From the Department of Neurosurgery (O.P.L., K.M., S.S., K.S., P.M.K.), Brown University Warren Alpert Medical School, Providence, Rhode Island
Department of Diagnostic Imaging (Z.Z., L.B., Z.J., G.R., S.C., J.L.B.), Brown University Warren Alpert Medical School, Providence, Rhode Island.
AJNR Am J Neuroradiol. 2024 Oct 3;45(10):1536-1544. doi: 10.3174/ajnr.A8372.
Symptoms of normal pressure hydrocephalus (NPH) are sometimes refractory to shunt placement, with limited ability to predict improvement for individual patients. We evaluated an MRI-based artificial intelligence method to predict postshunt NPH symptom improvement.
Patients with NPH who underwent MRI before shunt placement at a single center (2014-2021) were identified. Twelve-month postshunt improvement in mRS, incontinence, gait, and cognition were retrospectively abstracted from clinical documentation. 3D deep residual neural networks were built on skull-stripped T2-weighted and FLAIR images. Predictions based on both sequences were fused by additional network layers. Patients from 2014-2019 were used for parameter optimization, while those from 2020-2021 were used for testing. Models were validated on an external validation data set from a second institution ( = 33).
Of 249 patients, = 201 and = 185 were included in the T2-based and FLAIR-based models according to imaging availability. The combination of T2-weighted and FLAIR sequences offered the best performance in mRS and gait improvement predictions relative to models trained on imaging acquired by using only 1 sequence, with area under the receiver operating characteristic (AUROC) values of 0.7395 [0.5765-0.9024] for mRS and 0.8816 [0.8030-0.9602] for gait. For urinary incontinence and cognition, combined model performances on predicting outcomes were similar to FLAIR-only performance, with AUROC values of 0.7874 [0.6845-0.8903] and 0.7230 [0.5600-0.8859].
Application of a combined algorithm by using both T2-weighted and FLAIR sequences offered the best image-based prediction of postshunt symptom improvement, particularly for gait and overall function in terms of mRS.
常压脑积水（NPH）的症状有时对抗分流术有抗性，对于个体患者的改善能力有限。我们评估了一种基于 MRI 的人工智能方法来预测分流术后 NPH 症状的改善。
在一个中心（2014-2021 年），我们识别了接受分流术前进行 MRI 的 NPH 患者。从临床记录中回顾性提取 12 个月时 mRS、尿失禁、步态和认知的分流术后改善情况。在去骨皮的 T2 加权和 FLAIR 图像上构建 3D 深度残差神经网络。通过额外的网络层融合基于两种序列的预测。2014-2019 年的患者用于参数优化，而 2020-2021 年的患者用于测试。在第二家机构的外部验证数据集（ = 33）上验证模型。
在 249 名患者中，根据成像可用性， = 201 名和 = 185 名患者分别纳入基于 T2 加权和 FLAIR 加权的模型。与仅使用 1 种序列采集的成像相比，T2 加权和 FLAIR 序列的组合在 mRS 和步态改善预测方面提供了最佳的性能，mRS 的接受者操作特征曲线（AUROC）值为 0.7395 [0.5765-0.9024]，步态为 0.8816 [0.8030-0.9602]。对于尿失禁和认知，联合模型在预测结果方面的表现与 FLAIR 仅表现相似，AUROC 值分别为 0.7874 [0.6845-0.8903]和 0.7230 [0.5600-0.8859]。
应用基于 T2 加权和 FLAIR 序列的联合算法提供了最佳的基于图像的术后症状改善预测，特别是对于步态和 mRS 整体功能。
