D-Net: Siamese based Network with Mutual Attention for Volume Alignment

TL;DR

This paper introduces D-net, a novel 3D deep learning network that accurately aligns contrast and non-contrast CT scans without requiring templates, improving biomedical image registration tasks.

Contribution

D-net extends Siamese networks with mutual attention to estimate arbitrary rotations and translations in 3D CT scans without prior templates.

Findings

Outperforms existing alignment methods on preclinical CT data.

Effectively estimates arbitrary rotations and translations.

Does not require a standard template for alignment.

Abstract

Alignment of contrast and non-contrast-enhanced imaging is essential for the quantification of changes in several biomedical applications. In particular, the extraction of cartilage shape from contrast-enhanced Computed Tomography (CT) of tibiae requires accurate alignment of the bone, currently performed manually. Existing deep learning-based methods for alignment require a common template or are limited in rotation range. Therefore, we present a novel network, D-net, to estimate arbitrary rotation and translation between 3D CT scans that additionally does not require a prior standard template. D-net is an extension to the branched Siamese encoder-decoder structure connected by new mutual non-local links, which efficiently capture long-range connections of similar features between two branches. The 3D supervised network is trained and validated using preclinical CT scans of mouse tibiae with and without contrast enhancement in cartilage. The presented results show a significant improvement in the estimation of CT alignment, outperforming the current comparable methods.