基于黑质 MRI 的深度学习回归模型可有效预测帕金森综合征纹状体多巴胺转运体-SPECT 摄取。
Deep learning regressor model based on nigrosome MRI in Parkinson syndrome effectively predicts striatal dopamine transporter-SPECT uptake.
机构信息
Departments of Radiology, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnam, Republic of Korea.
Departments of Neurology, Seoul National University Bundang Hospital, Seoul National University College of Medicine, 82, Gumi-ro 173beon-gil, Bundang-gu, 13620, Seongnam, Republic of Korea.
出版信息
Neuroradiology. 2023 Jul;65(7):1101-1109. doi: 10.1007/s00234-023-03168-z. Epub 2023 May 20.
PURPOSE
Nigrosome imaging using susceptibility-weighted imaging (SWI) and dopamine transporter imaging using I-2β-carbomethoxy-3β-(4-iodophenyl)-N-(3-fluoropropyl)-nortropane (I-FP-CIT) single-photon emission computerized tomography (SPECT) can evaluate Parkinsonism. Nigral hyperintensity from nigrosome-1 and striatal dopamine transporter uptake are reduced in Parkinsonism; however, quantification is only possible with SPECT. Here, we aimed to develop a deep-learning-based regressor model that can predict striatal I-FP-CIT uptake on nigrosome magnetic resonance imaging (MRI) as a biomarker for Parkinsonism.
METHODS
Between February 2017 and December 2018, participants who underwent 3 T brain MRI including SWI and I-FP-CIT SPECT based on suspected Parkinsonism were included. Two neuroradiologists evaluated the nigral hyperintensity and annotated the centroids of nigrosome-1 structures. We used a convolutional neural network-based regression model to predict striatal specific binding ratios (SBRs) measured via SPECT using the cropped nigrosome images. The correlation between measured and predicted SBRs was evaluated.
RESULTS
We included 367 participants (203 women (55.3%); age, 69.0 ± 9.2 [range, 39-88] years). Random data from 293 participants (80%) were used for training. In the test set (74 participants [20%]), the measured and predicted I-FP-CIT SBRs were significantly lower with the loss of nigral hyperintensity (2.31 ± 0.85 vs. 2.44 ± 0.90) than with intact nigral hyperintensity (4.16 ± 1.24 vs. 4.21 ± 1.35, P < 0.01). The sorted measured I-FP-CIT SBRs and the corresponding predicted values were significantly and positively correlated (ρ = 0.7443; 95% confidence interval, 0.6216-0.8314; P < 0.01).
CONCLUSION
A deep learning-based regressor model effectively predicted striatal I-FP-CIT SBRs based on nigrosome MRI with high correlation using manually-measured values, enabling nigrosome MRI as a biomarker for nigrostriatal dopaminergic degeneration in Parkinsonism.
目的
利用磁敏感加权成像（SWI）进行神经黑磁共振成像（nigrosome-1）和利用碘-123-β-单-C （I-123-β-C）-β-羧基-3β-（4-碘苯基）-N-（3-氟丙基）-n-托烷（I-FP-CIT）单光子发射计算机断层扫描（SPECT）进行多巴胺转运蛋白成像，可用于评估帕金森病。帕金森病患者的神经黑磁共振成像 1 号神经黑磁共振成像（nigrosome-1）中的神经黑磁共振成像（nigrosome-1）和纹状体多巴胺转运蛋白摄取减少；然而，定量分析只能通过 SPECT 进行。在这里，我们旨在开发一种基于深度学习的回归模型，可以预测纹状体 I-FP-CIT 在神经黑磁共振成像上的摄取情况，作为帕金森病的生物标志物。
方法
在 2017 年 2 月至 2018 年 12 月期间，我们纳入了因疑似帕金森病而接受 3T 脑部 MRI 检查（包括 SWI 和 I-FP-CIT SPECT）的患者。两位神经放射科医生评估了黑磁共振成像的黑磁共振成像（nigral hyperintensity）和神经黑磁共振成像-1 结构的中心点。我们使用基于卷积神经网络的回归模型，利用裁剪后的神经黑磁共振成像图像来预测通过 SPECT 测量的纹状体特异性结合率（SBR）。评估了测量的 SBR 和预测的 SBR 之间的相关性。
结果
我们纳入了 367 名参与者（203 名女性（55.3%）；年龄，69.0±9.2[范围，39-88]岁）。随机选取 293 名参与者（80%）的数据进行训练。在测试集（74 名参与者[20%]）中，与完整的神经黑磁共振成像相比，测量的和预测的 I-FP-CIT SBR 随着神经黑磁共振成像的丧失而显著降低（2.31±0.85 比 2.44±0.90）（P<0.01）。按排序的测量的 I-FP-CIT SBR 与相应的预测值之间存在显著的正相关关系（ρ=0.7443；95%置信区间，0.6216-0.8314；P<0.01）。
结论
基于神经黑磁共振成像的深度学习回归模型可以有效地预测纹状体 I-FP-CIT SBR，与使用手动测量值的相关性较高，从而使神经黑磁共振成像成为帕金森病中黑质纹状体多巴胺能变性的生物标志物。
Zotero 插件