Xiongchao Chen1, Bo Zhou1, Luyao Shi1, Hui Liu2,3, Yulei Pang4, Rui Wang2,3, Edward J Miller2,5, Albert J Sinusas1,2,5, Chi Liu6,7. 1. Department of Biomedical Engineering, Yale University, New Haven, CT, USA. 2. Department of Radiology and Biomedical Imaging, Yale University, PO Box 208048, New Haven, CT, 06520-8048, USA. 3. Department of Engineering Physics, Tsinghua University, Beijing, People's Republic of China. 4. Department of Mathematics, Southern Connecticut State University, New Haven, CT, USA. 5. Department of Medicine (Cardiology), Yale University, New Haven, CT, USA. 6. Department of Biomedical Engineering, Yale University, New Haven, CT, USA. chi.liu@yale.edu. 7. Department of Radiology and Biomedical Imaging, Yale University, PO Box 208048, New Haven, CT, 06520-8048, USA. chi.liu@yale.edu.
Abstract
BACKGROUND: Attenuation correction (AC) using CT transmission scanning enables the accurate quantitative analysis of dedicated cardiac SPECT. However, AC is challenging for SPECT-only scanners. We developed a deep learning-based approach to generate synthetic AC images from SPECT images without AC. METHODS: CT-free AC was implemented using our customized Dual Squeeze-and-Excitation Residual Dense Network (DuRDN). 172 anonymized clinical hybrid SPECT/CT stress/rest myocardial perfusion studies were used in training, validation, and testing. Additional body mass index (BMI), gender, and scatter-window information were encoded as channel-wise input to further improve the network performance. RESULTS: Quantitative and qualitative analysis based on image voxels and 17-segment polar map showed the potential of our approach to generate consistent SPECT AC images. Our customized DuRDN showed superior performance to conventional network design such as U-Net. The averaged voxel-wise normalized mean square error (NMSE) between the predicted AC images by DuRDN and the ground-truth AC images was 2.01 ± 1.01%, as compared to 2.23 ± 1.20% by U-Net. CONCLUSIONS: Our customized DuRDN facilitates dedicated cardiac SPECT AC without CT scanning. DuRDN can efficiently incorporate additional patient information and may achieve better performance compared to conventional U-Net.
BACKGROUND: Attenuation correction (AC) using CT transmission scanning enables the accurate quantitative analysis of dedicated cardiac SPECT. However, AC is challenging for SPECT-only scanners. We developed a deep learning-based approach to generate synthetic AC images from SPECT images without AC. METHODS: CT-free AC was implemented using our customized Dual Squeeze-and-Excitation Residual Dense Network (DuRDN). 172 anonymized clinical hybrid SPECT/CT stress/rest myocardial perfusion studies were used in training, validation, and testing. Additional body mass index (BMI), gender, and scatter-window information were encoded as channel-wise input to further improve the network performance. RESULTS: Quantitative and qualitative analysis based on image voxels and 17-segment polar map showed the potential of our approach to generate consistent SPECT AC images. Our customized DuRDN showed superior performance to conventional network design such as U-Net. The averaged voxel-wise normalized mean square error (NMSE) between the predicted AC images by DuRDN and the ground-truth AC images was 2.01 ± 1.01%, as compared to 2.23 ± 1.20% by U-Net. CONCLUSIONS: Our customized DuRDN facilitates dedicated cardiac SPECT AC without CT scanning. DuRDN can efficiently incorporate additional patient information and may achieve better performance compared to conventional U-Net.