A deep neural network for fast and accurate scatter estimation in quantitative SPECT/CT under challenging scatter conditions.
A deep neural network for fast and accurate scatter estimation in quantitative SPECT/CT under challenging scatter conditions.
复制标题
DOI：
10.1007/s00259-020-04840-9
复制
发表时间：
2020-12
影响因子：
9.1
通讯作者：
Dewaraja YK
中科院分区：
文献类型：
--
作者：
Xiang H;Lim H;Fessler JA;Dewaraja YK
一些放射性核素的精确定量SPECT成像的主要挑战是基于简单能量窗的散射估计方法的不足，其广泛用于临床系统。研究了用于SPECT/CT散射估计的深度学习方法，作为用于挑战SPECT放射性核素（例如90 Y）的计算昂贵的蒙特卡罗（MC）方法的替代方案。训练深度卷积神经网络（DCNN），以根据形成网络输入的测量的90 Y韧致辐射SPECT发射投影和CT衰减投影分别估计每个散射投影。13层深度架构由发射和衰减投影的单独路径组成，这些路径在最终卷积步骤之前连接。训练标签由体模中MC生成的“真实”散射投影组成（MC仅用于训练），相对于模型输出的均方差用作损失函数。测试数据集包括带有肺插入物的模拟球形体模、肝脏体模和90 Y放射栓塞后患者的测量值。比较了无散射校正的OS-EM SPECT重建（NO-SC）、真实散射（TRUE-SC）（仅适用于模拟数据）、DCNN估计散射（DCNN-SC）和先前开发的MC散射模型（MC-SC），包括90 Y PET（可用时）。使用DCNN-SC和MC-SC估计重建的图像的对比度恢复（CR）与噪声和肺部插入残差与噪声曲线相似。在10%的相同噪声水平下（跨多个实现），NO-SC、MC-SC、DCNN-SC和TRUE-SC的平均球CR分别为24%、52%、55%和67%。对于肝脏体模，NO-SC、MC-SC和DCNN-SC的肝脏插入物的平均CR分别为32%、73%和65%，而低浓度肝外插入物的平均对比噪声比（可见性指数）的相应值分别为2、19和61。在患者中，使用DCNN-SC进行SPECT重建的病变与肝脏摄取比率之间具有高度一致性（中位数4.8，范围0.02 - 13.8）与MC-SC相比（中位数4.0，范围0.13 - 12.1; CCC = 0.98）和90 Y PET（中位数4.9，范围0.02 - 11.2; CCC = 0.96），而与NO-SC的一致性较差（中位数2.8，范围0.3 - 7.2; CCC = 0.59）。经过训练的DCNN花费约40秒（使用台式计算机上的单个i5处理器）来生成患者扫描中所有128个视图的散射估计值，而使用12个处理器的MC散射模型花费约80分钟。对于包括患者研究的各种90 Y测试数据，我们证明了使用深度学习重建的图像与使用剂量测定和安全性相关指标的基于MC的散射估计之间的可比性能。这种方法可以通过改变训练数据推广到其他放射性核素，非常适合实时临床使用，因为速度快，比MC快几个数量级，同时保持高精度。
A major challenge for accurate quantitative SPECT imaging of some radionuclides is the inadequacy of simple energy window based scatter estimation methods, widely available on clinic systems. A deep learning approach for SPECT/CT scatter estimation is investigated as an alternative to computationally expensive Monte Carlo (MC) methods for challenging SPECT radionuclides, such as 90Y. A deep convolutional neural network (DCNN) was trained to separately estimate each scatter projection from the measured 90Y bremsstrahlung SPECT emission projection and CT attenuation projection that form the network inputs. The 13 layer deep architecture consisted of separate paths for the emission and attenuation projection that are concatenated before the final convolution steps. The training label consisted of MC-generated ‘true’ scatter projections in phantoms (MC is needed only for training) with the mean square difference relative to the model output serving as the loss function. The test data set included a simulated sphere phantom with a lung insert, measurements of a liver phantom and patients after 90Y radioembolization. OS-EM SPECT reconstruction without scatter correction (NO-SC), with the true scatter (TRUE-SC) (available for simulated data only), with the DCNN estimated scatter (DCNN-SC), and with a previously developed MC scatter model (MC-SC) were compared, including with 90Y PET when available. The contrast recovery (CR) vs. noise and lung insert residual error vs. noise curves for images reconstructed with DCNN-SC and MC-SC estimates were similar. At the same noise level of 10% (across multiple realizations) the average sphere CR was 24%, 52%, 55% and 67% for NO-SC, MC-SC, DCNN-SC and TRUE-SC, respectively. For the liver phantom, the average CR for liver inserts were 32%, 73% and 65% for NO-SC, MC-SC and DCNN-SC, respectively while the corresponding values for average contrast-to-noise ratio (visibility index) in low-concentration extra hepatic inserts were 2, 19 and 61, respectively. In patients, there was high concordance between lesion-to-liver uptake ratios for SPECT reconstruction with DCNN-SC (Median 4.8, range 0.02 −13.8) compared with MC-SC (Median 4.0, range 0.13 – 12.1; CCC = 0.98) and with 90Y PET (Median 4.9, range 0.02 – 11.2; CCC = 0.96) while the concordance with NO-SC was poor (Median 2.8, range 0.3 – 7.2; CCC = 0.59). The trained DCNN took ~ 40 seconds (using a single i5 processor on a desktop computer) to generate the scatter estimates for all 128 views in a patient scan, compared to ~ 80 min for the MC scatter model using 12 processors. For diverse 90Y test data that included patient studies, we demonstrated comparable performance between images reconstructed with deep learning and MC based scatter estimates using metrics relevant for dosimetry and for safety This approach, that can be generalized to other radionuclides by changing the training data, is well suited for real-time clinical use because of the high speed, orders of magnitude faster than MC, while maintaining high accuracy.
登录
查看更多内容
影响因子：
9.3
作者：
Uribe, Carlos F.;Mathotaarachchi, Sulantha;Zukotynski, Katherine
通讯作者：
Zukotynski, Katherine
影响因子：
9.3
作者：
Minarik, David;Enqvist, Olof;Tragardh, Elin
通讯作者：
Tragardh, Elin
影响因子：
9.3
作者：
Elschot, Mattijs;Lam, Marnix G. E. H.;de Jong, Hugo W. A. M.
通讯作者：
de Jong, Hugo W. A. M.
影响因子：
20.6
作者：
Gong, Kuang;Berg, Eric;Qi, Jinyi
通讯作者：
Qi, Jinyi
影响因子：
3.8
作者：
Dewaraja, Yuni K.;Chun, Se Young;Fessler, Jeffrey A.
通讯作者：
Fessler, Jeffrey A.