论文标题
使用混合表示形式进行图像分割
Image Segmentation Using Hybrid Representations
论文作者
论文摘要
这项工作探讨了一种混合分割方法，作为纯粹数据驱动方法的替代方法。我们引入了一个名为DU-NET的基于端到端U-NET的网络，该网络使用其他频率保留功能，即散射系数（SC），用于医疗图像分割。 SC是翻译不变的，Lipschitz连续变形，这些变形可帮助DU-NET在四个数据集上的其他常规CNN对应物和两个分割任务上的其他传统CNN对应物：彩色眼底图像中的视盘和光盘和视杯，以及超声图像中的胎儿头部。所提出的方法显示出对基本U-NET的显着改善，其性能与最新方法具有竞争力。结果表明，可以使用较轻的网络训练的图像较少（没有任何扩展）来获得良好的分割结果。
This work explores a hybrid approach to segmentation as an alternative to a purely data-driven approach. We introduce an end-to-end U-Net based network called DU-Net, which uses additional frequency preserving features, namely the Scattering Coefficients (SC), for medical image segmentation. SC are translation invariant and Lipschitz continuous to deformations which help DU-Net outperform other conventional CNN counterparts on four datasets and two segmentation tasks: Optic Disc and Optic Cup in color fundus images and fetal Head in ultrasound images. The proposed method shows remarkable improvement over the basic U-Net with performance competitive to state-of-the-art methods. The results indicate that it is possible to use a lighter network trained with fewer images (without any augmentation) to attain good segmentation results.
