# Siamese Networks with Location Prior for Landmark Tracking in Liver Ultrasound Sequences

## TL;DR

This paper introduces a fully-convolutional Siamese network with a location prior for accurate landmark tracking in liver ultrasound sequences, demonstrating effective application of CNNs with temporal regularization.

## Contribution

It presents the first successful application of CNNs for landmark tracking in liver ultrasound, combining a Siamese network with a temporal consistency model.

## Key findings

- Achieved competitive results on CLUST dataset.
- First CNN-based approach for this tracking problem.
- Effective use of temporal regularization enhances tracking accuracy.

## Abstract

Image-guided radiation therapy can benefit from accurate motion tracking by ultrasound imaging, in order to minimize treatment margins and radiate moving anatomical targets, e.g., due to breathing. One way to formulate this tracking problem is the automatic localization of given tracked anatomical landmarks throughout a temporal ultrasound sequence. For this, we herein propose a fully-convolutional Siamese network that learns the similarity between pairs of image regions containing the same landmark. Accordingly, it learns to localize and thus track arbitrary image features, not only predefined anatomical structures. We employ a temporal consistency model as a location prior, which we combine with the network-predicted location probability map to track a target iteratively in ultrasound sequences. We applied this method on the dataset of the Challenge on Liver Ultrasound Tracking (CLUST) with competitive results, where our work is the first to effectively apply CNNs on this tracking problem, thanks to our temporal regularization.