Papers

用物理模拟训练 AI 矫正口腔全景片摆位误差,无需重拍

Fix, Don't Retake: Physics-Simulated Training for Correcting Patient Positioning Errors in Dental Panoramic Radiographs

Why we picked it

给牙科影像团队看的:研究者用 CT 体数据模拟摆位错误造训练对,五种模型里 U-Net 和误差条件化方案表现最好,能直接在已有片子上纠正而不是让患者重拍,省剂量也省时间。

一篇新研究针对全景牙片因患者摆位错误导致的失真和重复拍摄问题,用基于物理的模拟器从锥形束 CT 体数据生成摆位正确与错误的配对全景片,并可控地注入单独或组合的摆位误差。

Body

研究对比了五种方案:U-Net、pix2pix、条件扩散模型、误差条件化模型以及按误差类型分工的专家混合模型,在三个测试集上用图像相似度和几何指标评估。结果显示所有方法都提升了平均图像相似度并降低几何误差,其中 U-Net 和两种误差感知方案明显优于 pix2pix 与条件扩散模型。

这类方法若落地,可减少重复曝光带来的辐射剂量和科室运营成本,对口腔影像设备和软件厂商有直接的工程参考价值。

Original · arXiv cs.AI

Fix, Don't Retake: Physics-Simulated Training for Correcting Patient Positioning Errors in Dental Panoramic Radiographs

Patient-positioning errors can distort panoramic radiographs and lead to repeat examinations. This study investigated artificial intelligence for correcting these errors in existing images. A physics-based simulator generated paired correctly positioned and mispositioned panoramics from cone-beam computed tomography volumes, with controlled individual and combined positioning errors. Five approaches were compared: U-Net, pix2pix, conditional diffusion, an error-conditioned model, and a mixture of error-specific specialists. Evaluation used image similarity and geometric metrics across three test sets. All approaches improved mean image similarity and reduced geometric errors, with U-Net and the two error-aware approaches outperforming pix2pix and conditional diffusion.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include U-Net, diffusion models, medical imaging.

Source attribution: curated from arXiv cs.AI (@Sema Helali, Lina Abu Nada, Faleh Tamimi, Rafat Damseh).