Prompt-Based Vertebral Segmentation Using a Generative Ai Approach in OVCF Spinal Radiographs

Osteoporotic vertebral compression fractures (OVCFs) are prevalent among elderly patients, with X-ray imaging serving as the primary diagnostic tool. However, challenges such as organ obstruction and poor contrast after vertebroplasty procedures complicate vertebral segmentation in spinal X-rays. This research introduces an innovative generative AI framework for vertebral segmentation in spinal X-ray images, combining YOLO-based detection with prompt-driven segmentation inspired by the Segment Anything Model (SAM). The system generates bounding boxes around vertebrae as segmentation prompts and employs an interpolation strategy to address potentially missed compressed vertebrae. By incorporating domain-specific knowledge of vertebral anatomy via the interpolation strategy, the framework enables accurate delineation of vertebral structures in cases of compression fractures. The model achieves impressive performance metrics, including a Dice coefficient of 0.9389 ± 0.0026, an IoU of 0.8854 ± 0.0045, and a sensitivity of 0.9436 ± 0.0062. Validation was conducted using data from 305 patients and 813 spinal X-ray images sourced from Taipei Medical Hospital (2014-2024), with training based on 164 patients (531 images, 2014-2019) and validation on 141 patients (282 images, 2020-2024). This generative AI application effectively addresses clinical challenges in vertebral segmentation for OVCF patients, potentially enhancing the accuracy of diagnoses and treatment planning.