EU-Net: Efficient Dense Skip-Connected Autoencoder for Medical Image Segmentation
EU-Net: Efficient Dense Skip-Connected Autoencoder for Medical Image Segmentation
复制标题
DOI：
10.1109/access.2023.3334621
复制
发表时间：
2023
期刊：
影响因子：
3.9
通讯作者：
Lizhuang Liu;Jiacun Qiu;Ke Wang;Qiao Zhan;Jiaxi Jiang;Zhenqi Han;Jianxin Qiu;Tian Wu;Jinghang Xu;Zheng Zeng
中科院分区：
文献类型：
--
作者：
Lizhuang Liu;Jiacun Qiu;Ke Wang;Qiao Zhan;Jiaxi Jiang;Zhenqi Han;Jianxin Qiu;Tian Wu;Jinghang Xu;Zheng Zeng
本文介绍了 EU-Net，这是一种高效且增强的类似 U-Net 的架构，专为医学图像分割而设计。它包括通过密集跳跃连接连接的轻量级编码器和解码器。为了进一步提高EU-Net的鲁棒性，提出了链式EU-Net。 Chain EU-Net 基于流线型架构，使用多个 EU-Net 通过密集跳跃连接构建轻量级深度神经网络。与U-Net及其变体等传统分割算法相比，我们的神经网络结构同时具有轻量级和稳定性。 EU-Net 和链 EU-Net 在三个典型的医学图像分割任务上进行评估：GLAS（腺体分割）数据集、RITE（视网膜图像血管树提取）数据集和 LiTS（肝脏肿瘤分割挑战）数据集。此外，我们使用PUFH（北京大学第一医院）数据集。实验结果表明，所提出的方法以很少的参数实现了最先进的性能。
This paper introduces EU-Net, an efficient and enhanced U-Net-like architecture designed for medical image segmentation. It comprises a lightweight encoder and decoder connected through dense skip-connections. To further improve the robustness of the EU-Net, chain EU-Net is proposed. Chain EU-Net is based on a streamlined architecture that uses multiple EU-Net to build light weight deep neural networks by dense skip-connection. Compared to traditional segmentation algorithms such as U-Net and its variants, our neural network structure possesses both lightweight and stability simultaneously. EU-Net and chain EU-Net are evaluated on three typical medical image segmentation tasks: GLAS (Gland segmentation) dataset, RITE (Retinal Images Vessel Tree Extraction) dataset and LiTS (Liver Tumor Segmentation Challenge) dataset. In addition, we used PUFH (Peking University First Hospital) dataset. Experimental results show that the proposed methods achieve state-of-the-art performance with very few parameters.