文献速递心脏核医学

基于三维双挤压激励残差密集网络的专用心脏SPECT无CT衰减校正

CT-free attenuation correction for dedicated cardiac SPECT using a 3D dual squeeze-and-excitation residual dense network.
PubMed 文献 · J Nucl Cardiol · 2021-06-03

研究开发了基于深度学习的DuRDN网络,从无衰减校正的SPECT图像生成合成AC图像,使用172例临床SPECT/CT负荷/静息心肌灌注研究进行训练、验证和测试。定量和定性分析显示该方法能生成一致的SPECT AC图像,且DuRDN性能优于U-Net,平均体素归一化均方误差为2.01±1.01% vs 2.23±1.20%。

要点

  • DuRDN可从无AC的SPECT图像生成合成AC图像,无需CT扫描。
  • DuRDN性能优于传统U-Net网络设计。
  • 额外编码BMI、性别和散射窗信息可进一步提升网络性能。

核心结论

  • 定制的DuRDN网络可实现专用心脏SPECT的无CT衰减校正,并能有效整合额外患者信息,性能可能优于传统U-Net。

研究设计与样本

  • 使用定制双挤压激励残差密集网络(DuRDN)从无AC的SPECT图像生成合成AC图像。
  • 172例匿名临床混合SPECT/CT负荷/静息心肌灌注研究用于训练、验证和测试。
  • 额外将BMI、性别和散射窗信息编码为通道级输入以改进网络性能。

主要发现

  • 基于图像体素和17节段极图的定量与定性分析显示该方法有潜力生成一致的SPECT AC图像。
  • DuRDN预测AC图像与真实AC图像的平均体素归一化均方误差为2.01±1.01%,U-Net为2.23±1.20%。

临床怎么用

  • 对于仅有SPECT的扫描仪,可利用DuRDN从无AC的SPECT图像生成合成AC图像,辅助定量分析。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

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.

来源:J Nucl Cardiol,查看原文。版权归原作者所有。

引用

  1. Chen X, Zhou B, Shi L, et al. CT-free attenuation correction for dedicated cardiac SPECT using a 3D dual squeeze-and-excitation residual dense network. J Nucl Cardiol. 2021. PMID: 34085168. doi:10.1007/s12350-021-02672-0

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。