Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate
This addresses annotation inaccuracies in 3D medical or scientific imaging, offering an incremental improvement for researchers and practitioners using deep learning for segmentation tasks.
The paper tackles the problem of inaccurate 3D annotations in deep learning for structure delineation by introducing a method that treats annotations as deformable active contour models, jointly training the network and correcting errors, which boosts performance with potentially inaccurate annotations.
Deep learning-based approaches to delineating 3D structure depend on accurate annotations to train the networks. Yet, in practice, people, no matter how conscientious, have trouble precisely delineating in 3D and on a large scale, in part because the data is often hard to interpret visually and in part because the 3D interfaces are awkward to use. In this paper, we introduce a method that explicitly accounts for annotation inaccuracies. To this end, we treat the annotations as active contour models that can deform themselves while preserving their topology. This enables us to jointly train the network and correct potential errors in the original annotations. The result is an approach that boosts performance of deep networks trained with potentially inaccurate annotations. Code has been released at https://github.com/doruk-oner/AdjustingAnnotationswithSnakes.