Dual-Branch Squeeze-Fusion-Excitation Module for Cross-Modality Registration of Cardiac SPECT and CT

TL;DR

This paper introduces a novel dual-branch squeeze-fusion-excitation module for improved cross-modality registration of cardiac SPECT and CT images, significantly enhancing attenuation correction accuracy.

Contribution

The paper proposes a new DuSFE module that effectively fuses multi-modality features at multiple layers, addressing limitations of previous CNN-based registration methods.

Findings

Lower registration errors with DuSFE compared to previous methods

More accurate attenuation correction in cardiac SPECT imaging

Effective feature fusion at multiple spatial dimensions

Abstract

Single-photon emission computed tomography (SPECT) is a widely applied imaging approach for diagnosis of coronary artery diseases. Attenuation maps (u-maps) derived from computed tomography (CT) are utilized for attenuation correction (AC) to improve diagnostic accuracy of cardiac SPECT. However, SPECT and CT are obtained sequentially in clinical practice, which potentially induces misregistration between the two scans. Convolutional neural networks (CNN) are powerful tools for medical image registration. Previous CNN-based methods for cross-modality registration either directly concatenated two input modalities as an early feature fusion or extracted image features using two separate CNN modules for a late fusion. These methods do not fully extract or fuse the cross-modality information. Besides, deep-learning-based rigid registration of cardiac SPECT and CT-derived u-maps has not been investigated before. In this paper, we propose a Dual-Branch Squeeze-Fusion-Excitation (DuSFE) module for the registration of cardiac SPECT and CT-derived u-maps. DuSFE fuses the knowledge from multiple modalities to recalibrate both channel-wise and spatial features for each modality. DuSFE can be embedded at multiple convolutional layers to enable feature fusion at different spatial dimensions. Our studies using clinical data demonstrated that a network embedded with DuSFE generated substantial lower registration errors and therefore more accurate AC SPECT images than previous methods.