arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.09229physics.med-pheess.IV
收藏

在大脑锥束CT的深度学习重建中使用不确定性

Using Uncertainty in Deep Learning Reconstruction for Cone-Beam CT of the Brain

Pengwei Wu, Alejandro Sisniega, Ali Uneri, Runze Han, Craig Jones, Prasad Vagdargi, Xiaoxuan Zhang, Mark Luciano, William Anderson, Jeffrey Siewerdsen

摘要:

超越传统锥形束CT(CBCT)系统极限的对比度分辨率对于高质量的脑部成像至关重要。我们提出了一种深度学习重建方法(称为DL-Recon),该方法基于合成图像中的统计不确定性,将物理原理重建模型与基于DL的图像合成集成在一起。开发了一种合成网络,用于从未校正的滤波反投影(FBP)图像生成合成CBCT图像(DL合成)。为了提高可推广性(包括训练中未观察到的病变的准确表示),使用贝叶斯推断技术(Monte-Carlo dropout)计算DL合成的逐体素认知不确定性。在高不确定性区域,DL-重建方法结合了来自基于物理的重建模型和伪影校正投影数据的信息。提出了两种形式的DL-重建方法:(i)通过DL不确定性加权的DL-合成和FBP(DL-FBP)的图像域融合;以及(ii)使用DL-合成来计算基于DL不确定性的空间变化正则化项(DL-MBIR)的基于模型的迭代图像重建(MBIR)优化。DL合成图像中的误差与合成估计中的不确定性相关。与FBP和PWLS相比,DL-Recon方法(DL-FBP和DL-MBIR)显示噪声降低约50%(在匹配的空间分辨率下),图像均匀性改善约40-70%。单独的常规DL合成在模拟和真实脑病变中表现出约10-60%的病变对比度低估和约5-40%的病变分割准确度(Dice系数)降低,这表明训练数据中看不到的结构缺乏可靠性/可推广性。DL-FBP和DL-MBIR通过直接合并来自高不确定性区域中的测量的信息来提高重建的准确性。

英文摘要:

Contrast resolution beyond the limits of conventional cone-beam CT (CBCT) systems is essential to high-quality imaging of the brain. We present a deep learning reconstruction method (dubbed DL-Recon) that integrates physically principled reconstruction models with DL-based image synthesis based on the statistical uncertainty in the synthesis image. A synthesis network was developed to generate a synthesized CBCT image (DL-Synthesis) from an uncorrected filtered back-projection (FBP) image. To improve generalizability (including accurate representation of lesions not seen in training), voxel-wise epistemic uncertainty of DL-Synthesis was computed using a Bayesian inference technique (Monte-Carlo dropout). In regions of high uncertainty, the DL-Recon method incorporates information from a physics-based reconstruction model and artifact-corrected projection data. Two forms of the DL-Recon method are proposed: (i) image-domain fusion of DL-Synthesis and FBP (DL-FBP) weighted by DL uncertainty; and (ii) a model-based iterative image reconstruction (MBIR) optimization using DL-Synthesis to compute a spatially varying regularization term based on DL uncertainty (DL-MBIR). The error in DL-Synthesis images was correlated with the uncertainty in the synthesis estimate. Compared to FBP and PWLS, the DL-Recon methods (both DL-FBP and DL-MBIR) showed ~50% reduction in noise (at matched spatial resolution) and ~40-70% improvement in image uniformity. Conventional DL-Synthesis alone exhibited ~10-60% under-estimation of lesion contrast and ~5-40% reduction in lesion segmentation accuracy (Dice coefficient) in simulated and real brain lesions, suggesting a lack of reliability / generalizability for structures unseen in the training data. DL-FBP and DL-MBIR improved the accuracy of reconstruction by directly incorporating information from the measurements in regions of high uncertainty.

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。

↑