光学学报, 2020, 40 (6): 0610001, 网络出版: 2020-03-06   

多模态磁共振脑肿瘤图像自动分割算法研究 下载: 1776次

Automatic Segmentation Algorithm for Multimodal Magnetic Resonance-Based Brain Tumor Images
作者单位
四川大学电气工程学院, 四川 成都 610065
摘要
脑肿瘤图像自动分割的难点在于肿瘤形态各异,且类别不平衡情况比较严重,常规的卷积神经网络难以预测出高精度分割图像。针对以上问题,在原始3D-Unet的基础上提出一种改进模型,以混合膨胀卷积模块代替常规卷积模块,指数级地增大神经元的感受野,同时减小网络深度,避免上采样时无法恢复小目标的情况。同时以混合损失函数代替原来的Dice损失函数,加强稀疏类分类错误时对模型的惩罚,迫使模型更好地学习分类错误的样本。实验结果表明,混合膨胀卷积模块与混合损失函数能分别提高整个肿瘤区域和肿瘤核心区域的预测精度,提出的3D-HDC-Unet模型改善了脑肿瘤自动分割的多项性能参数。
Abstract
Automatic segmentation of brain tumor images is difficult to achieve owing to the diversity in tumor shapes and severe imbalance in the segmentation categories. Conventional convolutional neural network can hardly predict high precision segmentation images. To solve the abovementioned problems, an improved model based on the original three-dimensional (3D)-Unet was proposed, which replaced the conventional convolution module with a hybrid dilated convolution module to exponentially increase the receptive field of neurons, reducing the network depth and avoiding scenarios wherein small targets could not be recovered during up-sampling. Furthermore, the hybrid loss function was used to replace the original Dice loss function to increase the penalty faced by the model when classification errors of sparse classes occurred, forcing the model to learn the features of these classes better. Experiment results showed that the hybrid dilated convolution module and the hybrid loss function could respectively improve the prediction accuracy of the whole tumor region and the core tumor region. Multiple performance parameters of brain tumor automatic segmentation were improved using this 3D-HDC-Unet model.

何承恩, 徐慧君, 王忠, 马丽萍. 多模态磁共振脑肿瘤图像自动分割算法研究[J]. 光学学报, 2020, 40(6): 0610001. Cheng'en He, Huijun Xu, Zhong Wang, Liping Ma. Automatic Segmentation Algorithm for Multimodal Magnetic Resonance-Based Brain Tumor Images[J]. Acta Optica Sinica, 2020, 40(6): 0610001.

本文已被 13 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!