论文标题
带有小残留3D U-NET体系结构的黄斑水肿数据集的分割
Segmentation of Macular Edema Datasets with Small Residual 3D U-Net Architectures
论文作者
论文摘要
本文研究了深度卷积神经网络的应用，该网络具有极小的小数据集，以使黄斑水肿分割问题。特别是，我们研究了几种不同的规范性架构。我们发现，与普遍的看法相反，这种应用程序环境中的神经体系结构能够在看不见的测试图像上接近人类水平的性能，而无需大量的培训示例。注释这些3D数据集很困难，需要多个标准。经验丰富的临床医生需要两天的时间来注释单个3D图像，而我们训练的模型在不到一秒钟的时间内实现了相似的性能。我们发现，尽管依靠少于15个培训示例，但使用针对性数据集扩展的方法以及重点是剩余设计的方法，并强调了剩余的设计。
This paper investigates the application of deep convolutional neural networks with prohibitively small datasets to the problem of macular edema segmentation. In particular, we investigate several different heavily regularized architectures. We find that, contrary to popular belief, neural architectures within this application setting are able to achieve close to human-level performance on unseen test images without requiring large numbers of training examples. Annotating these 3D datasets is difficult, with multiple criteria required. It takes an experienced clinician two days to annotate a single 3D image, whereas our trained model achieves similar performance in less than a second. We found that an approach which uses targeted dataset augmentation, alongside architectural simplification with an emphasis on residual design, has acceptable generalization performance - despite relying on fewer than 15 training examples.
