U-Net算法的简介(论文介绍)
U-Net算法是一种适合医学影像分割的网络模型。医学领域进行视觉分割的一大难题是数据比较少，而U-Net模型，可以相对较少的数据，准确预测肿瘤存在的位置。
Abstract
There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net .
人们普遍认为，深度网络的成功训练需要数千个带注释的训练样本。在本文中，我们提出了一种网络和训练策略，它依赖于对数据增强的强大使用，从而更有效地使用可用的带注释的样本。该体系结构由捕获上下文的收缩路径和支持精确定位的对称扩展路径组成。我们证明了这种网络可以从非常少的图像端到端的训练，并且在ISBI竞赛挑战中，在电子显微镜栈中神经元结构的分割上，它比之前的最佳方法(滑动窗口卷积网络)表现得更好。使用相同的网络训练传输光学显微镜图像(相位对比和DIC)，我们赢得了2015年ISBI细胞跟踪挑战赛在这些类别的巨大优势。此外，网络是快速的。在最新的GPU上，512*512图像的分割需要不到一秒钟的时间。完整的实现(基于Caffe)和经过训练的网络可以在http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net上找到。
Conclusion
The u-net architecture achieves very good performance on very different biomedical segmentation applications. Thanks to data augmentation with elastic deformations, it only needs very few annotated images and has a very reasonable training time of only 10 hours on a NVidia Titan GPU (6 GB). We provide the full Caffe[6]-based implementation and the trained networks4 . We are sure that the u-net architecture can be applied easily to many more tasks.
u-net体系结构在非常不同的生物医学分割应用上取得了非常好的性能。由于数据增强与弹性变形，它只需要非常少的注释图像，并有一个非常合理的训练时间只有10小时，在NVidia Titan GPU (6GB)。我们提供完整的基于Caffe的实现和训练有素的网络。我们确信u-net体系结构可以很容易地应用于更多的任务。
论文
Ronneberger, Olaf, Philipp Fischer, and Thomas Brox.
U-net: Convolutional networks for biomedical image segmentation
International Conference on Medical image computing and computer-assisted intervention. 2015.
https://arxiv.org/abs/1505.04597
0、实验结果
1、U-Net算法图像分割的定性效果——用差示干涉对比显微镜在玻璃上记录海拉细胞
HeLa cells on glass recorded with DIC (differential interference contrast) microscopy
(a)raw image.
原始图像。
(b)overlay with ground truth segmentation. Different colors indicate different instances of the HeLa cells.
人工分割图像：不同的颜色表示hela单元的不同实例。
(c) generated segmentation mask (white: foreground, black: background).
生成的分割mask （白色是前景，黑色是背景）。
(d) map with a pixel-wise loss weight to force the network to learn the border pixels.
采用像素丢失权重进行映射，以强制网络学习边界像素。图中红色边界，很好的将细胞分割开！
2、U-Net算法图像分割的定性效果——ISBI细胞追踪挑战竞赛的结果
Result on the ISBI cell tracking challenge
(a)part of an input image of the“PhC-U373” data set.
数据集中的图像：“PhC-U373”数据集的输入图像的一部分。
(b)Segmentation result (cyan mask) with manual ground truth (yellow border)
黄色边框的是人工分割框，青色mask的是U-Net分割后的结果
(c)input image of the “DIC-HeLa” data set.
数据集中的图像：输入“DIC-HeLa”数据集的图像。
(d)Segmentation result (random colored masks) with manual ground truth (yellow border).
随机彩色masks是U-Net分割后的结果，黄色边框的是人工分割框。
3、U-Net算法图像分割的定量效果——Segmentation results (IOU) on the ISBI cell tracking challenge 2015
U-Net算法效果非常好，远远超过了其他模型算法。
U-Net算法的架构详解
更新……
U-Net算法的案例应用
更新……
