Dual-level weighted cross-entropy loss function and multi-object region segmentation network evaluation for dynamic knee joint X-ray radiography based on a novel scoring criterion
The proposed multi-object region segmentation model has the potential to greatly enhance the accuracy and effectiveness of quantitative analysis of the knee joint motion.
Authors
- Yingjian Yang
- Yanbing Liu (ORCID: https://orcid.org/0009-0002-1142-7053)
- Nanrong Zeng
- Yi Liu (ORCID: https://orcid.org/0000-0002-1058-0382)
- Shiming Wang (ORCID: https://orcid.org/0000-0003-3222-3914)
- Fajin Lv (ORCID: https://orcid.org/0000-0002-8431-0350)
- Tianqi Wu (ORCID: https://orcid.org/0009-0004-8475-4367)
- Ziran Chen
- Qi Gao
- Jie Zheng
- Weiqing Huang
- Peng Guo
- Jinglong Du
- Yingying Chen
- Junyi Liao
- Zhibo Xiao
- Huai Chen
Institutions
- Northeastern University (US)
- Construction Development (Qatar) (QA)
- Second Affiliated Hospital of Guangzhou Medical University (CN)
- Lantheus Medical Imaging (United States) (US)
- The Affiliated Yongchuan Hospital of Chongqing Medical University (CN)
- Artificial Intelligence in Medicine (Canada) (CA)
- Chongqing Medical University (CN)
- Guangzhou Medical University (CN)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2026-03-04
- DOI
- https://doi.org/10.3389/fmed.2026.1768134
- Primary Topic
- Advanced Neural Network Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00