Report on the AAPM deep-learning sparse-view CT grand challenge.
Report on the AAPM deep-learning sparse-view CT grand challenge.
复制标题
作者：
该挑战的目的是找到用于稀疏视图CT图像重建的深度学习技术，该技术可以在理想条件下产生最小RMSE，从而解决深度学习是否可以解决成像中的逆问题。挑战设置涉及2D乳腺CT模拟，其中模拟乳腺体模具有随机纤维腺体结构和高对比度斑点。幻影允许任意大的训练集生成完全已知的真理。训练集由4000个病例组成，其中每个病例由真实图像、128视图正弦图数据和相应的128视图滤波反投影（FBP）图像组成。训练网络以从正弦图或FBP数据预测真实图像。不提供几何信息。参与的算法进行了测试的数据集，包括100个新的情况下。大约有60个小组参与了验证阶段的挑战，25个小组提交了测试阶段的结果沿着关于他们深度学习方法的报告。获胜的团队将重建精度提高了两个数量级，超过了我们之前对类似测试问题的基于CNN的研究。DL稀疏视图挑战提供了一个独特的机会，可以检查用于解决稀疏视图CT逆问题的最先进的深度学习技术。
The purpose of the challenge is to find the deep-learning technique for sparse-view CT image reconstruction that can yield the minimum RMSE under ideal conditions, thereby addressing the question of whether or not deep learning can solve inverse problems in imaging. The challenge set-up involves a 2D breast CT simulation, where the simulated breast phantom has random fibro-glandular structure and high-contrast specks. The phantom allows for arbitrarily large training sets to be generated with perfectly known truth. The training set consists of 4000 cases where each case consists of the truth image, 128-view sinogram data, and the corresponding 128-view filtered back-projection (FBP) image. The networks are trained to predict the truth image from either the sinogram or FBP data. Geometry information is not provided. The participating algorithms are tested on a data set consisting of 100 new cases. About 60 groups participated in the challenge at the validation phase, and 25 groups submitted test-phase results along with reports on their deep-learning methodology. The winning team improved reconstruction accuracy by two orders of magnitude over our previous CNN-based study on a similar test problem. The DL-sparse-view challenge provides a unique opportunity to examine the state-of-the-art in deep-learning techniques for solving the sparse-view CT inverse problem.