Controlled comparative study of YOLOv8-Pose, YOLOv11-Pose, and Detectron2 for vertebrae detection and keypoint estimation

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: YOLOv8n-Pose fastest inference with competitive performance; Detectron2 models showed lower accuracy and frequent duplicates

• Primary Outcome: YOLOv11n-Pose achieved best balance between keypoint accuracy and inference efficiency

• Nnt Or Sensitivity: YOLOv8l-Pose showed improved accuracy with increased computational cost

• Confidence Interval: Not reported

Clinical Application

High feasibility for integration into existing medical imaging workflows, particularly for automated spine analysis Relevant for Australian radiology departments and spine clinics using automated imaging analysis. Could support TGA-approved medical imaging software development and align with RACGP guidelines for appropriate imaging utilisation Patients requiring spinal imaging analysis and vertebrae alignment assessment

Abstract

Accurate vertebrae detection with precise keypoint localization is essential for medical image analysis and clinical applications, such as spinal alignment assessment. This study presents a controlled, task-driven comparison of four pose-based deep learning models for vertebrae detection and keypoint estimation: YOLOv8n-Pose, YOLOv11n-Pose, and Detectron2 (Keypoint R-CNN) with ResNet-50 and ResNet-101 backbones. A single-class vertebrae dataset with bounding box annotations and four anatomically meaningful keypoints per vertebra was evaluated under consistent training settings. Performance was assessed in terms of keypoint localization accuracy, detection precision, inference speed, and vertebrae-specific prediction behavior, including detection completeness and duplicate detections, which are critical for clinical usability. Results show that YOLOv11n-Pose provides the best balance between keypoint accuracy and inference efficiency, while YOLOv8n-Pose achieves the fastest inference with competitive performance. Detectron2-based models exhibit lower keypoint accuracy, slower inference, and frequent duplicate predictions that obscure correct anatomical landmarks. Additional experiments indicate that larger YOLO variants (particularly YOLOv8l-Pose) improve accuracy, albeit at increased computational cost. Overall, the results demonstrate that model capacity or architectural recency alone does not guarantee superior performance in vertebrae keypoint detection, highlighting the importance of anatomy-aware model selection for spine imaging applications.

References

1. 1.Bansal, A., Kubíček, J., & Garg, S. (2026). Controlled comparative study of YOLOv8-Pose, YOLOv11-Pose, and Detectron2 for vertebrae detection and keypoint estimation. PLoS One. https://doi.org/10.1371/journal.pone.0347290