Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY, 10065, USA.
Department of Neurology, Memorial Sloan Kettering Cancer Center, New York, NY, 10065, USA.
J Digit Imaging. 2022 Dec;35(6):1662-1672. doi: 10.1007/s10278-022-00654-3. Epub 2022 May 17.
In large clinical centers a small subset of patients present with hydrocephalus that requires surgical treatment. We aimed to develop a screening tool to detect such cases from the head MRI with performance comparable to neuroradiologists. We leveraged 496 clinical MRI exams collected retrospectively at a single clinical site from patients referred for any reason. This diagnostic dataset was enriched to have 259 hydrocephalus cases. A 3D convolutional neural network was trained on 16 manually segmented exams (ten hydrocephalus) and subsequently used to automatically segment the remaining 480 exams and extract volumetric anatomical features. A linear classifier of these features was trained on 240 exams to detect cases of hydrocephalus that required treatment with surgical intervention. Performance was compared to four neuroradiologists on the remaining 240 exams. Performance was also evaluated on a separate screening dataset of 451 exams collected from a routine clinical population to predict the consensus reading from four neuroradiologists using images alone. The pipeline was also tested on an external dataset of 31 exams from a 2nd clinical site. The most discriminant features were the Magnetic Resonance Hydrocephalic Index (MRHI), ventricle volume, and the ratio between ventricle and brain volume. At matching sensitivity, the specificity of the machine and the neuroradiologists did not show significant differences for detection of hydrocephalus on either dataset (proportions test, p > 0.05). ROC performance compared favorably with the state-of-the-art (AUC 0.90-0.96), and replicated in the external validation. Hydrocephalus cases requiring treatment can be detected automatically from MRI in a heterogeneous patient population based on quantitative characterization of brain anatomy with performance comparable to that of neuroradiologists.
在大型临床中心，一小部分患者出现需要手术治疗的脑积水。我们旨在开发一种筛选工具，以便从头部 MRI 中检测到这种情况，其性能可与神经放射科医生相媲美。我们利用单个临床站点回顾性收集的 496 例临床 MRI 检查，这些患者因任何原因就诊。该诊断数据集经过扩充，包含 259 例脑积水病例。在 16 例手动分割的检查中（10 例脑积水）训练了一个 3D 卷积神经网络，然后该网络用于自动分割其余 480 例检查并提取体积解剖特征。在 240 例检查中，使用这些特征的线性分类器训练以检测需要手术干预的脑积水病例。在其余 240 例检查中，将性能与四位神经放射科医生进行了比较。还在从常规临床人群中收集的 451 例单独的筛查数据集上评估了性能，以仅使用图像来预测四位神经放射科医生的共识读数。该管道还在来自第二个临床站点的 31 例外部数据集上进行了测试。最具鉴别力的特征是磁共振脑积水指数（MRHI）、脑室体积和脑室与脑体积之比。在匹配灵敏度的情况下，机器和神经放射科医生在两个数据集上检测脑积水的特异性没有显著差异（比例检验，p>0.05）。ROC 性能优于最新技术（AUC 0.90-0.96），并在外部验证中得到复制。基于脑解剖结构的定量特征，可以从 MRI 中自动检测需要治疗的脑积水病例，其性能可与神经放射科医生相媲美，适用于异质患者人群。
