详情页 - 首都医科大学宣武医院知识库

当前位置：首页 > 详情页

3D Brain Tumor Segmentation Through Integrating Multiple 2D FCNNs

文献详情

资源类型：

收录情况： ◇ CPCI(ISTP) ◇ EI

作者：

机构： [1]National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China [2]University of Chinese Academy of Sciences, Beijing, China zhaoxiaomei14@mails.ucas.ac.cn [3]Beijing Neurosurgical Institute, Capital Medical University, Beijing, China [4]Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China [5]Beijing Institute for Brain Disorders Brain Tumor Center, Beijing, China [6]China National Clinical Research Center for Neurological Diseases, Beijing, China [7]Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA

出处：

DOI：

ISSN：

关键词： Brain tumor segmentation Fully Convolutional Neural Networks 3D Conditional Random Fields Multi-views

摘要：

The Magnetic Resonance Images (MRI) which can be used to segment brain tumors are 3D images. To make use of 3D information, a method that integrates the segmentation results of 3 2D Fully Convolutional Neural Networks (FCNNs), each of which is trained to segment brain tumor images from axial, coronal, and sagittal views respectively, is applied in this paper. Integrating multiple FCNN models by fusing their segmentation results rather than by fusing into one deep network makes sure that each FCNN model can still be tested by 2D slices, guaranteeing the testing efficiency. An averaging strategy is applied to do the fusing job. This method can be easily extended to integrate more FCNN models which are trained to segment brain tumor images from more views, without retraining the FCNN models that we already have. In addition, 3D Conditional Random Fields (CRFs) are applied to optimize our fused segmentation results. Experimental results show that, integrating the segmentation results of multiple 2D FCNNs obviously improves the segmentation accuracy, and 3D CRF greatly reduces false positives and improves the accuracy of tumor boundaries.

基金：

语种：

被引次数：

WOS：

第一作者：

第一作者机构： [1]National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China [2]University of Chinese Academy of Sciences, Beijing, China zhaoxiaomei14@mails.ucas.ac.cn

通讯作者：

通讯机构： [1]National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China [2]University of Chinese Academy of Sciences, Beijing, China zhaoxiaomei14@mails.ucas.ac.cn

推荐引用方式(GB/T 7714)：

APA：

MLA：

相关文献

[1]A deep learning model integrating FCNNs and CRFs for brain tumor segmentation [2]Brain Tumor Segmentation Using a Fully Convolutional Neural Network with Conditional Random Fields [3]Automatic Brain Tumor Segmentation Method Based on Modified Convolutional Neural Network [4]Brain tumor segmentation through data fusion of T2-weighted image and MR spectroscopy [5]A mix-pooling CNN architecture with FCRF for brain tumor segmentation [6]Brain tumor segmentation based on attention mechanism and multi-model fusion [7]Automatic Brain Tumor Segmentation Method Based on Modified Convolutional Neural Network [8]A framework of automatic brain tumor segmentation method based on information fusion of structural and functional MRI signals [9]A Framework of Automatic Brain Tumor Segmentation Method Based on Information Fusion of Structural and Functional MRI Signals [10]An Improvement Method of Brain Extraction Tools for Magnetic Resonance Images