Seung Su Yoon1,2, Michaela Schmidt2, Manuela Rick2, Teodora Chitiboi3, Puneet Sharma3, Tilman Emrich4,5, Christoph Tilmanns6, Ralph Waßmuth6, Jens Wetzl2, and Andreas Maier1
1Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany, 2Magnetic Resonance, Siemens Healthcare GmbH, Erlangen, Germany, 3Siemens Medical Solutions USA, Inc., Princeton, NJ, United States, 4Department of Radiology, University Medical Center, Johannes Gutenberg-University Mainz, Mainz, Germany, 5Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, Charleston, SC, United States, 6Diagnostikum Berlin, Berlin, Germany
1Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany, 2Magnetic Resonance, Siemens Healthcare GmbH, Erlangen, Germany, 3Siemens Medical Solutions USA, Inc., Princeton, NJ, United States, 4Department of Radiology, University Medical Center, Johannes Gutenberg-University Mainz, Mainz, Germany, 5Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, Charleston, SC, United States, 6Diagnostikum Berlin, Berlin, Germany
To standardize and automate the
selection of correct inversion time to null healthy myocardium, we propose an
automated deep-learning-based system and validate the system with a prospective
study. The system achieved high accuracy in the range of observers’ annotation.
Figure 1: Overview of the proposed
system based on an example. A SAX TI scout series is used as an input for the
system. By applying the localization, style transfer and segmentation network,
the time point where the mean pixel intensities from myocardium signal is
minimum is selected as TInull. By examining the 80ms window starting
from the TInull, the time point where the difference between the
average LV, RV blood pool and myocardium signal is highest, is selected as TIcontrast.
Figure 4: Qualitative results of the system output and the
observers' annotation. The illustrated images show the first 16 phases of the standardized
TI scout series. In a), b) the results on 1.5T are shown. In c), d) the results
of 3.0T data are shown. In d) the observer 2 was selected one frame later than TIcontrast. However, the deviation is negligible. In e) series
acquired without- while in f) with compressed sensing on the same patient with
4min 30s in between.