no code implementations • 2 May 2022 • Inês P. Machado, Esther Puyol-Antón, Kerstin Hammernik, Gastão Cruz, Devran Ugurlu, Ihsane Olakorede, Ilkay Oksuz, Bram Ruijsink, Miguel Castelo-Branco, Alistair A. Young, Claudia Prieto, Julia A. Schnabel, Andrew P. King
Cine cardiac magnetic resonance (CMR) imaging is considered the gold standard for cardiac function evaluation.
We consider inverse problems with both linear and non-linear forward models for computational MRI, and review the classical approaches for solving these.
The training of neural networks with Differentially Private Stochastic Gradient Descent offers formal Differential Privacy guarantees but introduces accuracy trade-offs.
The forward pass of the network takes explicit image dissimilarity gradient steps and generalized regularization steps parameterized by Convolutional Neural Networks (CNN) for a fixed number of iterations.
We present $\zeta$-DP, an extension of differential privacy (DP) to complex-valued functions.
Our dataset contains short axis images from 4 different MR scanners and 3 different pathology groups.
no code implementations • 16 Sep 2021 • Ines Machado, Esther Puyol-Anton, Kerstin Hammernik, Gastao Cruz, Devran Ugurlu, Bram Ruijsink, Miguel Castelo-Branco, Alistair Young, Claudia Prieto, Julia A. Schnabel, Andrew P. King
The framework consists of a deep learning model for the reconstruction of 2D+t cardiac cine MRI images from undersampled data, an image quality-control step to detect good quality reconstructions, followed by a deep learning model for bi-ventricular segmentation, a quality-control step to detect good quality segmentations and automated calculation of cardiac functional parameters.
In this paper, we present a cooperative framework for training image segmentation models and a latent space augmentation method for generating hard examples.
To this end, we solve the linear inverse problem of undersampled MRI reconstruction in a variational setting.
The iterative model is embedded into a deep recurrent neural network which learns to recover the image via exploiting spatio-temporal redundancies in complementary domains.
no code implementations • 10 Aug 2020 • Oliver Maier, Steven H. Baete, Alexander Fyrdahl, Kerstin Hammernik, Seb Harrevelt, Lars Kasper, Agah Karakuzu, Michael Loecher, Franz Patzig, Ye Tian, Ke Wang, Daniel Gallichan, Martin Uecker, Florian Knoll
The reference implementations were in good agreement, both visually and in terms of image similarity metrics.
We present a deep network interpolation strategy for accelerated parallel MR image reconstruction.
Purpose: To systematically investigate the influence of various data consistency layers, (semi-)supervised learning and ensembling strategies, defined in a $\Sigma$-net, for accelerated parallel MR image reconstruction using deep learning.
We explore an ensembled $\Sigma$-net for fast parallel MR imaging, including parallel coil networks, which perform implicit coil weighting, and sensitivity networks, involving explicit sensitivity maps.
Both linear and non-linear methods are covered, followed by a discussion of recent efforts to further improve parallel imaging using machine learning, and specifically using artificial neural networks.
Due to its high computational performance, i. e., reconstruction time of 193 ms on a single graphics card, and the omission of parameter tuning once the network is trained, this new approach to image reconstruction can easily be integrated into clinical workflow.