There are many approaches that use weak-supervision to train networks to segment 2D images. By contrast, existing 3D approaches rely on full-supervision of a subset of 2D slices of the 3D image volume. In this paper, we propose an approach that is truly weakly-supervised in the sense that we only need to provide a sparse set of 3D point on the surface of target objects, an easy task that can be quickly done. We use the 3D points to deform a 3D template so that it roughly matches the target object outlines and we introduce an architecture that exploits the supervision provided by coarse template to train a network to find accurate boundaries. We evaluate the performance of our approach on Computed Tomography (CT), Magnetic Resonance Imagery (MRI) and Electron Microscopy (EM) image datasets. We will show that it outperforms a more traditional approach to weak-supervision in 3D at a reduced supervision cost.

翻译：有许多方法使用薄弱的监控来培训网络到 2D 部分图像。 相反, 现有的 3D 方法依赖于对 3D 图像卷 2D 片段的子集的全面监督。 在本文中, 我们建议了一种真正弱小的监管方法, 也就是说我们只需要在目标对象表面提供一套稀疏的 3D 点, 这是一项可以快速完成的简单任务。 我们用 3D 点来对一个 3D 模板进行变形, 使其大致匹配目标对象的轮廓, 我们引入了一种结构, 利用粗略模板提供的监管来培训一个网络, 以找到准确的边界 。 我们评估了我们关于 Computtotography (CT)、 Magetic Resonance 图像(MRI) 和 电算显微镜(EM) 图像数据集的方法的绩效。 我们将会显示, 3D 以较低的监督成本, 超越了对弱超视的较传统的方法 。