论文标题
使用U-NET类型的体系结构进行医学图像分割
Medical Image Segmentation Using a U-Net type of Architecture
论文作者
论文摘要
深度卷积神经网络已被证明在与图像相关的分析和任务中非常有效，例如图像分割，图像分类，图像产生等。最近，为图像分割而提出了许多基于CNN的复杂体系结构。这些新设计的网络中的一些用于医学图像分割的特定目的，例如V-NET，U-NET及其变体。已经表明，U-NET在医学图像分割的领域中产生非常有希望的结果。但是，在本文中，我们认为，在瓶颈层上与监督培训策略相结合时，U-NET的体系结构可以与原始U-NET体系结构产生可比的结果。更具体地说，我们在U-NET的编码器分支的瓶颈上引入了完全监督的基于FC的像素损失。基于两层的FC子网络将训练瓶颈表示以包含更多的语义信息，解码器层将使用该信息来预测最终的分割图。基于FC层的子网络是通过使用像素的横熵损失来训练的，而使用L1损失训练的U-NET体系结构。
Deep convolutional neural networks have been proven to be very effective in image related analysis and tasks, such as image segmentation, image classification, image generation, etc. Recently many sophisticated CNN based architectures have been proposed for the purpose of image segmentation. Some of these newly designed networks are used for the specific purpose of medical image segmentation, models like V-Net, U-Net and their variants. It has been shown that U-Net produces very promising results in the domain of medical image segmentation.However, in this paper, we argue that the architecture of U-Net, when combined with a supervised training strategy at the bottleneck layer, can produce comparable results with the original U-Net architecture. More specifically, we introduce a fully supervised FC layers based pixel-wise loss at the bottleneck of the encoder branch of U-Net. The two layer based FC sub-net will train the bottleneck representation to contain more semantic information, which will be used by the decoder layers to predict the final segmentation map. The FC layer based sub-net is trained by employing the pixel-wise cross entropy loss, while the U-Net architectures trained by using L1 loss.
