MSB Online Seminar: Deep Learning in Dynamic Cardiac MRI Reconstruction

Titel: Deep Learning in Dynamic Cardiac MRI Reconstruction

Sprecher:  Hossam El Rewaidy,  GCB Doktorand in der Arbeitsgruppe „Bild-basierte biomedizinische Modellierung” (Menze) und Harvard Medical School (Cardiac Magnetic Resonance Center)

Datum und Uhrzeit: Dienstag, 26. Januar 2021, 13:00 Uhr

Abstract: Cardiac MR cine imaging allows accurate and reproducible assessment of cardiac function. However, MRI is associated with a slow acquisition process which not only limits the spatial and temporal resolutions of the cardiac images but is also challenging in patients with breath‐holding difficulty or non‐sinus rhythms. In this talk, we will present a multi‐domain convolutional neural network (MD‐CNN)  for fast reconstruction of highly undersampled radial cine images to reduce the scan time.