Using 2D U-Net convolutional neural networks for automatic acetabular and proximal femur segmentation of hip MRI images and morphological quantification: a preliminary study in DDH
Utilizing U-Net-based image segmentation and automated measurement of morphological parameters significantly enhances the accuracy and efficiency of DDH assessment. These methods improve precision in automatic measurements and provide an objective basis for clinical diagnosis and treatment of DDH.
Authors
- Mao Sheng (ORCID: https://orcid.org/0000-0002-3001-1865)
- Lei Wang (ORCID: https://orcid.org/0000-0002-5065-8447)
- Xiaodong Yang (ORCID: https://orcid.org/0000-0003-4509-6045)
- Dian Zhang (ORCID: https://orcid.org/0000-0002-9079-3889)
- Mengli Zhou (ORCID: https://orcid.org/0000-0001-5933-7722)
- Huihui Jia
- Tianli Zhou
- Yan Chang
Institutions
- Xuzhou Medical College (CN)
- Chinese Academy of Sciences (CN)
- Wenzhou Medical University (CN)
- State Intellectual Property Office (CN)
- Soochow University (CN)
- Affiliated Eye Hospital of Wenzhou Medical College (CN)
- Suzhou Institute of Biomedical Engineering and Technology (CN)
Publication Details
- Journal
- BioMedical Engineering OnLine
- Published
- 2024-10-05
- DOI
- https://doi.org/10.1186/s12938-024-01291-3
- Citations
- 8
- Primary Topic
- Hip disorders and treatments
- Type
- article
- Field-Weighted Citation Impact
- 4.58