MSc thesis projects - Biomedical signal processing

Generative AI for suppressing tinnitus

This MSc project aims to improve the current tinnitus-matching methods available through for example a literature study and / or the design and testing of a prototype. The project can still be shaped according to your interests or expertise. A literature study on the currently used methods for tinnitus-matching can be conducted. The design of a prototype may consist of an algorithm, application, or device using AI such as generative AI. Also, implementing a UI and designing an appropriate user experience can be important aspects of a tinnitus-matching method.

EEG-based Brain Signatures for Personalized Therapeutic Intervention in Chronic Pain

Chronic-pain management remains a complex clinical challenge, often requiring personalized therapeutic approaches. EEG data offers valuable insights into the underlying brain activity associated with chronic pain conditions. Traditional analysis methods may overlook crucial information, necessitating a focus on constructing forward models based on EEG-derived brain signatures. These models can facilitate personalized interventions by targeting specific brain regions implicated in pain processing. This thesis aims at developing advanced techniques for constructing forward models based on EEG-derived brain signatures in chronic pain patients. Machine learning (ML) and data-driven approaches will be utilized to identify and characterize unique brain signatures associated with different chronic pain conditions, including neuropathic and fibromyalgia pain. This will be the first key-step towards personalized therapeutic interventions through in-silico stimulation and computational modeling, with the ultimate goal of optimizing treatment strategies for individual patients.

Epilepsy diagnosis using multimodal machine learning

In this project we aim to build on this previous research and determine whether it is possible to accurately distinguish between patients with epilepsy and controls with a different diagnosis using multimodal machine learning. We use both the EEG and clinical information. On the one hand, the aim is to improve the information and treatment of patients with epilepsy, because we can more quickly assess who will benefit from starting anti-epileptic drugs. On the other hand, by visualizing the features on which a machine learning algorithm bases its classification, we hope to gain more insight into the underlying neurological mechanisms that contribute to the risk of epilepsy.

Thesis topics at CWI

Center for Mathematics and Computer Science, Amsterdam

Decoding Emotions: Advanced Analysis of Vocal Expressions in Children With Hearing Impairment

Detecting differences in vocal emotions of Children with and without hearing impairments. This project is a collaboration between TUDelft - SPS and Sophia Children’s Hospital at EMC Rotterdam.

Analysis of electrophysiologic data acquired on PhysioHeartTM platform (ex-vivo beating heart)

Development of automated and (semi) live analysis of electrophysiologic data acquired from an isolated ex-vivo beating porcine heart.

Nonlinear identification of the hemodynamic response in functional ultrasound

The goal of this thesis is use Volterra kernels to investigate the nonlinear characteristics of the functional ultrasound signal measure in the brain in response to external stimuli; and their dependence on the stimulus.

Audio processing in wireless earbuds (Several assignments with the company Dopple)

What can you do with an in-ear computer, 8 microphones, a motion sensor, and multiple wireless links?

Spectral Noise Estimation for Hearing Aids

Absolute Audio Labs BV (AAL) is an internationally recognised innovation leader in the field of advanced hearing, voice and safe listening embedded software applications. Most AAL applications are dependent on reliable noise estimation as the first step in the audio chain. In this assignment, the task is to develop an improved noise PSD estimator.

In ear (with hearing aid) based Biomedical Signal Processing

Over the last years, Sonion has developed an offering to measure Biomedical signals in the ear based on PPG technology. The goal of this project is to advance this technology in order extract information on the users' physiological condition.

Generalized signal models in MRI

Electrical Properties Tomography - Theory and Validation

Nonlinear Model Order Reduction Methods for Inverse Scattering Problems

Domain Integral Equation Preconditioning in Electromagnetics for Elongated Structures

Active Noise Reduction for MRIs

Patients who undergo MRI scanning or are treated with radiotherapy on a MRLinac in a mask suffer from acoustic noise produced by the MR scanner. The aim is to reduce acoustic noise burden to the patient.

Optimizing the analysis of auditory event-related potentials in EEG (with Erasmus Medical Center)

In this project we intend to predict variation in neurodevelopment from auditory event-related potentials (ERPs) measured with EEG. This project is a collaboration between TUDelft - CAS and Sophia Children’s Hospital at EMC Rotterdam.

Contactless determination of vital parameters for improved healthcare (with Intelliprove)

The aim of the project is to extract vital parameters such as heart rate from video, based on the principles of remote photopletysmography (rPPG) using signal processing techniques.

Heart rate extraction from speech signals

Assessment of patient’s therapy response based on smartphone data

Clinical trials are moving from the clinic towards inclusion of real-world data and measurements. This allows to study the effect of medication in a more continuous manner and also monitor objective aspects that were previously evaluated by structured interviews. To allow these measurements, the Centre for Human Drug Research (CHDR) has developed a platform that allows for home monitoring of the effect of medication. In this project, a close collaboration with the CHDR is foreseen, where algorithms will be developed to improve the current platform.

Cell-to-sensor distance estimation for epicardiac measurements

Develop improved data models for better understanding the principles underlying Atrial Fibrillation

Improving signal quality of a wearable device for electrocardiogram (ECG) measurement

(At PraxaSense) Motion artefact removal for a 2-electrode ECG

Dynamic brain network analysis

Cardiac Arrhythmia Data Analysis (several projects)

Atrial fibrillation is the most common cardiac arrhythmia. The mechanisms are poorly understood. Using high-resolution multichannel data sets, we try to derive data models and indicators.