基于深度可分离卷积的缺血性脑卒中多模态磁共振图像梗死分割模型研究

Ischemic stroke infarct segmentation model based on depthwise separable convolution for multimodal magnetic resonance imaging

磁共振成像(MRI)在缺血性脑卒中的诊断中扮演着重要的角色,准确分割梗死病灶对于介入治疗方法的选择以及评估患者预后效果有着重要的意义。针对现有分割方法对于多尺度脑卒中梗死病灶分割精度较差的问题,本文提出了一种新型的基于深度可分离卷积的编码器—解码器结构网络。首先,该网络将U型网络(U-Net)原有的卷积层模块替换为重新设计的深度可分离卷积模块;其次,引入改进型空洞空间金字塔池化(MASPP),扩大感受野,以加强多尺度特征的提取;再次,在网络的跳跃连接处加入注意力门(AG)模块,进一步增强网络对于多尺度目标的分割精度;最后使用缺血性脑卒中梗死分割2022年挑战赛(ISLES2022)数据集进行实验,本文算法在该数据集上的戴斯相似系数(DSC)、豪斯多夫距离(HD)、敏感度(SEN)、准确度(PRE)分别为0.8165、3.6681、0.8892、0.8946,优于其他主流分割算法。实验结果表明,本文方法能有效地提高梗死病灶的分割效果,有望为临床诊断和治疗提供可靠辅助。

Magnetic resonance imaging(MRI)plays a crucial role in the diagnosis of ischemic stroke.Accurate segmentation of the infarct is of great significance for selecting intervention treatment methods and evaluating the prognosis of patients.To address the issue of poor segmentation accuracy of existing methods for multiscale stroke lesions,a novel encoder-decoder architecture network based on depthwise separable convolution is proposed.Firstly,this network replaces the convolutional layer modules of the U-Net with redesigned depthwise separable convolution modules.Secondly,an modified Atrous spatial pyramid pooling(MASPP)is introduced to enlarge the receptive field and enhance the extraction of multiscale features.Thirdly,an attention gate(AG)structure is incorporated at the skip connections of the network to further enhance the segmentation accuracy of multiscale targets.Finally,Experimental evaluations are conducted using the ischemic stroke lesion segmentation 2022 challenge(ISLES2022)dataset.The proposed algorithm in this paper achieves Dice similarity coefficient(DSC),Hausdorff distance(HD),sensitivity(SEN),and precision(PRE)scores of 0.8165,3.6681,0.8892,and 0.8946,respectively,outperforming other mainstream segmentation algorithms.The experimental results demonstrate that the method in this paper effectively improves the segmentation of infarct lesions,and is expected to provide a reliable support for clinical diagnosis and treatment.