标题:Hybrid Pyramid U-Net Model for Brain Tumor Segmentation
作者:Kong, Xiangmao; Sun, Guoxia; Wu, Qiang; Liu, Ju; Lin, Fengming
通讯作者:Wu, Q;Wu, Q;Wu, Qiang
作者机构:[Kong, Xiangmao; Sun, Guoxia; Wu, Qiang; Liu, Ju; Lin, Fengming] Shandong Univ, Sch Informat Sci & Engn, Jinan 250100, Shandong, Peoples R China.; [ 更多
会议名称:10th IFIP TC 12 International Conference on Intelligent Information Processing (IIP)
会议日期:OCT 19-22, 2018
来源:INTELLIGENT INFORMATION PROCESSING IX
出版年:2018
卷:538
页码:346-355
DOI:10.1007/978-3-030-00828-4_35
关键词:HPU-Net; Tumor segmentation; Hybrid pyramid network; Multimodal MRI;; Deep learning
摘要:In this paper, we extend the U-Net model and propose a novel hybrid pyramid U-Net (HPU-Net) model which explores the global context information combined different region based context. Global context information combination is effective for producing good quality results in tumor segmentation tasks, and HPU-Net provides a better framework for pixel-level prediction. Because of the continuous downsampling of FCN the resolution of the feature map gradually decreases and direct upsampling during restoration of resolution will introduce noise and make the segmentation inaccurate. A novel and efficient multimodal tumor segmentation (including internal tumor) model based on U-Net is proposed to perform end-to-end training and testing. Our model includes a downsampling path and a symmetrical upsampling path, concatenating the features at the symmetrical block of upsampling and downsampling path. In the process of upsampling, we extract multiple scale features from every block, and add them pixel-wise after recovering them to origin resolution. Integrating the multi-scale information, semantic and location information before softmax layer, it helps the model complete the segmentation efficiently. The model was evaluated on two datasets BRATS2015 and BRATS2017, and outperformed state-of-the-art methods with better segmentation results.
收录类别:CPCI-S;EI;SCOPUS
资源类型:会议论文;期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85055674292&doi=10.1007%2f978-3-030-00828-4_35&partnerID=40&md5=0fe441f3f0601f35a651e08221418695
TOP