Department of Nuclear Medicine, E.O. "Ospedali Galliera", Mura delle Cappuccine 14, 16128, Genoa, Italy.
I.N.F.N. - Section of Pisa, Pisa, Italy.
Eur Radiol. 2021 Sep;31(9):7003-7011. doi: 10.1007/s00330-021-07779-z. Epub 2021 Mar 8.
To test the performance of a 3D convolutional neural network (CNN) in analysing brain [F]DOPA PET/CT in order to identify patients with nigro-striatal neurodegeneration. We evaluated the robustness of the 3D CNN by testing it against a manual regional analysis of the striata by using a striatal-to-occipital ratio (SOR).
We analyzed patients who had undergone [F]DOPA PET/CT from 2016 to 2018. Two examiners interpreted PET/CT images as positive or negative. Only patients with at least 2 years of follow-up and an ascertained neurological diagnosis were included. A 3D CNN was developed to evaluate [F]DOPA PET/CT and refine the diagnosis of movement disorder. This system required training and testing, which were carried out on 2/3 and 1/3 of patients, respectively. A regional analysis was also conducted by drawing region of interest on T1-weighted 3D MRI scans, on which the [F]DOPA PET images were first co-registered.
Ninety-eight patients were enrolled: 43 presented nigro-striatal degeneration and 55 negative cases used as controls. After training on 69 patients, the diagnostic performance of the 3D CNN was then calculated in 29 patients. Sensitivity, specificity, negative predictive value, positive predictive value and accuracy were 100%, 89%, 100%, 85% and 93%, respectively. When we compared the 3D CNN results with the SOR analysis, we found that the two patients falsely classified as positive by the 3D CNN procedure showed SOR values ≤ 5 percentile of the negative cases' distribution.
3D CNNs are able to interpret [F]DOPA PET/CT properly, revealing patients affected by Parkinson's disease.
• [F]DOPA PET/CT is a sensitive diagnostic tool to identify patients with nigro-striatal neurodegeneration. • A semiquantitative evaluation of the images allows a more confident interpretation of the PET findings. • 3D convolutional neural network allows an accurate interpretation of 18F-DOPA PET/CT images, revealing patients affected by Parkinson's disease.
测试三维卷积神经网络（CNN）在分析脑[F]DOPA PET/CT 以识别黑质纹状体神经退行性变患者中的性能。我们通过使用纹状体-枕叶比（SOR）对纹状体进行手动区域分析来测试 3D CNN 的稳健性。
我们分析了 2016 年至 2018 年期间进行[F]DOPA PET/CT 的患者。两名检查者将 PET/CT 图像解释为阳性或阴性。仅纳入至少随访 2 年且神经学诊断明确的患者。开发了一种 3D CNN 来评估[F]DOPA PET/CT 并改善运动障碍的诊断。该系统需要培训和测试，分别在 2/3 和 1/3 的患者上进行。还通过在 T1 加权 3D MRI 扫描上绘制感兴趣区域来进行区域分析，首先在其上对[F]DOPA PET 图像进行配准。
共纳入 98 例患者：43 例表现为黑质纹状体变性，55 例阴性病例作为对照。在对 69 例患者进行培训后，然后在 29 例患者中计算了 3D CNN 的诊断性能。敏感性、特异性、阴性预测值、阳性预测值和准确性分别为 100%、89%、100%、85%和 93%。当我们将 3D CNN 结果与 SOR 分析进行比较时，我们发现被 3D CNN 程序错误分类为阳性的两名患者的 SOR 值低于阴性病例分布的第 5 个百分位数。
3D CNN 能够正确解释[F]DOPA PET/CT，显示出受帕金森病影响的患者。
•[F]DOPA PET/CT 是一种敏感的诊断工具，可用于识别黑质纹状体神经退行性变患者。•对图像进行半定量评估可以更自信地解释 PET 结果。•3D 卷积神经网络可以准确解释 18F-DOPA PET/CT 图像，显示出受帕金森病影响的患者。
