Automated grading of enlarged perivascular spaces in clinical imaging data of an acute stroke cohort using an interpretable, 3D deep learning framework.
Automated grading of enlarged perivascular spaces in clinical imaging data of an acute stroke cohort using an interpretable, 3D deep learning framework.
复制标题
DOI：
10.1038/s41598-021-04287-4
复制
发表时间：
2022-01-17
影响因子：
4.6
通讯作者：
Vagal A
中科院分区：
文献类型：
--
作者：
Williamson BJ;Khandwala V;Wang D;Maloney T;Sucharew H;Horn P;Haverbusch M;Alwell K;Gangatirkar S;Mahammedi A;Wang LL;Tomsick T;Gaskill-Shipley M;Cornelius R;Khatri P;Kissela B;Vagal A
血管周围间隙扩大（EPVS），特别是在卒中患者中，已被证明与1年随访时小血管疾病和认知障碍的其他指标密切相关。EPVS的典型分级通常具有挑战性且耗时，并且通常基于主观视觉评级量表。本研究的目的是开发一种可解释的3D神经网络，用于在全脑小血管疾病（CSVD）负荷的背景下，在异质性急性卒中队列中使用临床级成像对基底节水平的血管周围间隙扩大（EPVS）严重程度进行分级。使用2015年从5个区域医疗中心收集的262例急性卒中患者的回顾性队列的T2加权图像进行分析。患者的无至轻度EPVS（< 10）标签为0，中度至重度EPVS（≥ 10）标签为1。创建了152层的三维残差网络（3D-ResNet-152）以预测EPVS严重程度，并使用3D梯度类激活映射（3DGradCAM）对结果进行视觉解释。我们的模型在总队列（n = 39）的15%的保持测试集上实现了0.897的准确度和0.879的曲线下面积。3DGradCAM显示了生理有效位置的重点区域，包括EPVS的其他流行区域。这些地图还表明，类激活值的分布表明了对模型决策的信心。我们的研究结果的潜在临床意义包括：（1）支持使用临床级神经影像学数据自动化EPVS评分的可行性，可能减轻评分者的主观性并提高视觉评分量表的置信度，以及（2）证明可解释的模型对于临床翻译至关重要。
Enlarged perivascular spaces (EPVS), specifically in stroke patients, has been shown to strongly correlate with other measures of small vessel disease and cognitive impairment at 1 year follow-up. Typical grading of EPVS is often challenging and time consuming and is usually based on a subjective visual rating scale. The purpose of the current study was to develop an interpretable, 3D neural network for grading enlarged perivascular spaces (EPVS) severity at the level of the basal ganglia using clinical-grade imaging in a heterogenous acute stroke cohort, in the context of total cerebral small vessel disease (CSVD) burden. T2-weighted images from a retrospective cohort of 262 acute stroke patients, collected in 2015 from 5 regional medical centers, were used for analyses. Patients were given a label of 0 for none-to-mild EPVS (< 10) and 1 for moderate-to-severe EPVS (≥ 10). A three-dimensional residual network of 152 layers (3D-ResNet-152) was created to predict EPVS severity and 3D gradient class activation mapping (3DGradCAM) was used for visual interpretation of results. Our model achieved an accuracy 0.897 and area-under-the-curve of 0.879 on a hold-out test set of 15% of the total cohort (n = 39). 3DGradCAM showed areas of focus that were in physiologically valid locations, including other prevalent areas for EPVS. These maps also suggested that distribution of class activation values is indicative of the confidence in the model’s decision. Potential clinical implications of our results include: (1) support for feasibility of automated of EPVS scoring using clinical-grade neuroimaging data, potentially alleviating rater subjectivity and improving confidence of visual rating scales, and (2) demonstration that explainable models are critical for clinical translation.
登录
查看更多内容
DOI：
10.1159/000375153
发表时间：
2015
期刊：
Cerebrovascular diseases (Basel, Switzerland)
影响因子：
--
作者：
Potter GM;Chappell FM;Morris Z;Wardlaw JM
通讯作者：
Wardlaw JM
影响因子：
5.7
作者：
Park SH;Zong X;Gao Y;Lin W;Shen D
通讯作者：
Shen D
影响因子：
6.7
作者：
Arba, Francesco;Quinn, Terence J.;Inzitari, Domenico
通讯作者：
Inzitari, Domenico
DOI：
10.1148/ryai.2020190043
发表时间：
2020-05-01
期刊：
RADIOLOGY-ARTIFICIAL INTELLIGENCE
影响因子：
--
作者：
Reyes, Mauricio;Meier, Raphael;Wiest, Roland
通讯作者：
Wiest, Roland
影响因子：
5.7
作者：
Dubost, Florian;Yilmaz, Pinar;de Bruijne, Marleen
通讯作者：
de Bruijne, Marleen