Weakly Supervised Volumetric Image Segmentation with Deformed Templates
This addresses the challenge of reducing annotation effort for 3D medical image segmentation, though it is incremental as it builds on existing weakly supervised 2D approaches.
The paper tackles the problem of weakly supervised volumetric image segmentation by proposing a method that uses only sparse 3D points on object surfaces instead of detailed 2D masks, and shows it substantially reduces the required effort on CT, MRI, and EM datasets.
There are many approaches to weakly-supervised training of networks to segment 2D images. By contrast, existing approaches to segmenting volumetric images rely on full-supervision of a subset of 2D slices of the 3D volume. We propose an approach to volume segmentation that is truly weakly-supervised in the sense that we only need to provide a sparse set of 3D points on the surface of target objects instead of detailed 2D masks. 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 it provides to train a network to find accurate boundaries. We evaluate our approach on Computed Tomography (CT), Magnetic Resonance Imagery (MRI) and Electron Microscopy (EM) image datasets and show that it substantially reduces the required amount of effort.