Search results

The Faculty of Law Library provides two multifunction photocopiers for photocopying, black-and-white printing and A4 scanning..

Find databases that can help you on site or remotely.

Find various catalogs that may be useful to you in Law School.

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

In late November 2024, UNamur hosted the 23rd BENEVOL Congress, an annual research seminar that provides an opportunity for international researchers to meet and discuss new ideas, important issues and cutting-edge research in the field of software engineering, maintenance and evolution.

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.

Stanford University has published a prestigious ranking that highlights the most influential researchers in a wide range of scientific fields. The list, based on bibliographic criteria, aims to provide a standardized means of identifying the world's scientific leaders. It is one criterion among others for assessing the quality of scientific research. Twelve researchers from the University of Namur are among them!

Animated by a desire to help the most disadvantaged, Father Pedro Opeka, a Lazarist priest, devotes his life to improving the living conditions of Madagascar's marginalized populations. His strong humanitarian commitment has resulted in the creation of Akamasoa, an association that provides shelter, education and healthcare to thousands of Malagasy people. By transforming the lives of an entire community in this way, he has become a symbol of hope in a country beset by poverty.

Program and speakers Explanation of the reform - Mr. La TorreMain changes relating to the abolition of unemployment benefits and their implementation. The standstill obligation - S. RemouchampsLegal and constitutional analysis of the reform in light of the principle of non-regression.Judicial perspective on the reform - Mr. SimonOverview of certain contentious issues and possible avenues of appeal for citizens deprived of their rights.Right to RIS and/or social assistance - A. MichelThe process of submitting an application to the CPAS. Registrations Registration is required via https://www.ajn.be (payment confirms registration).Advance registration fee (payment by January 23, 2026): €40 (€20 for trainee lawyers)Standard price for payments received after January 23, 2026: €50 (€25 for trainee lawyers)Free for students (enter a student email address or send a copy of your student card)Payment to bank account BE16 6301 8124 6074 - AJN AsblReference: "29-01-2026 + participant's name."Accreditation request pending for IFJ, OBFG, and IJE. Further information: ajn@unamur.be. Registration form

Program 1001 questions about the Ombudsman - How can administrative mediation be used as an effective tool for dispute resolution?The scope and added value of administrative mediationThe matters in which the Ombudsman can interveneThe types of disputes concerned and the concrete solutions you can obtain.Taking a resolutely practical approach, our two experts explain when and why to call on the Ombudsman, how to initiate administrative mediation, and how to make it an effective tool for quickly resolving your disputes!SpeakersNicolas Lagasse | Joint Mediator for Wallonia and the Wallonia-Brussels Federation; President of the Association of Ombudsmen and Mediators of La Francophonie (AOMF); member of the Belgian network of mediatorsBenoit Havet | Lawyer at the Walloon Brabant Bar, specializing in urban planning, environmental, and real estate law; lecturer at the ULB and UMons  Registrations Registration is required via https://www.ajn.be (payment confirms registration).Advance registration fee (payment before February 20, 2026): €40 (€30 for trainees)Price after February 20, 2026: €50 (€40 for interns)Free for students upon presentation of student IDAccreditation request in progress for IFJ, OBFG, FRNB, and IJE. Further information: ajn@unamur.be. Registration form

Abstract Since its emergence in 1996, the Asian H5 Goose/Guangdong (Gs/Gd) lineage has circulated widely in poultry in southern China, spilling over to wild birds by 2002. Wild bird infections facilitated global dissemination via migratory waterfowl and repeated spillback into poultry, challenging the view that HPAI primarily arises from LPAI mutation. Subclade 2.3.4.4b emerged in Asia in 2013, reached Europe in 2016, caused recurrent epizootics, diversified into multiple genotypes, became dominant in wild birds, and shows zoonotic potential.This thesis investigates critical knowledge gaps regarding H5Nx subclade 2.3.4.4b in poultry: (1) early within-flock spread after punctual introduction in chickens, particularly during the first European epizootics; (2) influence of pre-existing immunity on silent circulation; (3) limitations in diagnostic throughput during epizootic peaks; (4) potential of environmental surveillance, including air and dust sampling; and (5) impact on egg contamination and the reproductive tract, relevant for food safety and zoonotic risk.Four main objectives were addressed: (1) development of an experimental model simulating punctual introductions and spread, comparing 2017 and 2020 strains and assessing pre-existing immunity; (2) enhancement of diagnostic capacity via alternative sampling, semi-automated RNA extraction, and high-throughput processing; (3) evaluation of air and dust sampling for virus monitoring under experimental and field conditions; and (4) assessment of egg contamination risk. Alternative sampling and environmental monitoring were also applied to Newcastle disease virus as a comparative notifiable pathogen. Jury Prof. Tuci Elio - University of Namur, BelgiumProf. Anthony Cleve - University of Namur, BelgiumProf. Pierre-Yves Schobbens - University of Namur, BelgiumProf. Alvaro Gutierrez - Universidad Politecnica de Madrid, EspagneMr. Fabian Duchesne - Qualitics SPRLProf. Anders Lyhne Christensen - SDU, Denmark Evènement public et gratuit - Inscription obligatoire Je m'inscris