用于PET合成的3D分割引导基于风格的生成对抗网络
3D Segmentation Guided Style-based Generative Adversarial Networks for PET Synthesis
AI总结：
针对低剂量PET转全剂量问题，提出SGSGAN，通过风格调制生成器和分割任务联合引导提升图像纹理及感兴趣区域合成质量。
摘要：
全剂量正电子发射断层扫描（PET）成像中潜在的放射性危害仍然令人担忧，而低剂量图像的质量在临床应用中始终不尽如人意。因此，将低剂量PET图像转换为全剂量图像具有重要意义。以往基于深度学习方法的研究通常直接提取层次化特征进行重建。我们注意到，每个特征的重要性各不相同，应当对其进行差异化加权，以便神经网络能够捕捉细微信息。此外，在某些应用中，对部分感兴趣区域的合成非常重要。为此，我们提出了一种新颖的分割引导基于风格的生成对抗网络（SGSGAN），用于PET合成。（1）我们提出了一种采用风格调制的基于风格的生成器，该调制在转换过程中专门控制层次化特征，以生成具有更真实纹理的图像。（2）我们采用任务驱动策略，将分割任务与生成对抗网络（GAN）框架相结合，以提升转换性能。大量实验表明，我们的整体框架在PET合成方面具有优越性，尤其是在那些感兴趣区域上。
英文摘要：
Potential radioactive hazards in full-dose positron emission tomography (PET) imaging remain a concern, whereas the quality of low-dose images is never desirable for clinical use. So it is of great interest to translate low-dose PET images into full-dose. Previous studies based on deep learning methods usually directly extract hierarchical features for reconstruction. We notice that the importance of each feature is different and they should be weighted dissimilarly so that tiny information can be captured by the neural network. Furthermore, the synthesis on some regions of interest is important in some applications. Here we propose a novel segmentation guided style-based generative adversarial network (SGSGAN) for PET synthesis. (1) We put forward a style-based generator employing style modulation, which specifically controls the hierarchical features in the translation process, to generate images with more realistic textures. (2) We adopt a task-driven strategy that couples a segmentation task with a generative adversarial network (GAN) framework to improve the translation performance. Extensive experiments show the superiority of our overall framework in PET synthesis, especially on those regions of interest.
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。
