# Tracing 3D Anatomy in 2D Strokes: A Multi-Stage Projection Driven Approach to Cervical Spine Fracture Identification Source: [Tracing 3D Anatomy in 2D Strokes: A Multi-Stage Projection Driven Approach to Cervical Spine Fracture Identification]() Collection index: [llms.txt]() Data updated: 2026-07-08T05:00:04.940Z Authors: Fabi Nahian Madhurja, Rusab Sarmun, Muhammad E. H. Chowdhury, Adam Mushtak, Israa Al-Hashimi, Sohaib Bassam Zoghoul Published: 2026-01-21T18:15:47.000Z ## Abstract Cervical spine fractures require rapid and accurate diagnosis, yet automatic CT interpretation remains challenging as subtle injuries must be assessed across large 3D volumes. We ask whether full 3D vertebra segmentation is necessary for automated fracture recognition, or whether vertebra masks approximated from 2D projections can preserve sufficient diagnostic context. We propose an end-to-end pipeline that localizes the cervical spine, estimates C1-C7 vertebra masks from optimized 2D projections, and uses the resulting vertebra-level volumes for downstream fracture classification. A YOLOv8 detector first localizes spine regions of interest from multi-view variance projections, achieving a 3D mean Intersection over Union of 94.45%. Multi-label vertebra segmentation is then performed with a DenseNet121-Unet on energy-based sagittal and coronal projections, attaining a mean Dice score of 87.86%. The predicted 2D masks are back-projected and fused into approximate 3D masks for each vertebra to extract volumes of interest from the original CT. These volumes are analyzed by an ensemble of 2.5D spatio-sequential CNN-Transformer models, yielding vertebra-level and patient-level F1 scores of 68.15 and 82.26, area under the receiver operating characteristic curve of 91.62 and 90.95, and area under the precision-recall curve of 75.60 and 92.00, respectively. The projection-derived volumes achieved fracture-recognition performance comparable to a full 3D-segmentation baseline, while shifting the vertebra segmentation stage into a lower-dimensional domain. Saliency-based explainability and interobserver variability analysis further examine interpretability and reliability. Overall, the results indicate that projection-based mask approximation is a viable proxy for full 3D vertebra segmentation in cervical fracture recognition. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Vertebra Fracture Recognition on RSNA dataset (test)](): Vertebra Fracture Recognition; RSNA dataset (test); Accuracy: 94.51. - [Patient-level Fracture Detection on RSNA](): Patient-level fracture detection; RSNA (patient-level); Accuracy: 83.06. - [Vertebra Level Fracture Recognition on RSNA Dataset](): Vertebra Level Fracture Recognition; RSNA Dataset; Accuracy: 0.9451. - [Patient Level Fracture Recognition on Private Dataset](): Patient Level Fracture Recognition; Private Dataset; Accuracy: not recorded. - [Vertebra Level Fracture Recognition on Private Dataset](): Vertebra Level Fracture Recognition; Private Dataset; ROC-AUC: not recorded. ## Original sources and implementation [Original paper]() [PDF]()