MedDet: Generative Adversarial Distillation for Efficient Cervical Disc Herniation Detection
_{^{BIBM 2024 Oral}}

Zeyu Zhang^*, Nengmin Yi^*, Shengbo Tan^*, Ying Cai^✉, Yi Yang, Lei Xu, Qingtai Li, Zhang Yi, Daji Ergu, Yang Zhao

^*Equal contribution ^✉Corresponding author: [email protected]

Cervical disc herniation (CDH) is a prevalent musculoskeletal disorder that significantly impacts health and requires labor-intensive analysis from experts. Despite advancements in automated detection of medical imaging, two significant challenges hinder the real-world application of these methods. First, the computational complexity and resource demands present a significant gap for real-time application. Second, noise in MRI reduces the effectiveness of existing methods by distorting feature extraction. To address these challenges, we propose three key contributions: Firstly, we introduced MedDet, which leverages the multi-teacher single-student knowledge distillation for model compression and efficiency, meanwhile integrating generative adversarial training to enhance performance. Additionally, we customize the second-order nmODE to improve the model's resistance to noise in MRI. Lastly, we conducted comprehensive experiments on the CDH-1848 dataset, achieving up to a 5% improvement in mAP compared to previous methods. Our approach also delivers over 5 times faster inference speed, with approximately 67.8% reduction in parameters and 36.9% reduction in FLOPs compared to the teacher model. These advancements significantly enhance the performance and efficiency of automated CDH detection, demonstrating promising potential for future application in clinical practice.

News

(10/14/2024) 🎉 Our paper has been accepted for an oral presentation at BIBM 2024!

Citation

@article{zhang2024meddet,
  title={MedDet: Generative Adversarial Distillation for Efficient Cervical Disc Herniation Detection},
  author={Zhang, Zeyu and Yi, Nengmin and Tan, Shengbo and Cai, Ying and Yang, Yi and Xu, Lei and Li, Qingtai and Yi, Zhang and Ergu, Daji and Zhao, Yang},
  journal={arXiv preprint arXiv:2409.00204},
  year={2024}
}