External validation of SpineNetv2 deep learning system for automated lumbar spine MRI analysis: A multi-pathology diagnostic agreement study
SpineNetv2 demonstrated high agreement across five binary lumbar pathologies, while Pfirrmann grading remained the main limitation, particularly in elderly upper lumbar discs. Its specificity-oriented profile supports use as a confirmatory second reader, but reliance on negative findings is not recommended. Broader reliability will require multicenter, multi-reader validation and sensitivity-oriented calibration.
Authors
- Xueyuan Wu (ORCID: https://orcid.org/0000-0002-0325-4175)
- Qian Du (ORCID: https://orcid.org/0000-0001-6922-6778)
- Zhiyu Zhou (ORCID: https://orcid.org/0000-0002-8101-2083)
- Kebing Jin (ORCID: https://orcid.org/0000-0002-2788-5756)
- Guangru Cao
- Qibin Song
- Jiaxiang Zhou
Institutions
- Sun Yat-sen University (CN)
- Guizhou University (CN)
- Zunyi Medical University (CN)
- Guizhou Minzu University (CN)
- The Seventh Affiliated Hospital of Sun Yat-sen University (CN)
- Guiyang University (CN)
- The First Affiliated Hospital, Sun Yat-sen University (CN)
Publication Details
- Journal
- European Spine Journal
- Published
- 2025-11-08
- DOI
- https://doi.org/10.1007/s00586-025-09543-z
- Citations
- 1
- Primary Topic
- Medical Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.67