发表机构
Rensselaer Polytechnic Institute（伦斯勒理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出PEEL方法，利用物理测量识别NIG回归中的不可识别纤维，通过冻结网络和MC教师标签估计偶然不确定性，在CT成像中实现高相关性和可容许性。
AI 中文摘要
正态逆伽马（NIG）回归无法从其边际Student-t似然中唯一识别：该似然决定了四个NIG参数的三个组合，并沿一维纤维保持恒定。我们利用独立的物理测量来识别该纤维。作为初步实现，重建网络接收一幅含噪的滤波反投影（FBP）图像，并首先仅通过Student-t负对数似然进行训练，以估计三个可识别坐标（gamma, alpha, c）。随后网络被冻结；通过其重建输出传播的重复物理噪声实现形成输出域偶然不确定性的蒙特卡洛（MC）教师标签。附加在冻结特征上的偶然性头部学习该标签，之后代数恢复（beta, nu）。在五个光子水平下的30个保留模拟对象上，单图像预测与独立的400次重复参考相比，合并Spearman相关性为0.832-0.951，图像内中位相关性为0.834-0.947，98.81-99.55%的评估像素满足代数可容许性条件。该方法不需要KL项、参考先验、证据正则化器或交叉损失权重。
英文摘要
Normal-inverse-gamma (NIG) regression is not uniquely identifiable from its marginal Student-t likelihood: the likelihood determines three combinations of four NIG parameters and is constant along a one-dimensional fiber. We identify that fiber using independent physical measurement. As an initial embodiment, a reconstruction network receives one noisy filtered-backprojection (FBP) image and is first trained only by Student-t negative log-likelihood to estimate the three identifiable coordinates (gamma, alpha, c). The network is then frozen; repeated physical-noise realizations propagated through its reconstruction output form a Monte Carlo (MC) teacher label for output-domain aleatoric variance. An aleatoric head attached to frozen features learns this label, after which (beta, nu) are recovered algebraically. On 30 held-out simulated objects at five photon levels, one-image predictions achieved pooled Spearman correlations of 0.832-0.951 against independent 400-repeat references, median within-image correlations were 0.834-0.947, and 98.81-99.55% of evaluated pixels satisfied the algebraic admissibility condition. The method needs no KL term, reference prior, evidence regularizer, or cross-loss weight.
Comments10 pages, 3 figures, 1 table. Proof-of-concept study of physics-enabled identification of NIG uncertainty in CT imaging
