YOLOv11-based framework outperforms two-stage ResNet in scoliosis detection from spine X-rays

YOLOv11 outperformed a two-stage ROI-guided ResNet for automated scoliosis detection from spinal radiographs; exact accuracy metrics not reported. Retrospective, single public dataset without external validation.

• Study design: AI model comparison using a publicly available spinal X-ray dataset (n not reported).
• YOLOv11 demonstrated superior diagnostic stability across representative cases, but no quantitative metrics were provided.
• Limitation: No external validation, no comparison with radiologist interpretation, retrospective single-dataset design.

RadPigeon summaries are original and for information only. They are not clinical advice.