Medical Deep Learning

Ongoing Projects

Thesis Proposals

LABEL: Segmentation of the anatomy in large-scale datasets under noisy and imperfect labels (Annotation-efficient deep learning for automatic medical image segmentation, Wang et al. 2021)

MEDICARE: Accelerated Reconstruction- Dynamic multi-coil MRI acceleration using Implicit Neural Representations and temporal regularization (CineJENSE: Simultaneous Cine MRI Image Reconstruction and Sensitivity Map Estimation using Neural Representations, Hemidi et al. 2023, submitted to STACOM Workshop at MICCAI 2023)

MEDICARE: Motion Compensation - Unsupervised Deep Learning Registration in undersampled cardiac MRI K- space data for respiratory motion compensation (LAPNet: Non-rigid Registration derived in k-space for Magnetic Resonance Imaging, Küstner et al. 2021)

MEIDIC-VTACH: (Bachelor thesis) Detection of abnormal ventricular beatsin surface time-series data (Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT, Chen et al. 2022)

Completed Projects

VIKOOB: Visual context information for optimising ventilation therapy
(funded by Federal Ministry of Economics and Technology)