发表机构
The University of Texas at Austin（德克萨斯大学奥斯汀分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出RibAssist 3D模型，通过CT的双侧投影实现肋骨骨折的检测、配对与选择性3D定位，识别跨视图配对置信度为瓶颈，经实验验证其几何精度高，可辅助提升肋骨骨折定位效率。
AI 中文摘要
肋骨骨折是常见且具有临床意义的损伤，但在计算机断层扫描（CT）上进行定位耗时较长。本研究探究能否在受控的3D假阳性输出率下，将两个正交投影（前后位AP和侧位）中检测到的骨折进行跨视图配对并三角化为可靠的3D骨折点，通过分阶段诊断研究对此进行验证。双侧几何结构是精确的：当配对正确时，检测器预测的中心重构后3D误差中位数为4.0 mm。在密封队列中，双视图可用性达61.1%，候选图中58.4%的骨折存在正确配对。瓶颈并非几何结构或定位，而是受置信度限制的跨视图配对。侧位检测器的重新训练将双视图可用性从开发阶段的0.52提升至0.76，在10 mm处的召回率从0%提升至2.44%。当模型选择正确配对时，输出点几何精度高（密封队列中位数1.49 mm，肋骨匹配率93%）。对未接触的55例队列进行预设验证，从601处骨折中成功将15处转为正确的3D定位，每例产生0.436个假3D点，端到端承诺率达2.50%。本研究的贡献包括经验证的双侧重建几何结构、高条件定位保真度，分阶段识别跨视图配对置信度为有效瓶颈，以及保留不确定结果的选择性辅助工作流程，而非独立自动重建器。
英文摘要
Rib fractures are common and time-consuming to localize on computed tomography (CT). We ask whether fractures detected independently in two orthogonal CT-derived projections (anteroposterior and lateral) can be paired across views and triangulated into reliable 3D points at a controlled rate of false outputs, and we answer it with a staged diagnostic study. The projection geometry is exact, and given correct correspondence, localization is accurate (median 4.0 mm, 88% within 10 mm, 93.6% rib-exact). On a sealed 55-case cohort, a large share of fractures is in principle recoverable (61.1% dual-view availability, and a correct pair present in the candidate graph for 58.4% of fractures), yet the binding limitation is neither geometry nor localization but confidence-limited cross-view correspondence. A controlled detector-by-correspondence factorial attributes the operational gain to lateral-detector quality rather than the tested matching methods; retraining the lateral detector produces the first nonzero controlled-budget reconstructions. Under a deliberately conservative commitment policy, a pre-specified sealed pass promotes 15 of 601 fractures to correct 3D localizations at 0.436 false points per case (2.50% end-to-end commitment yield), and committed points are accurate (median 1.49 mm, 93% rib-exact). The low yield is a consequence of confidence-gated abstention, not of geometry or detection: the study establishes a reproducible framework for selective 3D localization and identifies cross-view correspondence as the dominant operational bottleneck.
Comments9 pages, 6 figures. Code available at: https://github.com/kabJhai/RibAssist-3D
