“Signal Processing in the AI era” was the tagline of this year’s IEEE International Conference on Acoustics, Speech and Signal Processing, taking place in Rhodes, Greece.
In this context, Brent de Weerdt, Xiangyu Yang, Boris Joukovsky, Alex Stergiou and Nikos Deligiannis presented ETRO’s research during poster sessions and oral presentations, with novel ways to process and understand graph, video, and audio data. Nikos Deligiannis chaired a session on Graph Deep Learning, attended the IEEE T-IP Editorial Board Meeting, and had the opportunity to meet with collaborators from the VUB-Duke-Ugent-UCL joint lab.
Featured articles:
- De Weerdt, B. et al., “Designing Transformer Networks for Sparse Recovery of Sequential Data Using Deep Unfolding” (https://ieeexplore.ieee.org/abstract/document/10094712)
- Yang X. et al., “Relevance Propagation through Deep Conditional Random Fields” (https://ieeexplore.ieee.org/abstract/document/10095075)
- Stergiou A. et al., “Play it back: Iterative attention for audio recognition” (https://ieeexplore.ieee.org/abstract/document/10096532, developed at the University of Bristol)
A full immersive experience of Augmented Reality for neurosurgical planning and real-time intervention, demonstrated by Taylor on the FARI immersive CAVE during the Agoria HealthTech roundtable event June 17th , 2024.
- The lab receives the MC6800 development kit – the logic state analyser, was the mostly used development instrument, followed by programming in assembler. The system was interfaced to a mechanical teletype.
- First thesis work in microelectronics technology on CCD-MNOS combination. Roger Vounckx join the lab.
- An analogue bucket brigade system is built with discrete components.
- Worldwide first BSPM measurement system with 128 channels based on MSI ICs.
- Marc Nyssen joins the lab (August 1975).
- New instrument designs – Digital correlator and Histogram measurement system, Fourier transformer.
- CDC central ULB-VUB computer facility exclusively for numerical calculus, with punch card readers as interface; FORTRAN is the dominating programming language.
- May 1968: student revolt impacting citizen’s mindset, and changing society as well as university governance.
- 1968-1969 The unitary ULB/VUB starts a curriculum in mechanical/electrotechnical engineering in Dutch.
- 1969-1970: Prof. (Major) Marcel Verlinden teaches Electronics on the ULB-Campus Solbosch. While vacuum tubes and sometimes bipolar transistors are still the predominant devices, he teaches MOSFETs.
- 1969-1970 VUB – ULB split: VUB becomes an independent university – in the aftermath of “Leuven Vlaams”, Belgium gradually becomes a federal state between 1970 (3 communities are created) and 2014.
- 1970-1971: Oscar Steenhaut joins VUB from Louisiana State University – Baton Rouge, and Jacques Tiberghien becomes the first full time assistant.
Johan Stiens, the ETRO representative in the working group of “Digital for Climate” of the Alliance for IoT and Edge Computing Innovation, https://aioti.eu/
is co-author with a group of 20 people of a final report (+ 80 pages) on “IoT and Edge Computing Carbon Footprint Measurement Methodology”  (Release 1.1)
https://aioti.eu/wp-content/uploads/2022/11/AIOTI-Carbon-Footprint-Methodology-Report-Final-R1.1.pdf
The goals of this report are multifold:
• To help users of IoT and Edge Computing technologies and services, to understand and make informed choices on how to assess the carbon footprint of solutions and services they use, and to as well to measure how these methodologies support carbon footprint reduction of their use
• To present initiatives and standards, existing methodologies of measuring ICT carbon footprint and how they can be applied to IoT and Edge Computing
• To present selection methodology criteria and how to measure benefits of using them in reducing carbon footprint when using IoT and Edge Computing technologies and services for several industrial domains
• To propose a method of calculating the carbon avoided emissions in an industrial sector/domain, when ICT is used as an enabling technology
A research team of ETRO was selected (under supervision of Prof. Johan Stiens and Dr. Bruno Da Silva) to participate to the I-LOVE-SCIENCE FESTIVAL (15-16-17/10/2021) in BRUSSELS with demos of wearable devices.
During the festival, the visitor will be introduced to various existing portable/wearable medical measuring instruments and their operating principles by Angel, Joan, Salar, Vlad, Bruno and Johan. The visitor will be able to experiment with various technologies to detect different physiological signals of his/her body under different conditions of activity. The measurement systems are specially designed for educational purposes, such that the user will also be able to change settings themselves and check their influence (a little engineering experience).
In addition to the technical-medical aspects, the social relevance will also be explained: how this measurement technology can contribute to preventive medicine, extremely important for social cost reduction of the health care costs.
On April 2nd 2026 at 16:00, Sebastian Amador Sanchez will defend their PhD entitled “Advancing Landmark Localization through Deep Segmentation for Reliable Malalignment Assessment in Lower Limb Radiographs”.
Everybody is invited to attend the presentation in room I.2.01 or online via this link.
Knee osteoarthritis affects millions worldwide and is frequently associated with lower limb malalignment. Clinical assessment of malalignment relies on manual landmark identification in X-ray images, a time-consuming process prone to interobserver variability. While most automated approaches use regression-based deep learning, this thesis investigates image segmentation with circular masks centered on landmark locations as an alternative strategy.
First, we introduce a segmentation-guided coordinate regression framework that integrates a segmentation network with a coordinate regression branch, trained end-to-end. This hybrid approach improves localization accuracy over standard regression and increases robustness compared to standalone segmentation, thereby mitigating false positives and missed detections.
Second, we optimize segmentation-based methods by evaluating architectures, post-processing strategies, and mask sizes. A fully convolutional model trained with radius-15 masks, combined with adaptive threshold-based centroid extraction, outperformed conventional landmark localization approaches, with improved performance in knee phenotype classification.
Third, we propose a Siamese network trained with a contrastive loss for quality control that detects inaccurate predictions by comparing image patches to reference embeddings. The method reliably identifies errors exceeding 2.0 mm and estimates their magnitude, outperforming baseline methods.
Overall, this thesis advances the field of landmark localization and demonstrates its clinical relevance for the automated assessment of lower limb malalignment. Beyond landmark localization accuracy, our contributions address robustness and failure identification, two aspects that are often overlooked yet vital for future clinical deployment.