BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation
BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation
复制标题
DOI：
10.1007/978-3-030-87193-2_22
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Xinyi Wang;Tiange Xiang;Chaoyi Zhang;Yang Song;Dongnan Liu;Heng Huang;Weidong (Tom) Cai
中科院分区：
文献类型：
--
作者：
Xinyi Wang;Tiange Xiang;Chaoyi Zhang;Yang Song;Dongnan Liu;Heng Huang;Weidong (Tom) Cai
最近，在各种医学图像分割任务中，将递归机制引入到U-Net中。现有的研究主要集中在通过重用构建块来促进网络递归。虽然可以大大节省网络参数，但按照预先设定的迭代时间，计算量仍不可避免地增加。在这项工作中，我们研究了双向跳跃连接网络的多尺度升级，然后通过一种新的两阶段神经架构搜索（NAS）算法，即BiX-NAS，自动发现一个有效的架构。我们提出的方法通过在不同的层次和迭代中筛选出无效的多尺度特征来降低网络的计算成本。我们使用三种不同的医学图像数据集对BiX-NAS进行了两个分割任务的评估，实验结果表明，我们的BiX-NAS搜索架构以显著降低的计算成本实现了最先进的性能。我们的项目页面位于： https://bionets.github.io .
The recurrent mechanism has recently been introduced into U-Net in various medical image segmentation tasks. Existing studies have focused on promoting network recursion via reusing building blocks. Although network parameters could be greatly saved, computational costs still increase inevitably in accordance with the pre-set iteration time. In this work, we study a multi-scale upgrade of a bi-directional skip connected network and then automatically discover an efficient architecture by a novel two-phase Neural Architecture Search (NAS) algorithm, namely BiX-NAS. Our proposed method reduces the network computational cost by sifting out ineffective multi-scale features at different levels and iterations. We evaluate BiX-NAS on two segmentation tasks using three different medical image datasets, and the experimental results show that our BiX-NAS searched architecture achieves the state-of-the-art performance with significantly lower computational cost. Our project page is available at: https://bionets.github.io .