Deep Learning Achieves Neuroradiologist-Level Performance in Detecting Hydrocephalus Requiring Treatment.
Deep Learning Achieves Neuroradiologist-Level Performance in Detecting Hydrocephalus Requiring Treatment.
复制标题
深度学习在检测需要治疗的脑积水方面达到了神经放射科医生水平的性能。
DOI：
10.1007/s10278-022-00654-3
复制
发表时间：
2022
影响因子：
4.4
通讯作者：
Young,RobertJ
中科院分区：
文献类型：
--
作者：
Huang,Yu;Moreno,Raquel;Malani,Rachna;Meng,Alicia;Swinburne,Nathaniel;Holodny,AndreiI;Choi,Ye;Rusinek,Henry;Golomb,JamesB;George,Ajax;Parra,LucasC;Young,RobertJ
在大型临床中心，一小部分患者存在需要手术治疗的脑积水。我们的目的是开发一种筛选工具，以检测此类情况下，从头部MRI的性能与神经放射科医生。我们利用了在一个临床中心回顾性收集的496例临床MRI检查，这些检查来自因任何原因转诊的患者。该诊断数据集被丰富为259例脑积水病例。3D卷积神经网络在16个手动分割的检查（10个脑积水）上进行训练，随后用于自动分割剩余的480个检查并提取体积解剖特征。这些特征的线性分类器在240次检查中进行了训练，以检测需要手术干预治疗的脑积水病例。在其余240项检查中，将其性能与四名神经放射科医生进行比较。还对从常规临床人群中收集的451项检查的单独筛选数据集进行了性能评价，以预测仅使用图像的四名神经放射科医生的共识阅读。还在来自第二个临床研究中心的31项检查的外部数据集上测试了管道。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的比值。在匹配灵敏度时，机器和神经放射科医生的特异性在两个数据集上检测脑积水时均未显示出显著差异（比例检验，p> 0.05）。ROC性能与最新技术水平（AUC 0.90-0.96）相比更为有利，并在外部验证中重复。需要治疗的脑积水病例可以根据脑解剖结构的定量表征，在异质患者人群中从MRI中自动检测到，其性能与神经放射科医生相当。
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.