arXiv cs.AI· Fabi Nahian Madhurja, Rusab Sarmun, Muhammad E. H. Chowdhury, Adam Mushtak, Israa Al-Hashimi, Sohaib Bassam Zoghoul·· 4 小时前AI 评分36
用 2D 投影生成的掩码能否替代 3D 分割用于颈椎骨折识别
Tracing 3D Anatomy in 2D Strokes: Can Projection-Derived Masks Replace 3D Segmentation for Cervical Spine Fracture Recognition?
AI 导读
一项研究提出多阶段流程:YOLOv8 从多视图方差投影定位颈椎(3D 平均 IoU 94.45%),DenseNet121-Unet 在矢状与冠状投影上分割椎体(平均 Dice 87.86%),2D 掩码反投影融合成近似 3D 掩码后由 2.5D CNN-Transformer 集成模型分析。
正文 · 原文
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 fracture recognition, or whether vertebra masks approximated from 2D projections preserve sufficient diagnostic context. In the proposed multi-stage pipeline, a YOLOv8 detector localizes the cervical spine from multi-view variance projections (3D mean Intersection over Union 94.45%). Multi-label vertebra segmentation is performed with a DenseNet121-Unet on energy-based sagittal and coronal projections (mean Dice 87.86%). The predicted 2D masks are back-projected and fused into approximate 3D masks per vertebra to extract volumes of interest from the original CT, which are analyzed by an ensemble of 2.5D spatio-sequential CNN-Transformer models. On the full RSNA 2022 cohort at native prevalence (2,019 patients, five-fold cross-validation), the pipeline yields vertebra-level and patient-level F1-scores of 68.15% and 82.28%, area under the receiver operating characteristic curve of 91.63% and 90.95%, and area under the precision-recall curve (AUPRC) of 75.64% and 92.00%. With the classifier architecture fixed, replacing 3D-segmentation masks by projection-derived masks changed vertebra-level and patient-level AUPRC by +1.03 and +0.65 points, and the pipeline differed from the reproduced RSNA 2022 winning solution by -0.55 and +0.15 points. No AUPRC difference was statistically significant, and fold-wise 95% confidence intervals excluded vertebra-level losses larger than 1.46 and 2.81 points, respectively. Explainability and interobserver analyses examine reliability. Projection-based mask approximation is therefore a viable proxy for 3D vertebra segmentation in cervical fracture recognition.
| Comments: | Includes supplementary material. Under revision at Medical Image Analysis |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2601.15235 [cs.CV] |
| (or arXiv:2601.15235v5 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2601.15235 arXiv-issued DOI via DataCite |
Submission history
From: Fabi Nahian Madhurja [view email]
[v1]
Wed, 21 Jan 2026 18:15:47 UTC (10,377 KB)
[v2]
Sun, 15 Feb 2026 16:04:57 UTC (33,700 KB)
[v3]
Wed, 4 Mar 2026 06:54:39 UTC (27,171 KB)
[v4]
Thu, 2 Jul 2026 18:23:07 UTC (26,993 KB)
[v5]
Fri, 13 Nov 2026 18:54:05 UTC (33,346 KB)
来源:arXiv cs.AI · arxiv.org