arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.11852eess.IVphysics.med-ph
收藏

空间频率域和图像域感知损失函数的低剂量CT增强网络

Low-dose CT Enhancement Network with a Perceptual Loss Function in the Spatial Frequency and Image Domains

Kevin J. Chung, Roberto Souza, Richard Frayne, Ting-Yim Lee

摘要:

我们提出了一个双域级联的U-网(即“W-网”)在空间频率和图像域中操作,以增强低剂量CT(LDCT)图像,而不需要专有的X射线投影数据。中心切片定理促使使用空间频率域代替原始正弦图。数据来自AAPM低剂量大挑战。使用多尺度结构相似性和平均绝对误差损失函数训练傅立叶空间(F)和/或图像域(I)U-网和W-网的组合,以对滤波后的反投影(FBP)LDCT图像进行降噪,同时保持对诊断准确性重要的感知特征。深度学习增强在定量和定性性能方面优于FBP LDCT图像,双域W网优于单域U网级联。我们的研究结果表明,空间频率学习与图像域处理相结合,可以产生比仅图像域网络更好的LDCT增强。

英文摘要:

We propose a dual-domain cascade of U-nets (i.e. a "W-net") operating in both the spatial frequency and image domains to enhance low-dose CT (LDCT) images without the need for proprietary x-ray projection data. The central slice theorem motivated the use of the spatial frequency domain in place of the raw sinogram. Data were obtained from the AAPM Low-dose Grand Challenge. A combination of Fourier space (F) and/or image domain (I) U-nets and W-nets were trained with a multi-scale structural similarity and mean absolute error loss function to denoise filtered back projected (FBP) LDCT images while maintaining perceptual features important for diagnostic accuracy. Deep learning enhancements were superior to FBP LDCT images in quantitative and qualitative performance with the dual-domain W-nets outperforming single-domain U-net cascades. Our results suggest that spatial frequency learning in conjunction with image-domain processing can produce superior LDCT enhancement than image-domain-only networks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑