发表机构
AI Dentify（AI Dentify）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过大规模全景X光片语料库系统评估发现，牙齿分割的瓶颈在于边界精度而非检测，分辨率提升比架构创新更有效。
AI 中文摘要
全景X光片上的自动牙齿分割和FDI编号支撑着计算机辅助牙科诊断，然而哪些因素主导性能仍不清楚。我们构建了一个包含1,422张全景X光片的语料库，其中包含42,142个由专家描绘的牙齿多边形，覆盖32类FDI分类体系，由30名牙科从业者标注并由另外两名独立审查，并在单一评估协议下隔离输入分辨率、架构和解剖先验的影响。首先，分辨率占主导：在受控的640/1024/1280消融中，mask mAP50-95从0.656升至0.710再升至0.717，而mAP50保持在约0.982不变。在图像上的配对bootstrap下，两个增益均显著（p < 0.001，p = 0.024）；两个mAP50变化均与零无显著差异。增加的分辨率带来边界精度，而非检测能力。其次，架构在域内几乎无关：一个参数多2.1倍的基于查询的transformer与单阶段检测器在统计上等效（95% CI [-0.0064, +0.0064]），在域偏移下仅略微更好，CPU上慢5.5倍，且无法在标准ONNX运行时下执行。第三，三项针对性干预失败：LoRA适配的自监督编码器表现不佳，可提示的基础分割器使mask退化39%，全局最优解剖标签分配仅带来+0.0007的提升，尽管纠正了40%域外预测中违反的约束。对独立多中心队列的零样本迁移（经验证无重叠）损失了62%的mask mAP50-95，但仅损失18%的mAP50，重现了这种分离。沿牙齿轴分解mask将残余误差定位到根尖三分之一。因此，边界精度是约束瓶颈，努力应更集中于分辨率和采集多样性，而非架构新颖性。
英文摘要
Automatic tooth segmentation and FDI numbering on panoramic radiographs underpins computer-assisted dental diagnosis, yet which factors govern performance remains unclear. We assemble a corpus of 1,422 panoramic radiographs containing 42,142 expert-delineated tooth polygons across the 32-class FDI taxonomy, annotated by 30 dental practitioners and independently reviewed by two others, and use it to isolate input resolution, architecture and anatomical priors under a single evaluation protocol. First, resolution dominates: across a controlled 640/1024/1280 ablation, mask mAP50-95 rises 0.656 -> 0.710 -> 0.717 while mAP50 stays flat at ~0.982. Both gains are significant under a paired bootstrap over images (p < 0.001, p = 0.024); neither mAP50 change is distinguishable from zero. Added resolution buys boundary precision, not detection. Second, architecture is nearly irrelevant in-domain: a query-based transformer with 2.1x the parameters is statistically equivalent to a one-stage detector (95% CI [-0.0064, +0.0064]), only marginally better under domain shift, 5.5x slower on CPU and not executable under standard ONNX runtimes. Third, three targeted interventions fail: a LoRA-adapted self-supervised encoder underperforms, a promptable foundation segmenter degrades masks by 39%, and globally optimal anatomical label assignment yields +0.0007 despite correcting a constraint violated in 40% of out-of-domain predictions. Zero-shot transfer to an independent multi-centre cohort, verified overlap-free, costs 62% of mask mAP50-95 but only 18% of mAP50, reproducing the dissociation. Decomposing masks along the tooth axis localises the residual error to the apical third. Boundary precision is therefore the binding constraint, and effort is better directed at resolution and acquisition diversity than at architectural novelty.
Comments15 pages, 6 figures, 5 tables. Code: https://github.com/Rehan000/opg-tooth-segmentation
