An Automatic Method for Brain Tumors Segmentation Based on Deep Convolutional Neural Network
编号：66
稿件编号：38 访问权限：仅限参会人
更新：2021-11-08 09:25:08
浏览：924次
口头报告
报告开始：2021年11月13日 16:15 （Asia/Shanghai）
报告时间：15min
所在会议：[PS1] Plenary Session 1 » [AI1] Workshop on AI
暂无文件
摘要
[Purpose] Accurate outline of tumor targets is critical to a high quality radiotherapy plan. Manual segmentation is of great workload and has a strong artificial subjectivity. Using deep learning method to assist automatically segmenting of tumor target is the penetration and application of artificial intelligence in medicine.
[Methods] A 6-layer model of deep Convolution Neural Network (CNN) has been constructed by taking advantage of different types of layers for brain tumor segmentation. This model is a 6 layer CNN model (6-CNN) composed of three convolution layers, two pool layers and one full connection layer. To obtain enough samples for 6-CNN model training, a patch-based technology has been adopted. That is to successively extract a local area from the whole image as a patch. And the center pixel value is taken as the pixel value of the whole patch. Similarly, the label of the center pixel is also taken as the label of the whole patch. Thus the 6-CNN model transforms the brain tumor image segmentation into patch classification based on the excellent classification characteristics of deep convolution neural network. The model combines the local features of patch, the information extracted from shallow network and the global features to predict the category label of the central pixel of patch.
[Results] The model is validated on BRATS 2015 dataset and results show that the segmentation accuracy can be up to Dice Similarity Coefficient (DSC) 90%±4%.
[Conclusions] An automatic deep CNN segmentation model for brain tumors has been constructed based on MRI image patches, which is expected to assist or even substitute the manual segmentation of brain tumors.
[Methods] A 6-layer model of deep Convolution Neural Network (CNN) has been constructed by taking advantage of different types of layers for brain tumor segmentation. This model is a 6 layer CNN model (6-CNN) composed of three convolution layers, two pool layers and one full connection layer. To obtain enough samples for 6-CNN model training, a patch-based technology has been adopted. That is to successively extract a local area from the whole image as a patch. And the center pixel value is taken as the pixel value of the whole patch. Similarly, the label of the center pixel is also taken as the label of the whole patch. Thus the 6-CNN model transforms the brain tumor image segmentation into patch classification based on the excellent classification characteristics of deep convolution neural network. The model combines the local features of patch, the information extracted from shallow network and the global features to predict the category label of the central pixel of patch.
[Results] The model is validated on BRATS 2015 dataset and results show that the segmentation accuracy can be up to Dice Similarity Coefficient (DSC) 90%±4%.
[Conclusions] An automatic deep CNN segmentation model for brain tumors has been constructed based on MRI image patches, which is expected to assist or even substitute the manual segmentation of brain tumors.
关键字
Accurately radiotherapy,Brain Tumor Segmentation,Deep Learning,Convolutional Neural Network
报告人
发表评论