论文标题
OR-UNET：内窥镜图像中仪器分割的优化鲁棒剩余U-NET
OR-UNet: an Optimized Robust Residual U-Net for Instrument Segmentation in Endoscopic Images
论文作者
论文摘要
内窥镜图像的分割是计算机和机器人辅助干预措施的重要处理步骤。强大的MIS挑战提供了迄今为止注释的内窥镜图像的最大数据集，并提供了5983个手动注释的图像。在这里，我们描述了OR-UNET，这是内窥镜图像分割的优化鲁棒残留2D U-NET。顾名思义，该网络利用编码器中的残差连接。它接受了骰子和跨凝结损失和深层监督的培训。在培训期间，大量数据增加用于提高鲁棒性。在训练图像上的8倍交叉验证中，我们的模型达到了平均（中值）骰子分数为87.41（94.35）。我们将交叉验证中的八个模型用作测试集上的集合。
Segmentation of endoscopic images is an essential processing step for computer and robotics-assisted interventions. The Robust-MIS challenge provides the largest dataset of annotated endoscopic images to date, with 5983 manually annotated images. Here we describe OR-UNet, our optimized robust residual 2D U-Net for endoscopic image segmentation. As the name implies, the network makes use of residual connections in the encoder. It is trained with the sum of Dice and cross-entropy loss and deep supervision. During training, extensive data augmentation is used to increase the robustness. In an 8-fold cross-validation on the training images, our model achieved a mean (median) Dice score of 87.41 (94.35). We use the eight models from the cross-validation as an ensemble on the test set.
