Data Science Seminar

Deep Learning-based Magnetic Resonance Fingerprinting

Magnetic Resonance Fingerprinting (MRF) is a recently developed quantitative Magnetic Resonance Imaging technique. The sequence acquires multiple image contrasts, resulting in so-called fingerprints for every voxel by changing acquisition parameters. These fingerprints are used to reconstruct quantitative maps containing information about the physical state of the underlying tissues. This talk first will give an introduction to the quantitative acquisition and the State-of-the-art reconstruction methods. Further, it will give an overview about Deep Learning applications for MRF reconstruction and show how the efficient Deep Learning-based reconstruction can be achieved.

Biosketch Elisabeth Hoppe

Elisabeth Hoppe received her Bachelor's degree in Medical Computer Science from the Ostbayerische Technische Hochschule Regensburg in 2015, and her Master's degree in Computer Science from the Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg in 2017. During her studies, she was always interested in applying technical knowledge for the development of new medical applications. During her master's studies, she joined the Pattern Recognition Lab (PRL) at FAU for her final thesis, where she worked together with a Siemens predevelopment group on a first prototype for Deep Learning-based reconstruction framework for the recently developed quantitative imaging method called MR Fingerprinting. At the moment, she continues her joint work with Siemens and PRL on quantitative MR acquisition and reconstruction methods for her PhD.

to top
powered by webEdition CMS