DuSFE: Dual-Channel Squeeze-Fusion-Excitation co-attention for cross-modality registration of cardiac SPECT and CT

• Main Authors: Chen, X. (Author), Duncan, J.S (Author), Guo, X. (Author), Liu, C. (Author), Miller, E.J (Author), Onofrey, J.A (Author), Sinusas, A.J (Author), Xie, H. (Author), Zhang, J. (Author), Zhou, B. (Author)
• Format: Article
• Language: English
• Published: Elsevier B.V. 2023
• Subjects: Attenuation correction; Attenuation Correction; Cardiac single-photon emission computed tomography/computed tomography; Cardiac SPECT/CT; Cardiovascular disease; Convolution; Cross modality; Cross modality image registration; Deep learning; Diagnosis; Dual channel; Heart; Image registration; Images registration; Learning systems; Medical imaging; Myocardial perfusion; Particle beams; Perfusion imaging; Single photon emission computed tomography
• Online Access: View Fulltext in Publisher; View in Scopus

 Myocardial perfusion imaging (MPI) using single-photon emission computed tomography (SPECT) is widely applied for the diagnosis of cardiovascular diseases. Attenuation maps (μ-maps) derived from computed tomography (CT) are utilized for attenuation correction (AC) to improve the diagnostic accuracy of cardiac SPECT. However, in clinical practice, SPECT and CT scans are acquired sequentially, potentially inducing misregistration between the two images and further producing AC artifacts. Conventional intensity-based registration methods show poor performance in the cross-modality registration of SPECT and CT-derived μ-maps since the two imaging modalities might present totally different intensity patterns. Deep learning has shown great potential in medical imaging registration. However, existing deep learning strategies for medical image registration encoded the input images by simply concatenating the feature maps of different convolutional layers, which might not fully extract or fuse the input information. In addition, deep-learning-based cross-modality registration of cardiac SPECT and CT-derived μ-maps has not been investigated before. In this paper, we propose a novel Dual-Channel Squeeze-Fusion-Excitation (DuSFE) co-attention module for the cross-modality rigid registration of cardiac SPECT and CT-derived μ-maps. DuSFE is designed based on the co-attention mechanism of two cross-connected input data streams. The channel-wise or spatial features of SPECT and μ-maps are jointly encoded, fused, and recalibrated in the DuSFE module. DuSFE can be flexibly embedded at multiple convolutional layers to enable gradual feature fusion in different spatial dimensions. Our studies using clinical patient MPI studies demonstrated that the DuSFE-embedded neural network generated significantly lower registration errors and more accurate AC SPECT images than existing methods. We also showed that the DuSFE-embedded network did not over-correct or degrade the registration performance of motion-free cases. The source code of this work is available at https://github.com/XiongchaoChen/DuSFE_CrossRegistrationhttps://github.com/XiongchaoChen/DuSFE_CrossRegistration. © 2023