基于深度学习的CT影像脑卒中精准分割

Accurate segmentation of stroke in CT image based on deep learning

为解决脑卒中病变的人工定位和定量分析耗时且缺乏一致性的问题,提出了基于多尺度U-Net深度网络模型,从非增强计算机断层扫描影像中分割脑卒中病变的高密度征,同时使用Dice损失函数训练模型以对抗数据中类不平衡问题。实验数据表明:该模型可端到端的以数据驱动的方式自动学习高密度征显著特征,有效地分割脑部小病灶区域。

In order to manual localization and quantitative analysis of stroke lesions is time-consuming and lacks consistency. This paper proposes a multi-scale U-Net deep network method to segment high density sign of ischemic stroke from non-enhanced Computed Tomography(CT),and use the Dice loss to train the model to combat the class imbalance in the image. Experiments show that the model can automatically learn salient features of high density sign in an end-to-end data-driven manner,effectively segmenting small lesions.