Skip to main content
Fig. 5 | European Radiology Experimental

Fig. 5

From: Fully automated convolutional neural network-based affine algorithm improves liver registration and lesion co-localization on hepatobiliary phase T1-weighted MR images

Fig. 5

Manual registration of baseline static (a) and follow-up moving (b, c) images show aligned hepatic veins. A 1.0-cm focal liver observation is seen in segment IVa in baseline (a) but not seen on follow-up image (circle) (b). In c, follow-up registered image using the automated affine algorithm parameters applied to the whole image shows correspondence to the baseline image, including the presence of the same focal observation in segment IVa.

Back to article page