Extending convolutional neural networks to detect differences in symmetry in videorasterstereographic back scans with the aim to improve screening for adolescent idiopathic scoliosis
Adapting CNNs to include symmetry analysis could be an improvement to other known applications of deep learning in spinal deformity analysis. Refining the dataset to incorporate more mild cases could enhance the performance of DeepSymNet in particular. With these modifications, DeepSymNet as well as VGG16 are promising approaches for future AIS screenings.
Authors
- Andreas Heinke (ORCID: https://orcid.org/0009-0009-4218-418X)
- Arkadiusz Żurawski (ORCID: https://orcid.org/0000-0003-2564-8607)
- Thurid Jochim
- Hagen Malberg (ORCID: https://orcid.org/0009-0001-4063-6877)
- Nico Stecher (ORCID: https://orcid.org/0009-0009-4107-9169)
- Anke Tschirschky
- Paula Wilhelm
Institutions
- Jan Kochanowski University (PL)
- Technische Universität Dresden (DE)
Publication Details
- Journal
- European Spine Journal
- Published
- 2025-11-10
- DOI
- https://doi.org/10.1007/s00586-025-09520-6
- Primary Topic
- Scoliosis diagnosis and treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Bundesministerium für Bildung und Forschung
- Technische Universität Dresden
- Sächsische Aufbaubank