Skip to main content
European Radiology Experimental
Fig 6 | European Radiology Experimental

Fig 6

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

Fig 6

Baseline (a, d) and follow-up (b, c, e, and f) images. Manual registrations show the alignment of slices through anatomical references. However, focal observations are noted in different slice positions. The mismatch between focal observations and slice position negatively affects assessment as the observation in d may be interpreted as a new lesion. c, f On the automated affine registered follow-up images, focal liver observation correspondence is confirmed, and the diagnosis of previous existing growing lesion is made with higher confidence

Back to article page