“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:

Research by Redona Brahimetaj and colleagues at ETRO-imec shows that the tissue surrounding breast microcalcifications can provide more diagnostic information than the calcium deposits themselves, opening new perspectives for breast cancer imaging.
Breast microcalcifications are tiny calcium deposits that can appear in breast tissue and are important indicators in breast cancer screening. Traditionally, imaging techniques have focused on the shape, size and distribution of these deposits to help distinguish benign from malignant lesions.
A new study led by Redona Brahimetaj at the Department of Electronics and Informatics (ETRO-imec) of Vrije Universiteit Brussel challenges this perspective. The research demonstrates that the tissue immediately surrounding individual microcalcifications contains valuable diagnostic information, potentially even more than the calcifications themselves.
Using high-resolution three-dimensional micro-computed tomography (micro-CT), the research team analysed 3,504 individual microcalcifications from 94 breast biopsy specimens, achieving a spatial resolution of approximately 8 micrometres.
By combining advanced medical image analysis, radiomics and machine-learning techniques, the researchers systematically investigated where the most useful diagnostic information originates: within the calcium deposits or in the surrounding breast tissue.
The results were striking. Including the surrounding tissue improved classification performance, with the area under the receiver operating characteristic curve (AUC) increasing from approximately 0.69 to 0.81.
Remarkably, analysing the surrounding tissue alone achieved comparable performance, demonstrating that the microenvironment around the calcifications is a particularly important source of diagnostic information.
This work highlights ETRO’s expertise in medical image processing, quantitative image analysis and artificial intelligence, and illustrates how advanced computational methods can reveal information that conventional imaging analysis may overlook.
By shifting attention from the calcifications themselves to the interface between calcium deposits and surrounding tissue, the research provides a new direction for developing quantitative imaging biomarkers.
Although the study used highly detailed images of biopsy specimens rather than conventional clinical breast images, its findings offer important insights that may guide future breast cancer imaging research. Further validation and investigation of the underlying tissue structures will be necessary before clinical applications can be considered.
The study was conducted through a collaboration between ETRO-imec, VUB’s Laboratory of Experimental Pathology, and the Departments of Pathology and Radiology at UZ Brussel.
The research brings together expertise in artificial intelligence, medical imaging, radiology and pathology, demonstrating the value of interdisciplinary collaboration in addressing challenging medical diagnostic problems.
Micro-CT Radiomics Reveals the Microcalcification-Surrounding Tissue Interface as the Diagnostic Epicenter of Breast Microcalcifications
Authors: Redona Brahimetaj, Jan Cornelis, Guillaume Courtoy, Wim Waelput, Inneke Willekens, Johan De Mey, Ramses Forsyth and Bart Jansen.
https://www.vub.be/en/news/beyond-calcification-vub-imec-researchers-identify
On May 27th 2024 at 16:00, Yifei Da will defend their PhD entitled “DATA-DRIVEN CAUSAL MODELLING FOR DE-BIASING SENTIMENT ANALYSIS MODELS AND MULTIVARIATE STOCK PRICE MOVEMENT PREDICTION”.
Everybody is invited to attend the presentation in room I.0.01, or digitally via this link.
In this thesis, we address the stock price movement prediction problem by investigating the interdependencies between sentiments from financial news and international stock markets in stock forecasting. To provide reliable sentiment analysis results, especially to reduce bias, we studied sentiment analysis methods and detected, evaluated, and mitigated bias that was picked up on and amplified by large pre-trained models. To retrieve intra- and inter-market interdependencies, we adopt the Transfer Entropy theory to detect and incorporate the information flow between financial news sentiment and the dynamics of the stock markets. We contribute to these two sub-tasks by (i) proposing a new method for debiasing sentiment analysis models that leverages the causal mediation analysis to identify the parts of the model primarily responsible for the bias and apply targeted counterfactual training for model debiasing. Furthermore, (ii) a causal-enhanced multi-modality model for multivariate stock price movement prediction is proposed based on establishing an accurate information flow propagation between stocks and sentiments. To repeatedly validate the feasibility, the Dow Jones Industrial Average indexes of 13 countries and daily financial news data from the New York Times are used in stock Price and Return forecasting.
On March 29th 2024 at 16::00, Lucas Santana will defend their PhD entitled “TOWARDS UNCHARTED TERRITORIES: HIGH-PERFORMANCE AND HIGH-BANDWIDTH RINGAMP-BASED DELTA-SIGMA ADCs”.
Everybody is invited to attend the presentation in room D.2.01, or digitally via this link.
Analog-to-digital (ADC) research often happens in an agnostic detachment from the intended application; although motivation is sometimes presented, it is not always implemented with the proposed prototype. Advancements in ADC linearity and speed enable applications that were nonexistent before to emerge, such as direct RF conversion and 8k camera recording. Most ADC architectures cover all regions of the performance space, being at the forefront of the state-of-the-art for some areas and not so much for others. This high coverage enables the use of the advantages and peculiarities of different architectures across different applications. One notable architecture that does not perform this is the Discrete Time (DT) Delta-Sigma Modulator (DSM) ADC, in which the published state-of-the-art bandwidth front is limited to 20 MHz. This work investigates this limitation, showing that it can be overcome with high-efficiency ring amplifiers (ringamps) and the correct design process. This work presents a prototype for a single loop 3rd-order DT DSM ADC based on ringamps for the loop filter that could double the bandwidth reached by DT DSM ADC at 47.5 MHz and achieve 67 dB of signal-tonoise and distortion ratio (SNDR) when clocked at 950 MHz. It also shows outstanding figures of merit (FoM): the Schreier FoM, FoMs is 167 dB and the Walden FoM, FoMw is 27 fJ per conversion step. The second prototype used time interleaving to improve the sampling rate and bandwidth further and used a noise-coupled (NC) noiseshaping (NS) SAR quantizer to enable aliased noise suppression. It achieved 1.4 GS/s of sampling rate, a decimated bandwidth of 70 MHz at a peak SNDR of 67 dB, with a power consumption of 32 mW; this translated to a FoMs of 160 dB and a FoMw of 143 fJ/c.s. Both prototypes were the first to pave the way to increase the bandwidth in DT DSM ADC efficiently and can still benefit from recent developments in ringamps and noise-shaping SAR ADCs, leading the architecture to conquer even more space in this uncharted territory.
An Innoviris-funded project, called eTailor with Treedy’s and ETRO-VUB for full-body scanner that extrapolates your size without you even having to take your clothes off. It will be deployed in the Decathlon shops (and not only) worldwide.
The IP behind this tech is for a part shared IP between VUB and Treedy’s. A VUB-Treedy’s patent was recently accepted covering the technology that enables estimating the body shape under clothing and taking automatically measurements on each scanned person.
eTailor is an example of how an industrial project should run: one could achieve both academic and industrial excellence.
This guide explains how to install and configure WireGuard with an MFA overlay using Defguard. The setup consists of three main steps, to be executed after requesting a token from ETRO_ICT@vub.be.
Once these steps are completed, your device will be ready to connect to the VPN using WireGuard with MFA authentication.
Go to:
Log in with your ETROVUB credentials. Use only your username, without @etrovub.be.

Click Edit profile in the top-right corner.
Enable TOTP — Time-Based One-Time Password — as your two-factor authentication method by clicking on the gear wheel next to TOTP. You may need to do this twice.

Use an authenticator app, or equivalent, to register Defguard by scanning the QR code. Once registered, enter the one-time password code to confirm.


Recovery codes are not strictly necessary, as ICT can intervene if needed. Click I have saved my codes.
Do not forget to save your changes.
If you are logged out, log back in using your authentication code.
Go to::
https://enroll.etrovub.be
Start the enrollment process.

Click Launch enrollment.
You will be asked to enter the token sent by your administrator.
Download and install the client for your operating system.

Once the client has been installed, open it
In the Defguard client, click Add instance in the left menu bar.

Enter the URL and token you received from your administrator.
For each supplementary device please request a new token at ETRO_ICT@vub.be

Choose a name for your device.

Once the instance has been created, click Connect for the Brussels location.

Use MFA to authenticate.

You are now successfully connected.

Good luck! You are virtually there!
Perhaps one of the remedies below helps