/2025 from 12:45pm to 2pm at ADRE - NARC room, rue de Bruxelles, 55. Discover Midis de l'ADRE

Abstract Deep learning has revolutionized computer vision in recent years and has been applied to many fields. This thesis focuses on medical endoscopy, where deep learning can assist physicians in many tasks, such as navigating the lungs during bronchoscopy, assisting in the detection of lung diseases, detecting Crohn's disease from capsule endoscopy (PillCam), or automating the detection of polyps during colonoscopy procedures.This thesis, entitled From Pixels to Practice: Deep Learning for Endoscopy, explores how modern neural networks and learning paradigms can improve visual understanding in endoscopy, with the aim of contributing to computer-aided detection (CAD) systems that can be integrated into clinical workflows.This work follows an article-based structure and links methodological advances in geometric and temporal modeling to techniques for handling data scarcity and imbalance, as well as to the practical and clinical implications of deep learning for lung tumor detection, both from a clinical and practitioner perspective. The first part of the manuscript provides a common foundation for all subsequent parts. First, we present a general introduction to the field of machine learning in Chapter 1, explaining concepts such as classification, loss functions, and artificial neural networks. Next, Chapter 2 focuses on the field of deep learning for computer vision, detailing the main vision tasks, the concept of convolutional neural networks, ResNet, and U-Net. Finally, Chapter 3 describes medical imaging, with a focus on computed tomography (CT) scans and optical imaging. The second part of the thesis focuses on learning spatio-temporal representations. In Chapter 4, we use deep neural networks combining spatial features and temporal recurrence to address the problem of detecting the bronchial carina, an anatomical landmark that helps doctors navigate the lungs. By evaluating classification (ResNet-50), segmentation (nnU-Net), and recurrent (GRU) models on a bronchoscopy dataset we created, the study highlights the benefits of combining information from segmentation masks and temporal features. Chapter 5 continues the segmentation task by analyzing the extent to which rotation-equivariant U-Nets, based on E(2)-CNNs with C4, C8, and D4 symmetry groups, can improve performance when the orientation of objects in the image is arbitrary. Together, these chapters show how temporal and geometric modeling capture complementary aspects of visual structure. They further highlight that data imbalance and scarcity are recurring problems in deep learning. The third part studies learning in situations of data scarcity and imbalance. First, Chapter 6 explores supervised contrastive pre-training [1] on large, domain-close endoscopic datasets (Hyper-Kvasir [2], LDPolyp [3]), which is then transferred to smaller, disease-specific data (Crohn-IPI [4]). This methodology performs better than pre-training on ImageNet or based on cross-entropy, highlighting the value of domain-specific contrastive representations. Next, Chapter 7 introduces Mask-Aware Cropping (MAC), a new data augmentation technique that mitigates pixel-level imbalance in segmentation. On various datasets with varying imbalance regimes (URDE [5], Kvasir-SEG [6], HAM10000 [7]), MAC consistently improves Dice and IoU metrics under conditions of extreme imbalance. Together, these methods form a data-centric framework for effective learning when annotations are scarce or unevenly distributed. The fourth part of the thesis focuses on deep learning in the operating room. Chapter 8 proposes a first model (ResNet-50) for the visual detection of lung cancer in bronchoscopy, trained on real, in-vivo data. The model outperforms junior physicians, while remaining inferior to experts. This result shows that CAD systems for lung cancer detection are promising. Chapter 9 extends this work by evaluating the usability of a CAD system based on a deep learning model. Combining probability indices, temporal graphs, and saliency map overlays, a multicenter evaluation with 10 physicians is conducted. The tool received favorable feedback, with high usability (SUS score of 80.5 [8]) and strong clinical acceptance. Beyond endoscopy, the results concerning rotation equivariance and pixel imbalance can be generalized to other fields such as microscopy, dermatology, and aerial imaging. This shows that the proposed methods are applicable to visual learning under structured variability and limited data constraints.Keywords: machine learning, computer vision, medicine, endoscopy, convolutional neural networks, segmentation, recurrent models, equivariance.  Jury Prof. Bruno Dumas - University of NamurProf. Frénay Benoit - University of NamurProf. Schobbens P-Y. - University of NamurProf. Beuls Katrien - University of Namur,Dr. Benjamin Mertens - Lys MédicalProf. Oramas Mogrojevo José Antonio - University of AntwerpDr. Mancas Matei - University of Mons Register

The colloquium will be held on Tuesday, April 15 and Wednesday, April 16, 2025, at the University of Namur (Belgium). Proposals for papers (programmatic title and abstract of 500 signs, followed by a biobibliography) can be sent by November 15, 2024 to Jean-Benoit.Gabriel@unamur.be and Denis.Saint-Amand@unamur.be.

It's obvious to anyone paying attention to the paths taken by a growing number of 21st century thinkers: these paths lead to the living! Whether it's called "ecophilosophy", "ecoanthropology", "ecosophy", or "ecopolitics", this thinking about the living is occupying a growing place not only in the media and publications of all kinds, but also in concrete actions in a variety of fields.Program 2024-2025 | At the Roots of the HumanTo introduce the subjectIf we were to take stock of the history of mankind, one trend would certainly stand out: that of a utilitarian relationship with the non-human that continues to grow, and consequently that of a widening gap between the human and the rest.Humanity, however, has its roots in a living environment that cultivates many other relationships than those we currently privilege, which are dominated by instrumental rationality. Sounding out these forgotten relational universes without which it is increasingly difficult to think about the human is one aim of this seminar, which this year will invite you to encounter the plant.On December 13 2024 from 2:00 to 4:00 pm (intervention, discussions and convivial moment). Quentin HIERNAUX will introduce plant philosophy and tell us about Humboldt's "Tableau physique des Andes" and his equinoctial geography of plants.Next datesOn February 28, 2025 from 2:00 to 4:00 pm (intervention, discussions and convivial moment), Jean-Baptiste VUILLEROD will address the following theme: Naturphilosophie du végétal : Goethe, Schelling, Humboldt.OnApril 11, 2025from 2:00 to 4:00 pm (intervention, discussions and convivial moment), Roland CAZALIS will share with us his biologist's point of view on the plant world. Find out more about seminars

It's obvious to anyone paying attention to the paths taken by a growing number of 21st century thinkers: these paths lead to the living! Whether it's called "ecophilosophy", "ecoanthropology", "ecosophy", or "ecopolitics", this thinking about the living is occupying a growing place not only in the media and publications of all kinds, but also in concrete actions in a variety of fields.Program 2024-2025 | At the Roots of the HumanTo introduce the subjectIf we were to take stock of the history of mankind, one trend would certainly stand out: that of a utilitarian relationship with the non-human that continues to grow, and consequently that of a widening gap between the human and the rest.Humanity, however, has its roots in a living environment that cultivates many other relationships than those we currently privilege, which are dominated by instrumental rationality. Sounding out these forgotten relational universes without which it is increasingly difficult to think about the human is one of the aims of this seminar, which this year will invite you to encounter the plant.Next dateOnApril 11, 2025from 2:00 to 4:00 pm (talk, discussions and convivial moment), Roland CAZALIS will share with us his biologist's point of view on the plant world. Find out more about seminars

Come and watch the students selected for the finals, vote for the public prize and extend the evening with a drink.This event is open to the public. Free admission.

Julie Henry is a doctoral student in computer science and STEAM project leader. Her work focuses, among other things, on gender stereotypes and their influence on career orientation, particularly with regard to STEM professions. Antoinette Rouvroy holds a PhD in legal sciences from the European University Institute (Florence, 2006) and is a qualified FNRS researcher at the Centre de Recherche en Information, Droit et Société (CRIDS). Since 2000, she has been interested in the relationship between law, modes of construction and risk, science and technology, and neoliberal governmentality.The Midi will be moderated by François-Xavier Fiévez, Vice-Rector in charge of Gender. In parallel with this discussion, an exhibition by Plan International entitled #Dream4Girls, pinpointing some big dreams for the future of girls generated by AI, will be accessible in the Quai 22 exhibition hall.This free event is open to the public (registration required).Registrations: https://www.billetweb.fr/midi-genre-ia-menace-ou-opportunite-pour-les-femmes