University of Heidelberg
Faculty of Medicine Mannheim
University Hospital Mannheim
Genauere MRT-Auswertungen für MS-Patienten durch Künstliche Intelligenz
Modellprojekt mit CKM Beteiligung im Rahmen des Innovationswettbewerbs "KI für KMU" soll die Behandlung von MS-Patienten verbessern more
CKM receives DFG funding for Project "Prediktion von Therapieansprechen und Outcome beim lokal fortgeschrittenen Rektum-Karzinom mittels Radiomics und Deep Learning: eine beispielhafte Anwendung für eine allgemein verwendbare, Deep Learning basierte Prozessierungs-Pipeline für die Bild-Klassifikation" read more.
Alena-Kathrin Schnurr presented on our research on AI in medical imaging @ Research Plus forum
read more

If you have questions concerning a specific publication please use this form with subject 'information about publications' and giving the full citation in the message body.

Collaborate Research Projects
Home > Publications > Abstract >

Accelerated Simultaneous Multi-Slice MRI using Subject-Specific Convolutional Neural Networks.

C. Zhang, S. Moeller, S. Weingärtner, K. U?urbil and M. Akçakaya

Conference record. Asilomar Conference on Signals, Systems \& Computers, 2018, pp.1636-1640

Simultaneous multi-slice or multi-band (SMS/MB) imaging allows accelerated coverage in magnetic resonance imaging (MRI). Multiple slices are excited and acquired at the same time, and reconstructed using the redundancies in receiver coil arrays, similar to parallel imaging. SMS/MB reconstruction is currently performed with linear reconstruction techniques. Recently, a nonlinear reconstruction method for parallel imaging, Robust Artificial-neural-networks for k-space Interpolation (RAKI) was proposed and shown to improve upon linear methods. This method uses convolutional neural networks (CNN) trained solely on subject-specific calibration data. In this study, we sought to extend RAKI to SMS/MB imaging reconstruction. CNN training was performed on calibration data acquired prior to SMS/MB imaging, in a manner consistent with the existing linear methods. These CNNs were used to reconstruct a time series of functional MRI (fMRI) data. CNN network parameters were optimized using an extensive search of the parameter space. With these optimal parameters, RAKI substantially improves image quality compared to a commonly used linear reconstruction algorithm, especially for high acceleration rates.

Contact: Prof. Dr. Frank Zöllner last modified: 25.01.2021
to top of page