Kolloquiumsvortrag, PhD Tammy Riklin Raviv, Ben-Gurion-University of the Negev, Beer Sheva, Israel / am 09.06.2017
09.06.2017 von 13:30 bis 15:00
Institut für Informatik, Ludewig-Meyn-Straße 2, 24118 Kiel, Raum: Übungsraum 2/K
Titel:
Ensemble of Expert Deep Neural Networks for Spatio-Temporal Denoising of Contrast-Enhanced MRI Sequences
Abstract:
Abstract: Dynamic contrast-enhanced MRI (DCE-MRI) is an imaging protocol where MRI scans are acquired repetitively throughout the injection of a contrast agent. The analysis of dynamic scans is widely used for the detection and quantification of blood-brain barrier (BBB) permeability. Extraction of the pharmacokinetic (PK) parameters from the DCE-MRI concentration curves allows quantitative assessment of the integrity of the BBB functionality. However, curve fitting required for the analysis of DCE-MRI data is error-prone as the dynamic scans are subject to non-white, spatially dependent and anisotropic noise.
We present a novel spatio-temporal framework based on Deep Convolution Neural Networks (DCNNs) to address the DCE-MRI denoising challenges. This is accomplished by an ensemble of expert DCNNs constructed as deep autoencoders, where each is trained on a specific subset of the input space to accommodate different noise characteristics and curve prototypes. The most likely reconstructed curves are then chosen using a classifier DCNN followed by a quadratic programming optimization. As clean signals (ground-truth)
for training are not available, a fully automatic model for generating realistic training sets with complex nonlinear dynamics is introduced. The proposed approach has been applied to full and even temporally down-sampled DCE-MRI datasets acquired by MRI machines in different locations and of different manufacturers and is shown to favorably compare to state-of-the-art denoising methods.