Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation
Marijn F. Stollenga Wonmin Byeon Marcus Liwicki University of Kaiserslautern, Germany Juergen Schmidhuber
Abstract
Convolutional Neural Networks (CNNs) can be shifted across 2D images or 3D videos to segment them. They have a fixed input size and typically perceive only small local contexts of the pixels to be classified as foreground or background. In contrast, Multi-Dimensional Recurrent NNs (MD-RNNs) can perceive the entire spatio-temporal context of each pixel in a few sweeps through all pixels, especially when the RNN is a Long Short-Term Memory (LSTM). Despite these theoretical advantages, however, unlike CNNs, previous MD-LSTM variants were hard to parallelize on GPUs. Here we re-arrange the traditional cuboid order of computations in MD-LSTM in pyramidal fashion. The resulting PyraMiD-LSTM is easy to parallelize, especially for 3D data such as stacks of brain slice images. PyraMiD-LSTM achieved best known pixel-wise brain image segmentation results on MRBrainS13 (and competitive results on EM-ISBI12).
中文速览
通过把多维长短期记忆网络（MD-LSTM）的计算顺序从传统的"长方体扫描"重新排列为"金字塔式扫描"，本文解决了MD-LSTM在GPU上难以并行加速的瓶颈问题。新提出的PyraMiD-LSTM在处理三维体数据（如脑部MRI切片堆叠）时，只需6个方向的扫描（相比MD-LSTM所需的8个），且同一扫描平面内的所有像素可以同时并行计算，极大地提升了运算效率。在脑图像分割基准测试MRBrainS13上，PyraMiD-LSTM取得了当时最佳的逐像素分割精度，在神经元电镜图像分割基准EM-ISBI12上也达到了有竞争力的成绩。这项工作的重要意义在于，它首次让具备全局上下文感知能力的多维LSTM在三维医学图像分割任务中变得实用，为后续体数据分析提供了兼顾精度与速度的新思路。
原文 arXiv:1506.07452;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1506.07452v1