1. MedConv: Convolutions Beat Transformers on Long-Tailed Bone Density Prediction
- Author
-
Qi, Xuyin, Zhang, Zeyu, Zheng, Huazhan, Chen, Mingxi, Kutaiba, Numan, Lim, Ruth, Chiang, Cherie, Tham, Zi En, Ren, Xuan, Zhang, Wenxin, Zhang, Lei, Zhang, Hao, Lv, Wenbing, Yao, Guangzhen, Han, Renda, Wang, Kangsheng, Li, Mingyuan, Mao, Hongtao, Li, Yu, Liao, Zhibin, Zhao, Yang, and To, Minh-Son
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
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.
- Published
- 2025