Report on the AAPM deep-learning spectral CT Grand Challenge.
Report on the AAPM deep-learning spectral CT Grand Challenge.
复制标题
DOI：
10.1002/mp.16363
复制
发表时间：
2022-12
期刊：
影响因子：
3.8
通讯作者：
E. Sidky;Xiaochuan Pan
中科院分区：
文献类型：
--
作者：
E. Sidky;Xiaochuan Pan
本特别报告总结了2022年AAPM深度学习光谱计算机断层扫描（DL-光谱CT）图像重建的重大挑战。本挑战的目的是开发最准确的图像重建算法，用于解决与快速kV开关双能量CT扫描相关的逆问题，使用三个组织图分解。参与者可以选择使用深度学习（DL）、迭代或混合方法。方法：该挑战基于2D乳腺CT模拟，其中模拟乳腺体模由三种组织图组成：脂肪、纤维腺和钙化分布。幻影规范是随机的，因此可以为深度学习方法生成多个实现。模拟双能量扫描，其中连续视图的X射线源电势在50和80千伏（kV）之间交替。总共生成512个视图，每个源电压产生256个视图。我们生成50和80千伏的图像，通过使用过滤反投影（FBP）的负对数处理的传输数据。对于开发DL方法的参与者，可提供1000个案例。每个病例由三个512 x512组织图、50和80 kV传输数据集及其相应的FBP图像组成。然后，DL网络的目标是从传输数据、FBP图像或两者的组合中预测材质图。对于开发基于物理方法的参与者，所有所需的建模参数都可用：几何形状，光谱和组织衰减曲线。所提供的信息还允许混合方法，其中利用物理学以及关于从1000个训练案例导出的扫描对象的信息。最后的测试是通过计算均方根误差（RMSE）的预测组织图从100个新的情况下。结果收到了18个研究小组提交的测试阶段提交材料。在18份提交材料中，17份是使用涉及DL的算法获得的结果。只有第二名的完成团队开发了基于物理的图像重建算法。获胜和第二名的团队都有非常准确的结果，RMSE几乎是零到单浮点精度。前十名的结果也达到了高度的准确性;因此，这份特别报告概述了这些小组中的每一个开发的方法。结论：DL-能谱CT挑战赛成功建立了一个论坛，用于开发图像重建算法，解决与能谱CT相关的重要逆问题。
BACKGROUND This Special Report summarizes the 2022 AAPM Grand Challenge on Deep-Learning spectral Computed Tomography (DL-spectral CT) image reconstruction. PURPOSE The purpose of the challenge is to develop the most accurate image reconstruction algorithm possible for solving the inverse problem associated with a fast kV switching dual-energy CT scan using a three tissue-map decomposition. Participants could choose to use a deep-learning (DL), iterative, or a hybrid approach. METHODS The challenge is based on a 2D breast CT simulation, where the simulated breast phantom consists of three tissue maps: adipose, fibroglandular, and calcification distributions. The phantom specification is stochastic so that multiple realizations can be generated for deep-learning approaches. A dual-energy scan is simulated where the X-ray source potential of successive views alternates between 50 and 80 kilovolts (kV). A total of 512 views are generated, yielding 256 views for each source voltage. We generate 50 and 80 kV images by use of filtered back-projection (FBP) on negative logarithm processed transmission data. For participants who develop a DL approach, 1000 cases are available. Each case consists of the three 512x512 tissue maps, 50 and 80 kV transmission data sets and their corresponding FBP images. The goal of the DL network would then be to predict the material maps from either the transmission data, FBP images, or a combination of the two. For participants developing a physics-based approach, all of the required modeling parameters are made available: geometry, spectra, and tissue attenuation curves. The provided information also allows for hybrid approaches where physics is exploited as well as information about the scanned object derived from the 1000 training cases. Final testing is performed by computation of root-mean-square-error (RMSE) for predictions on the tissue maps from 100 new cases. RESULTS Test phase submission were received from 18 research groups. Of the 18 submissions, 17 were results obtained with algorithms that involved DL. Only the second place finishing team developed a physics-based image reconstruction algorithm. Both the winning and second place teams had highly accurate results where the RMSE was nearly zero to single floating point precision. Results from the top ten also achieved a high degree of accuracy; and as a result this special report outlines the methodology developed by each of these groups. CONCLUSIONS The DL-spectral CT challenge successfully established a forum for developing image reconstruction algorithms that address an important inverse problem relevant for spectral CT.