Deep Learning-based Adaptive Image Combination for Signal-Dropout Suppression in Liver DWI
Fasil Gadjimuradov1,2, Thomas Benkert2, Marcel Dominik Nickel2, and Andreas Maier1
1Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany, 2Magnetic Resonance, Siemens Healthcare GmbH, Erlangen, Germany
Signal-dropouts caused by pulsation can affect a large portion of repetitions in liver DWI, compromising its diagnostic value. Rather than computing a uniform average, we propose to locally suppress signal-dropouts by an adaptive average using weight maps estimated by a CNN.
Figure 3: First two columns: eight repetitions of a DW liver
slice (b = 800 s/mm2) with manually assigned labels. Last two
columns: corresponding weight maps produced by the network after processing all
patches using a sliding window. Locations with lower weight approximately
coincide with image regions affected by signal-dropouts.
Figure
4: Qualitative analysis of uniform and CNN-based adaptive averaging, compared
to the reference image obtained from averaging clean repetitions only. Using
the repetitions and weight maps from Figure 3, the proposed method is able to recover
signal which leads to higher agreement with the reference as confirmed by the
difference maps (5x) as well as the normalized root-mean-squared error (NRMSE)
and structural similarity (SSIM). Accordingly, elevated ADC values in the
affected liver lobe (ROI, yellow box) are corrected with the proposed method.