Detecting cardiovascular diseases using ECG scans and explainable artificial intelligence
An explainable AI framework for quantifying the stability of deep learning models analyzing ECG scans under controlled image perturbations.
Senior ML Systems Engineer · PhD Researcher · Data Scientist
I’m a Senior ML Systems Engineer at Graylight Imaging and a PhD candidate in Computer Science at the Silesian University of Technology. I build production-grade machine learning systems and research deep learning methods that make them more interpretable and reliable — from explainable ensemble architectures and self-supervised representation learning to GPU-accelerated inference pipelines deployed in clinical settings.
My work spans scientific imaging beyond medicine, including satellite and seismic data, with a focus on turning complex real-world signals into deployable, trustworthy AI. I have co-authored publications in npj Digital Medicine, IEEE ICIP, MICCAI, and Computer Methods and Programs in Biomedicine, and I’m a co-inventor on Roche-issued patents for automated medical image analysis.
An explainable AI framework for quantifying the stability of deep learning models analyzing ECG scans under controlled image perturbations.
A deep learning ensemble framework for detecting cardiac arrhythmias and predicting atrial fibrillation recurrence from ECG scans.
A genetic programming algorithm for building deep learning ensembles for ECG arrhythmia classification.