Semantic similarity metrics for image registration.

Image registration aims to find geometric transformations that align images. Most algorithmic and deep learning-based methods solve the registration problem by minimizing a loss function, consisting of a similarity metric comparing the aligned images, and a regularization term ensuring smoothness of the transformation. Existing similarity metrics like Euclidean Distance or Normalized Cross-Correlation focus on aligning pixel intensity values or correlations, giving difficulties with low intensity contrast, noise, and ambiguous matching. We propose a semantic similarity metric for image registration, focusing on aligning image areas based on semantic correspondence instead. Our approach learns dataset-specific features that drive the optimization of a learning-based registration model. We train both an unsupervised approach extracting features with an auto-encoder, and a semi-supervised approach using supplemental segmentation data. We validate the semantic similarity metric using both deep-learning-based and algorithmic image registration methods. Compared to existing methods across four different image modalities and applications, the method achieves consistently high registration accuracy and smooth transformation fields.

Metabolomics Reveals Heterogeneity in the Chemical Composition of Green and White Spears of Asparagus (A. officinalis).

Green and white asparagus are quite different crops but can be harvested from the same plant. They have distinct morphological differences due to their mode of cultivation and they are characterised by having contrasting appearance and flavour. Significant chemical differences are therefore expected. Spears from three varieties of both green and white forms, harvested in two consecutive seasons were analysed using headspace GC-MS and LC-MS with an untargeted metabolomic workflow. Mainly C5 and C8 alcohols and aldehydes, and phenolic compounds were more abundant in green spears, whereas benzenoids, monoterpenes, unsaturated aldehydes and steroidal saponins were more abundant in white ones. Previously reported key asparagus volatiles and non-volatiles were detected at similar or not significantly different levels in the two asparagus types. Spatial metabolomics revealed also that many volatiles with known positive aroma attributes were significantly more abundant in the upper parts of the spears and showed a decreasing trend towards the base. These findings provide valuable insights into the metabolome of raw asparagus, the contrasts between green and white spears as well as the different chemical distributions along the stem.