End-to-end Ultrasound Frame to Volume Registration

TL;DR

This paper introduces FVR-Net, an end-to-end deep learning model that efficiently registers 2D ultrasound frames with 3D volumes for real-time prostate biopsy guidance, without hardware tracking.

Contribution

The novel FVR-Net architecture enables accurate, real-time 2D/3D ultrasound registration using a dual-branch feature extractor and differentiable sampling, addressing previous research gaps.

Findings

Achieves high registration accuracy in real-time scenarios

Outperforms existing methods in efficiency and accuracy

Does not require hardware tracking for registration

Abstract

Fusing intra-operative 2D transrectal ultrasound (TRUS) image with pre-operative 3D magnetic resonance (MR) volume to guide prostate biopsy can significantly increase the yield. However, such a multimodal 2D/3D registration problem is a very challenging task. In this paper, we propose an end-to-end frame-to-volume registration network (FVR-Net), which can efficiently bridge the previous research gaps by aligning a 2D TRUS frame with a 3D TRUS volume without requiring hardware tracking. The proposed FVR-Net utilizes a dual-branch feature extraction module to extract the information from TRUS frame and volume to estimate transformation parameters. We also introduce a differentiable 2D slice sampling module which allows gradients backpropagating from an unsupervised image similarity loss for content correspondence learning. Our model shows superior efficiency for real-time interventional guidance with highly competitive registration accuracy.