摘要
为提高脑肿瘤磁共振图像分割精度,在U-Net图像分割方法基础上,提出了一种引入注意力机制的深度学习改进模型,利用全局上下文信息,使模型重点关注需要分割区域的特征,并抑制无关的特征,以此提高模型的分割精度,同时引入残差块来加速模型的训练.实验结果表明:提出的改进模型相比U-Net方法,脑肿瘤MRI图像的分割精度有了提高,具有良好的分割性能.
In order to improve the accuracy of brain tumor MRI image segmentation,based on the U-Net image segmentation method,an improved deep learning model with an attention mechanism is proposed.The global context information is used to make the model focus on the features of the region to be segmented,and suppress irrelevant features to improve the segmentation accuracy of the model,and at the same time introduce residual blocks to speed up the training of the model.The experimental results show that compared with the U-Net method,the proposed improved model improves the segmentation accuracy of brain tumor MRI images,has good segmentation performance.
作者
蔡畅
陈军波
陈心浩
CAI Chang;CHEN Junbo;CHEN Xinhao(College of Biomedical Engineering, South-Central University for Nationalities, Wuhan 430074, China)
出处
《中南民族大学学报(自然科学版)》
CAS
北大核心
2021年第4期417-423,共7页
Journal of South-Central University for Nationalities:Natural Science Edition
基金
中央高校基本科研业务费专项资金资助项目(CZP17089
CZP17057)。