Grading Loss: A Fracture Grade-based Metric Loss for Vertebral Fracture Detection

Malek El Husseini, Anjany Sekuboyina, Maximilian Löffler, Fernando Navarro, Bjoern H. Menze, Jan S. Kirschke

Abstract

Osteoporotic vertebral fractures have a severe impact on patients' overall well-being but are severely under-diagnosed. These fractures present themselves at various levels of severity measured using the Genant's grading scale. Insufficient annotated datasets, severe data-imbalance, and minor difference in appearances between fractured and healthy vertebrae make naive classification approaches result in poor discriminatory performance. Addressing this, we propose a representation learning-inspired approach for automated vertebral fracture detection, aimed at learning latent representations efficient for fracture detection. Building on state-of-art metric losses, we present a novel Grading Loss for learning representations that respect Genant's fracture grading scheme. On a publicly available spine dataset, the proposed loss function achieves a fracture detection F1 score of 81.5%, a 10% increase over a naive classification baseline.
BibTeX
@inproceedings{husseini2020grading,
  author = {Malek El Husseini and Anjany Sekuboyina and Maximilian Löffler and Fernando Navarro and Bjoern H. Menze and Jan S. Kirschke},
  title = {{Grading Loss: A Fracture Grade-based Metric Loss for Vertebral Fracture Detection}},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
  year = {2020},
  doi = {10.1007/978-3-030-59725-2\_71},
}
Figure