Hands-Free Segmentation of Medical Volumes via Binary Inputs
This incremental method addresses hands-free segmentation for medical imaging, potentially aiding radiologists in reducing manual effort.
The authors tackled interactive 3D medical volume segmentation by having users answer binary questions to refine organ boundaries, achieving improved performance over random questioning and thresholded probability map baselines on a prostate MRI dataset.
We propose a novel hands-free method to interactively segment 3D medical volumes. In our scenario, a human user progressively segments an organ by answering a series of questions of the form "Is this voxel inside the object to segment?". At each iteration, the chosen question is defined as the one halving a set of candidate segmentations given the answered questions. For a quick and efficient exploration, these segmentations are sampled according to the Metropolis-Hastings algorithm. Our sampling technique relies on a combination of relaxed shape prior, learnt probability map and consistency with previous answers. We demonstrate the potential of our strategy on a prostate segmentation MRI dataset. Through the study of failure cases with synthetic examples, we demonstrate the adaptation potential of our method. We also show that our method outperforms two intuitive baselines: one based on random questions, the other one being the thresholded probability map.