Btrfly Net: Vertebrae Labelling with Energy-based Adversarial Learning of Local Spine Prior
This work addresses automated spine analysis for medical imaging, offering a novel method with strong gains in a domain-specific application.
The paper tackled vertebrae labeling in spine analysis by proposing Btrfly Net, a butterfly-shaped architecture combining sagittal and coronal reformations, and an energy-based adversarial training regime to encode local spine structure, achieving state-of-the-art performance on a benchmark dataset of 302 scans without post-processing.
Robust localisation and identification of vertebrae is essential for automated spine analysis. The contribution of this work to the task is two-fold: (1) Inspired by the human expert, we hypothesise that a sagittal and coronal reformation of the spine contain sufficient information for labelling the vertebrae. Thereby, we propose a butterfly-shaped network architecture (termed Btrfly Net) that efficiently combines the information across reformations. (2) Underpinning the Btrfly net, we present an energy-based adversarial training regime that encodes local spine structure as an anatomical prior into the network, thereby enabling it to achieve state-of-art performance in all standard metrics on a benchmark dataset of 302 scans without any post-processing during inference.