MedConv: Convolutions Beat Transformers on Long-Tailed Bone Density Prediction
This work improves bone health assessment for clinical settings by offering a more efficient and accurate model, though it is incremental in method.
The paper tackled bone density prediction from CT scans by addressing computational complexity and data imbalance, achieving up to 21% accuracy and 20% ROC AUC improvement over prior methods.
Bone density prediction via CT scans to estimate T-scores is crucial, providing a more precise assessment of bone health compared to traditional methods like X-ray bone density tests, which lack spatial resolution and the ability to detect localized changes. However, CT-based prediction faces two major challenges: the high computational complexity of transformer-based architectures, which limits their deployment in portable and clinical settings, and the imbalanced, long-tailed distribution of real-world hospital data that skews predictions. To address these issues, we introduce MedConv, a convolutional model for bone density prediction that outperforms transformer models with lower computational demands. We also adapt Bal-CE loss and post-hoc logit adjustment to improve class balance. Extensive experiments on our AustinSpine dataset shows that our approach achieves up to 21% improvement in accuracy and 20% in ROC AUC over previous state-of-the-art methods.