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

TL;DR

This paper introduces a novel grading loss function for vertebral fracture detection that leverages fracture severity grades, significantly improving detection performance on a challenging dataset.

Contribution

It proposes a new Grading Loss based on Genant's fracture grading, enhancing representation learning for better fracture detection accuracy.

Findings

Achieved 81.5% F1 score on the dataset

10% improvement over baseline methods

Effective handling of data imbalance and subtle appearance differences

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.