Material decomposition from photon-counting CT using a convolutional neural network and energy-integrating CT training labels.
Material decomposition from photon-counting CT using a convolutional neural network and energy-integrating CT training labels.
复制标题
DOI：
10.1088/1361-6560/ac7d34
复制
发表时间：
2022-07-18
影响因子：
3.5
通讯作者：
Badea, Cristian T.
中科院分区：
文献类型：
--
作者：
Nadkarni, Rohan;Allphin, Alex;Clark, Darin P.;Badea, Cristian T.
光子计数CT（PCCT）具有比能量积分CT更好的剂量效率和光谱分辨率，有利于材料的分解。不幸的是，由于光子计数检测器（PCD）中的光谱失真，基于PCCT的材料分解的准确性受到限制。在这项工作中，我们展示了一种深度学习（DL）方法，该方法可以补偿PCD中的光谱失真，并通过使用高剂量多能量积分探测器（EID）数据提供的分解图作为训练标签来提高材料分解的准确性。我们使用3D U-网络架构，并将PCD滤波反投影（FBP）重建（FBP 2Decomp），PCD迭代重建（Iter 2Decomp）和PCD分解（Decomp 2Decomp）作为输入的网络进行比较。我们发现，我们的Iter 2Decomp方法性能最好，但DL优于矩阵求逆分解，无论输入如何。与PCD矩阵反演分解相比，Iter 2Decomp在碘（I）图中的均方根误差（RMSE）降低了27.50%，在光电效应（PE）图中的RMSE降低了59.87%。此外，它增加了结构相似性（SSIM）的1.92%，6.05%，和9.33%的I，康普顿散射（CS），和PE地图，分别。当从碘和钙小瓶中进行测量时，Iter 2Decomp提供了与多EID分解的良好一致性。一个限制是由我们的DL方法引起的一些模糊，当使用Iter 2Decomp时，从具有PCD矩阵求逆分解的50%调制传递函数（MTF）下的1.98线对/mm降低到50%MTF下的1.75线对/mm。总的来说，这项工作表明，我们的DL方法与高剂量多EID衍生的分解标签是有效的，从PCD数据生成更准确的材料图。像这样更准确的临床前光谱PCCT成像可以用于开发在治疗诊断学（治疗和诊断）领域显示前景的纳米颗粒。
Photon-counting CT (PCCT) has better dose efficiency and spectral resolution than energy-integrating CT, which is advantageous for material decomposition. Unfortunately, the accuracy of PCCT-based material decomposition is limited due to spectral distortions in the photon-counting detector (PCD). In this work, we demonstrate a deep learning (DL) approach that compensates for spectral distortions in the PCD and improves accuracy in material decomposition by using decomposition maps provided by high-dose multi-energy-integrating detector (EID) data as training labels. We use a 3D U-net architecture and compare networks with PCD filtered backprojection (FBP) reconstruction (FBP2Decomp), PCD iterative reconstruction (Iter2Decomp), and PCD decomposition (Decomp2Decomp) as the input. We found that our Iter2Decomp approach performs best, but DL outperforms matrix inversion decomposition regardless of the input. Compared to PCD matrix inversion decomposition, Iter2Decomp gives 27.50% lower root mean squared error (RMSE) in the iodine (I) map and 59.87% lower RMSE in the photoelectric effect (PE) map. In addition, it increases the structural similarity (SSIM) by 1.92%, 6.05%, and 9.33% in the I, Compton scattering (CS), and PE maps, respectively. When taking measurements from iodine and calcium vials, Iter2Decomp provides excellent agreement with multi-EID decomposition. One limitation is some blurring caused by our DL approach, with a decrease from 1.98 line pairs/mm at 50% modulation transfer function (MTF) with PCD matrix inversion decomposition to 1.75 line pairs/mm at 50% MTF when using Iter2Decomp. Overall, this work demonstrates that our DL approach with high-dose multi-EID derived decomposition labels is effective at generating more accurate material maps from PCD data. More accurate preclinical spectral PCCT imaging such as this could serve for developing nanoparticles that show promise in the field of theranostics (therapy and diagnostics).
登录
查看更多内容
影响因子：
12.4
作者：
Ashton JR;Castle KD;Qi Y;Kirsch DG;West JL;Badea CT
通讯作者：
Badea CT
DOI：
10.1016/j.nima.2008.03.080
发表时间：
2008-06-11
影响因子：
1.4
作者：
Ponchut, Cyril
通讯作者：
Ponchut, Cyril
影响因子：
3.8
作者：
Taguchi, Katsuyuki;Iwanczyk, Jan S.
通讯作者：
Iwanczyk, Jan S.
影响因子：
3.8
作者：
Taguchi, Katsuyuki;Frey, Eric C.;Barber, William C.
通讯作者：
Barber, William C.
影响因子：
3.8
作者：
Gong H;Tao S;Rajendran K;Zhou W;McCollough CH;Leng S
通讯作者：
Leng S