文献速递牙体牙髓病口腔修复与种植

有损JPEG压缩对全景片AI诊断输出稳定性的影响

Effect of lossy JPEG compression on AI diagnostic output stability in panoramic radiograph analysis.
PubMed 文献 · J Dent · 2026-09-12

结果显示压缩级别≥50时所有临床重要标签输出一致性保持良好,而≤30时根尖周透射影和龋齿等低对比度病变出现明显退化,建议最低压缩级别为50并报告所用压缩参数。

要点

  • 压缩级别≥50时AI输出与无压缩参考高度一致,临床重要标签未受影响。
  • 压缩级别≤30时根尖周透射影和龋齿等低对比度病变诊断输出显著下降。
  • 退化主要表现为漏诊而非误诊,建议避免压缩级别低于50并报告压缩参数。

核心结论

  • JPEG压缩级别≥50可保持AI对所有临床重要标签的输出稳定性,而≤30会导致有意义的退化,尤其影响根尖周透射影和龋齿。

研究设计与样本

  • AI系统对每张图像32个牙位的9个诊断类别赋予二分类标签,采用Cohen's kappa量化压缩图像与无压缩输出的一致性。

主要发现

  • 压缩主要导致发现丢失而非假阳性,罕见幻觉缺失牙位。
  • 所有标签在J90和J70时一致性接近完美(κ ≥ 0.920)。
  • 四个修复/修复性标签(种植体、桥、冠、根管充填)在所有压缩级别下不受影响,但种植体和桥的患病率低(≤1.3%)。
  • 五个标签低于一致性阈值:根尖周透射影和充填在J30,下颌管在J50,龋齿和现存/完整牙在J10。
  • 根尖周透射影的阳性百分比一致性在J10降至0.614,每牙精确一致性降至89.1%。

关键数值与推荐

  • 预定义一致性阈值κ = 0.90。
  • 推荐最低压缩级别为50,并应报告所用压缩参数。
  • 压缩级别90可实现约90%的文件大小缩减,且输出一致性损失可忽略。

临床怎么用

  • 临床使用AI分析全景片时,JPEG压缩级别应不低于50,并记录压缩设置以确保输出稳定性。
  • 对于根尖周透射影和龋齿等低对比度病变,应避免使用压缩级别≤30,以防漏诊增加。

局限性

  • 研究仅反映输出稳定性而非绝对诊断准确性。
  • 结果不应在未经验证的情况下推广到其他AI系统。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVES: To evaluate the effect of lossy JPEG compression on the output stability of a commercial AI system applied to panoramic radiographs. METHODS: One hundred panoramic radiographs were saved as uncompressed TIFF (reference standard) and at five JPEG compression levels (CL) - 90, 70, 50, 30, and 10 (J90-J10). All 600 images were processed by a commercial dental AI system (X-ray Insights, dentalXrai GmbH) which assigned binary labels for nine diagnostic categories across 32 tooth positions per image. Agreement between each compressed image and the system's own uncompressed output was quantified by Cohen's kappa (κ), with κ = 0.90 predefined as the agreement threshold. RESULTS: Compression predominantly caused loss of findings rather than false positives, with rare hallucination of absent tooth positions. All labels showed near-perfect agreement at J90 and J70 (κ ≥ 0.920). Four prosthetic and restorative labels (implant, bridge, crown, root canal filling) were unaffected at all CLs, although implant and bridge prevalence was low (≤1.3%). Five labels fell below the agreement threshold: periapical radiolucency and filling at J30, mandibular canal at J50, and caries and present/intact at J10. Positive percent agreement for periapical radiolucency fell to 0.614 and per-tooth exact agreement to 89.1% at J10. CONCLUSION: CL ≥ 50 preserved AI output across all clinically important labels, whereas CL ≤ 30 caused meaningful degradation, particularly for periapical radiolucency and caries. A minimum CL of 50 is recommended, and the compression applied should be reported. These findings reflect output stability rather than absolute diagnostic accuracy and should not be generalized to other AI systems without validation. CLINICAL SIGNIFICANCE: Most file-size reduction is achieved at CL 90 (≈90% reduction) with negligible loss of output agreement. Diagnostic tasks are not equally affected - low-contrast findings degrade whereas high-contrast ones remain robust. Degradation occurs predominantly through missed findings rather than false positives. A CL below 50 should therefore be avoided.

来源:J Dent,查看原文。版权归原作者所有。

引用

  1. Fidler A, Krenker V, Karobari MI, et al. Effect of lossy JPEG compression on AI diagnostic output stability in panoramic radiograph analysis. J Dent. 2026. PMID: 42731775. doi:10.1016/j.jdent.2026.107033

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。