MedConv: Convolutions Beat Transformers on Long-Tailed Bone Density Prediction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910902312239104 |
|---|---|
| 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 To, Minh-Son |
| author_facet | 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 To, Minh-Son |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_00631 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MedConv: Convolutions Beat Transformers on Long-Tailed Bone Density Prediction 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 To, Minh-Son Computer Vision and Pattern Recognition 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. |
| title | MedConv: Convolutions Beat Transformers on Long-Tailed Bone Density Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.00631 |