We introduce $\textit{InExtremIS}$, a weakly supervised 3D approach to train a deep image segmentation network using particularly weak train-time annotations: only 6 extreme clicks at the boundary of the objects of interest. Our fully-automatic method is trained end-to-end and does not require any test-time annotations. From the extreme points, 3D bounding boxes are extracted around objects of interest. Then, deep geodesics connecting extreme points are generated to increase the amount of "annotated" voxels within the bounding boxes. Finally, a weakly supervised regularised loss derived from a Conditional Random Field formulation is used to encourage prediction consistency over homogeneous regions. Extensive experiments are performed on a large open dataset for Vestibular Schwannoma segmentation. $\textit{InExtremIS}$ obtained competitive performance, approaching full supervision and outperforming significantly other weakly supervised techniques based on bounding boxes. Moreover, given a fixed annotation time budget, $\textit{InExtremIS}$ outperforms full supervision. Our code and data are available online.
翻译:我们引入了 $\ textit{ inExtremIS} $。 这是一种监管薄弱的三维方法, 用来用特别薄弱的列车时间说明来训练深图像分割网络: 只有6个极端点击点在受关注对象的边界上。 我们的全自动方法经过培训, 不需要任何测试时间说明。 从极端点中, 3D 捆绑框在受关注对象周围提取 。 然后, 产生连接极端点的深海大地测量, 以增加捆绑框内的“ 附加说明” 氧化物数量。 最后, 使用监管薄弱的常规损失, 用于鼓励在同质区域上预测一致性。 在 Vestibulal Schwannoma 分割的大型开放数据集上进行了广泛的实验。 $\ textit{ IntremIS} 获得竞争性业绩, 接近全面监督, 并大大优于其他基于绑框的监管不力的技术。 此外, 由于固定的注时间预算, $\ text {Instremis} experforages froductionsul expeciductions。