Self-supervised motion descriptor for cardiac phase detection in 4D CMR based on discrete vector field estimations

1 code implementation • 13 Sep 2022 • Sven Koehler, Tarique Hussain, Hamza Hussain, Daniel Young, Samir Sarikouch, Thomas Pickhardt, Gerald Greil, Sandy Engelhardt

Simultaneously, deep learning-based deformable image registration is able to estimate discrete vector fields which warp one time step of a CMR sequence to the following in a self-supervised manner.

Image Registration

Unsupervised Domain Adaptation from Axial to Short-Axis Multi-Slice Cardiac MR Images by Incorporating Pretrained Task Networks

1 code implementation • 19 Jan 2021 • Sven Koehler, Tarique Hussain, Zach Blair, Tyler Huffaker, Florian Ritzmann, Animesh Tandon, Thomas Pickardt, Samir Sarikouch, Heiner Latus, Gerald Greil, Ivo Wolf, Sandy Engelhardt

This is an improvement of $25\%$ in Dice for RV in comparison to direct application on axial slices.

Unsupervised Domain Adaptation

How well do U-Net-based segmentation trained on adult cardiac magnetic resonance imaging data generalise to rare congenital heart diseases for surgical planning?

2 code implementations • 10 Feb 2020 • Sven Koehler, Animesh Tandon, Tarique Hussain, Heiner Latus, Thomas Pickardt, Samir Sarikouch, Philipp Beerbaum, Gerald Greil, Sandy Engelhardt, Ivo Wolf

Our results confirm that current deep learning models can achieve excellent results (left ventricle dice of $0. 951\pm{0. 003}$/$0. 941\pm{0. 007}$ train/validation) within a single data collection.