Wu Guoqing, Chen Xi, Lin Jixian, Wang Yuanyuan, Yu Jinhua
Department of Electronic Engineering, Fudan University, Shanghai, 200433, China.
Department of Neurology, Minhang Branch, Zhongshan Hospital, Fudan University, Shanghai, 200433, China.
Med Phys. 2021 Mar;48(3):1262-1275. doi: 10.1002/mp.14691. Epub 2021 Feb 6.
Early identification of ischemic stroke lesion regions plays a vital role in its treatments like thrombolytic therapy and patients' recovery. Noncontrast computed tomography (ncCT) is the most widespread imaging modality in emergency departments. Unfortunately, it is extremely hard to distinguish the lesion from healthy tissue during the hyper-acute phase of stroke. In this paper, a two-stage convolutional neural network-based method was proposed to identify the invisible ischemic stroke from ncCT.
In order to combine the global and local information of images effectively, a cascaded structure with two coordinated networks was used to detect the suspicious stroke regions on the whole and optimize the detailed localization. In the first stage, an end-to-end U-net with adaptive threshold was proposed to integrate global position, symmetry and gray texture information to detect the suspicious regions. After reducing the interference from most normal regions, a ResNet-based patch classification network was used to eliminate some false positive samples on suspicious regions by mining deeper image features, contributing to a more precise localization of stroke. Finally, a MAP model was used to optimize the result by combining the classification results of each patch with their spatial constraint information.
Three independent experiments, that is, training and testing on dataset from one hospital, on the combination of two, and on the two respectively, were performed on a total of 277 cases from two hospitals to validate the proposed model, The proposed method achieved identification accuracy of 91.89%, 87.21%, and 85.71% in the three experiments, and the final localization accuracy in terms of precise localization of stroke were 82.35%, 83.02%, and 81.40%, respectively, which indicated the robustness and clinical values of the method.
There are some deep image feature differences between stroke region and normal region on ncCT images. The proposed two-stage convolutional neural network model can well seize these features and use them to effectively identify and locate stroke.
早期识别缺血性中风病变区域在溶栓治疗等治疗方法及患者康复过程中起着至关重要的作用。非增强计算机断层扫描（ncCT）是急诊科最常用的成像方式。不幸的是，在中风的超急性期很难将病变与健康组织区分开来。本文提出了一种基于两阶段卷积神经网络的方法，用于从ncCT中识别不可见的缺血性中风。
为了有效结合图像的全局和局部信息，采用了一种由两个协同网络组成的级联结构，以整体检测可疑中风区域并优化详细定位。在第一阶段，提出了一种具有自适应阈值的端到端U-net，以整合全局位置、对称性和灰度纹理信息来检测可疑区域。在减少了大多数正常区域的干扰后，使用基于ResNet的补丁分类网络通过挖掘更深层次的图像特征来消除可疑区域上的一些假阳性样本，从而更精确地定位中风。最后，使用MAP模型通过将每个补丁的分类结果与其空间约束信息相结合来优化结果。
对来自两家医院的总共277例病例进行了三项独立实验，即在一家医院的数据集上进行训练和测试、在两家医院数据集的组合上进行训练和测试以及分别在两家医院的数据集上进行训练和测试，以验证所提出的模型。所提出的方法在这三项实验中的识别准确率分别为91.89%、87.21%和85.71%，中风精确定位的最终定位准确率分别为82.35%、83.02%和81.40%，这表明了该方法的稳健性和临床价值。
ncCT图像上中风区域与正常区域之间存在一些深层次的图像特征差异。所提出的两阶段卷积神经网络模型能够很好地捕捉这些特征，并利用它们有效地识别和定位中风。
