Agenda

MSc SPS Thesis presentation

Dynamic Graph Topology Identification: A Kalman Filtering Approach

Anja Kroon

Complex systems and networks, including financial, brain, transport, and social networks, can be modeled as graphs. Learning their connectivity is valuable because structure drives dynamics, enabling prediction, monitoring, and control. Applications include understanding diseases such as Alzheimer’s, epilepsy, and other neurological disorders. Past work has emphasized static graphs with fixed connectivity, while more recent efforts address dynamic graphs that better reflect real-world networks. To accommodate time variation, online and recursive methods update connectivity estimates as new node signals arrive.

An online algorithm for graph topology identification, Kalman Dynamic Online GTI (KalDO GTI), has been developed where the adjacency is the hidden state of a state–space model and is updated via a recursive Kalman filter. Beyond state tracking, the state transition matrix is also estimated online through an optimization loop and is refined with Adam-based updates under sparsity, masking, and structural priors. This two-tier structure, sequential Kalman prediction–correction for adjacency tracking and batch optimization for state dynamics learning, yields a recursive yet adaptive framework suited for online, streaming data. In direct comparison with streaming LASSO and prediction–correction methods, the algorithm is competitive across regimes and particularly robust under high measurement noise. Experiments on synthetic networks with aggressive dynamic regimes validate the approach and show similar or better performance compared to existing methods.

Additional information ...


MSc SPS Thesis presentation

Automated Classification of Photic Stimulation EEG Responses for Improved Epilepsy Diagnosis

Giacomo Zanardini

Epilepsy is a common neurological disorder, but its diagnosis remains difficult when screening EEGs lack interictal epileptiform discharges (IEDs). Intermittent photic stimulation (IPS) can reveal abnormal responses associated with epilepsy; however, its clinical interpretation is often subjective, inconsistent, and sometimes inconclusive., and sometimes inconclusive. This thesis explores the automatic

classification of EEG responses to IPS using machine learning to improve diagnostic accuracy and reliability.

Two datasets are analysed: the Temple University Hospital (TUH) Epilepsy Corpus and clinical recordings from Erasmus MC. A structured pipeline is developed, comprising preprocessing, feature extraction across temporal, spectral, wavelet, and connectivity domains, and classification with interpretable models such as XGBoost and stacked ensemble approaches. To ensure robust generalization, leave-one-subject-out cross-validation is employed.

This work demonstrates that IPS EEG segments contain informative features capable of distinguishing epileptic from non-epileptic patients, even in the absence of IEDs, thereby aiding early diagnosis and reducing the risk of misdiagnosis. Furthermore, the use of explainability tools highlights candidate electrophysiological markers, providing valuable insights and suggesting new hypotheses for future investigation.


PhD Thesis Defence

Model-Based Processing in Ultrasound Imaging: Sparse Reconstruction and Coded Excitation

Didem Doğan Başkaya

Ultrasound is a widely used real-time imaging modality to diagnose patients. Ultrasound imaging has several modes of operation such as ultrafast Doppler which, due to the high frame-rates, is particularly suited to image blood flow inside bodily organs such as the brain. Despite its success, the ultrafast imaging technique has some downsides such as lower overall signal-to-noise ratio (SNR), especially in deeper regions due to the use of unfocussed transmissions. This thesis explores the use of advanced signal processing methods such as model-based image reconstruction to regain some of the loss in SNR.

The first part of the thesis focus on advanced model-based image reconstruction techniques, incorporating complex priors or statistical assumptions about the signal and noise instead of using a simple physical propagation model. Conventional ultrasound beamforming techniques, such as the delay-and-sum (DAS) beamformer, perform well in many clinical settings; however, they face challenges in applications requiring high structural detail or SNR, such as vascular imaging. This thesis explores deterministic and statistical model-based vascular image reconstruction techniques to improve SNR, resolution, and clarity of fine vascular details. The proposed techniques exploit the joint sparsity of the vasculature images at different time instants. These methods enhance the depiction of vascular structures while increasing SNR and suppressing background noise and artifacts.

A large part of the thesis focuses on the sparse Bayesian learning (SBL) techniques. Starting with classical SBL, this thesis introduces the application of block-sparsity-based SBL techniques, such as pattern-coupled sparse Bayesian learning with fixed-point iterations and correlated sparse Bayesian learning. Although some of the proposed techniques are not computationally efficient yet for real-time ultrasound imaging, they do provide a new contribution to signal processing and computational imaging fields.

The final chapter of the thesis focuses on improving the ultrasound transmission to enhance the SNR. An optimized coded excitation technique has been proposed as an alternative to standard coded excitation techniques. By keeping the computational complexity to a modest level, the codes are optimized to increase the SNR without a significant loss in the image resolution. The Cramér-Rao lower bound (CRB) minimization and a faster alternative Fisher information matrix (FIM) maximization have been proposed to optimize the codes. The optimized codes are tested on simulated data to demonstrate their potential for flow imaging.

To sum up, this thesis contributes to the ultrasound blood flow imaging area through solutions on image reconstruction algorithms and ultrasound transmissions to overcome current limitations and challenges. This thesis explores using advanced modelbased signal processing methods to improve image quality. Therefore, this work contributes new strategies that can inspire future research and clinical applications in vascular ultrasound imaging.