Salient Region Matching for Fully Automated MR-TRUS Registration

TL;DR

This paper introduces a fully automated framework for MR-TRUS prostate image registration using salient region matching, combining segmentation, rigid alignment, and deformable registration with a novel attention-based network.

Contribution

It presents a new salient region matching approach with a dual-stream encoder and cross-modal attention for improved multi-modality registration accuracy.

Findings

Outperforms several state-of-the-art methods on public dataset

Achieves accurate prostate registration results

Demonstrates effectiveness of salient region matching in multi-modality registration

Abstract

Prostate cancer is a leading cause of cancer-related mortality in men. The registration of magnetic resonance (MR) and transrectal ultrasound (TRUS) can provide guidance for the targeted biopsy of prostate cancer. In this study, we propose a salient region matching framework for fully automated MR-TRUS registration. The framework consists of prostate segmentation, rigid alignment and deformable registration. Prostate segmentation is performed using two segmentation networks on MR and TRUS respectively, and the predicted salient regions are used for the rigid alignment. The rigidly-aligned MR and TRUS images serve as initialization for the deformable registration. The deformable registration network has a dual-stream encoder with cross-modal spatial attention modules to facilitate multi-modality feature learning, and a salient region matching loss to consider both structure and intensity similarity within the prostate region. Experiments on a public MR-TRUS dataset demonstrate that our method achieves satisfactory registration results, outperforming several cutting-edge methods. The code is publicly available at https://github.com/mock1ngbrd/salient-region-matching.