反褶积
计算机科学
分割
预处理器
背景(考古学)
人工智能
模式识别(心理学)
冗余(工程)
特征(语言学)
特征提取
卷积(计算机科学)
算法
人工神经网络
生物
操作系统
哲学
古生物学
语言学
作者
Chi Zhang,Qian Hua,Yingying Chu,Pengwei Wang
标识
DOI:10.1016/j.compbiomed.2021.104424
摘要
Liver tumor segmentation networks are generally based on U-shaped encoder-decoder network with 2D or 3D structure. However, 2D networks lose the inter-layer information of continuous slices and 3D networks might introduce unacceptable parameters for GPU memory. As a result, 2.5D networks were proposed to balance the memory consumption and 3D context. Different from the canonical 2.5D design, which utilizes a 2D network combined with RNN, we propose a new 2.5D design called UV-Net to encode the inter-layer information in the context of 3D convolution, and reconstruct the high-resolution results with 2D deconvolution. At the same time, the multi-scale convolution structure enables multi-scale feature extraction without extra computational cost, which effectively mines structured information, reduces information redundancy, strengthens independent features, and makes feature dimension sparse, to enhance network capacity and efficiency. Combined with the proposed preprocessing method of removing mean energy, UV-Net significantly outperforms the existing methods in liver tumor segmentation and especially improves the segmentation accuracy of small objects on the LiTS2017 dataset.
科研通智能强力驱动
Strongly Powered by AbleSci AI