In positron emission tomography (PET) and X-ray computed tomography (CT), reducing radiation dose can cause significant degradation in image quality. For image quality enhancement in low-dose PET and CT, we propose a novel theoretical adversarial and variational deep neural network (DNN) framework relying on expectation maximization (EM) based learning, termed adversarial EM (AdvEM). AdvEM proposes an encoder–decoder architecture with a multiscale latent space, and generalized-Gaussian models enabling datum-specific robust statistical modeling in latent space and image space. The model robustness is further enhanced by including adversarial learning in the training protocol. Unlike typical variational-DNN learning, AdvEM proposes latent-space sampling from the posterior distribution, and uses a Metropolis–Hastings scheme. Unlike existing schemes for PET or CT image enhancement which train using pairs of low-dose images with their corresponding normal-dose versions, we propose a semi-supervised AdvEM (ssAdvEM) framework that enables learning using a small number of normal-dose images. AdvEM and ssAdvEM enable per-pixel uncertainty estimates for their outputs. Empirical analyses on real-world PET and CT data involving many baselines, out-of-distribution data, and ablation studies show the benefits of the proposed framework.

中文翻译：

---

用于变分深度学习的对抗性 EM：在低剂量 PET 和低剂量 CT 中半监督图像质量增强中的应用


在正电子发射断层扫描 (PET) 和 X 射线计算机断层扫描 (CT) 中，减少辐射剂量可能会导致图像质量显着下降。为了增强低剂量 PET 和 CT 中的图像质量，我们提出了一种新颖的理论对抗性和变分深度神经网络 (DNN) 框架，该框架依赖于基于期望最大化 (EM) 的学习，称为对抗性 EM (AdvEM)。 AdvEM 提出了一种具有多尺度潜在空间的编码器-解码器架构，以及广义高斯模型，可在潜在空间和图像空间中实现数据特定的鲁棒统计建模。通过将对抗性学习纳入训练协议中，模型的鲁棒性进一步增强。与典型的变分 DNN 学习不同，AdvEM 提出从后验分布中进行潜在空间采样，并使用 Metropolis-Hastings 方案。与使用低剂量图像对及其相应的正常剂量版本进行训练的现有 PET 或 CT 图像增强方案不同，我们提出了一种半监督 AdvEM (ssAdvEM) 框架，可以使用少量正常剂量图像进行学习。 AdvEM 和 ssAdvEM 可以对其输出进行每像素不确定性估计。对涉及许多基线、分布外数据和消融研究的真实 PET 和 CT 数据的实证分析显示了所提出框架的优点。