Department of Medicine, University of British Columbia, Vancouver, BC, V6T 1Z3, Canada.
Author to whom any correspondence should be addressed.
Phys Med Biol. 2020 Dec 18;65(23):235004. doi: 10.1088/1361-6560/abc230.
Measurement of stimulus-induced dopamine release and other types of transient neurotransmitter response (TNR) from dynamic positron emission tomography (PET) images typically suffers from limited detection sensitivity and high false positive (FP) rates. Measurement of TNR of a voxel-level can be particularly problematic due to high image noise. In this work, we perform voxel-level TNR detection using artificial neural networks (ANN) and compare their performance to previously used standard statistical tests. Different ANN architectures were trained and tested using simulated and real human PET imaging data, obtained with the tracer [C]raclopride (a D2 receptor antagonist). A distinguishing feature of our approach is the use of 'personalized' ANNs that are designed to operate on the image from a specific subject and scan. Training of personalized ANNs was performed using simulated images that have been matched with the acquired image in terms of the signal, resolution, and noise. In our tests of TNR detection performance, the F-test of the linear parametric neurotransmitter PET model fit residuals was used as the reference method. For a moderate TNR magnitude, the areas under the receiver operating characteristic curves in simulated tests were 0.64 for the F-test and 0.77-0.79 for the best ANNs. At a fixed FP rate of 0.01, the true positive rates were 0.6 for the F-test and 0.8-0.9 for the ANNs. The F-test detected on average 28% of a 8.4 mm cluster with a strong TNR, while the best ANN detected 47%. When applied to a real image, no significant abnormalities in the ANN outputs were observed. These results demonstrate that personalized ANNs may offer a greater detection sensitivity of dopamine release and other types of TNR compared to previously used method based on the F-test.
从动态正电子发射断层扫描（PET）图像中测量刺激诱导的多巴胺释放和其他类型的瞬态神经递质反应（TNR）通常受到有限的检测灵敏度和高假阳性（FP）率的限制。由于图像噪声高，对体素级 TNR 的测量可能特别成问题。在这项工作中，我们使用人工神经网络（ANN）进行体素级 TNR 检测，并将其性能与以前使用的标准统计测试进行比较。使用模拟和真实人体 PET 成像数据（使用示踪剂 [C]raclopride（D2 受体拮抗剂）获得）对不同的 ANN 架构进行了训练和测试。我们方法的一个区别特征是使用“个性化”ANN，这些 ANN 旨在对特定受试者和扫描的图像进行操作。个性化 ANN 的训练是使用在信号、分辨率和噪声方面与所获取图像匹配的模拟图像进行的。在我们对 TNR 检测性能的测试中，线性参数神经递质 PET 模型拟合残差的 F 检验被用作参考方法。对于适度的 TNR 幅度，模拟测试中接收器操作特性曲线下的面积对于 F 检验为 0.64，对于最佳 ANN 为 0.77-0.79。在固定的 FP 率为 0.01 的情况下，F 检验的真阳性率为 0.6，而 ANN 的为 0.8-0.9。F 检验平均检测到 8.4 毫米强 TNR 簇的 28%，而最佳 ANN 检测到 47%。当应用于真实图像时，ANN 输出中没有观察到明显的异常。这些结果表明，与以前基于 F 检验的方法相比，个性化 ANN 可能提供更高的多巴胺释放和其他类型 TNR 的检测灵敏度。
