文献速递口腔颌面外科

多模态语言模型用于颌骨坏死诊断与治疗

Multimodal Language Model for Jaw Osteonecrosis Diagnosis and Treatment.
PubMed 文献 · J Dent Res · 2025-06-24

本研究回顾性收集366例颌骨坏死(ONJ)患者全景X线片和病历,开发了视觉-语言交互系统ONJ-TS,用于ONJ诊断与治疗支持。系统回答准确率0.9598(95%CI 0.9351-0.9845),超过初级口腔颌面外科医生0.8835(95%CI 0.8432-0.9238,P=0.003),与高级医生0.9959(95%CI 0.8432-0.9238)疗效相当(P<0.001)。

要点

  • ONJ-TS系统基于微调的Qwen2-VL核心,结合SwinTransformer识别ONJ和U-Net分割ONJ区域。
  • 系统回答准确率0.9598,超过初级口腔颌面外科医生的0.8835(P=0.003)。
  • 系统与高级口腔颌面外科医生准确率0.9959相比疗效相当(P<0.001)。

核心结论

  • ONJ-TS系统在ONJ治疗支持回答生成方面优于基线模型,有望作为支持临床决策的数字解决方案。

研究设计与样本

  • 回顾性收集366例ONJ患者全景X线片和病历,开发ONJ-TS系统,核心Qwen2-VL微调用于自然语言问答,SwinTransformer和U-Net分别用于识别ONJ病例和分割ONJ区域。

主要发现

  • ONJ-TS系统准确率0.9598(95%CI 0.9351-0.9845) vs 初级口腔颌面外科医生0.8835(95%CI 0.8432-0.9238),P=0.003。
  • ONJ-TS系统与高级口腔颌面外科医生(准确率0.9959,95%CI 0.8432-0.9238)疾病管理疗效相当,P<0.001。
  • 广泛实验显示ONJ-TS系统在生成准确治疗支持回答方面优于基线模型。

关键数值与推荐

  • ONJ-TS系统回答准确率为0.9598(95%CI 0.9351-0.9845)。
  • 初级口腔颌面外科医生回答准确率为0.8835(95%CI 0.8432-0.9238)。
  • 高级口腔颌面外科医生回答准确率为0.9959(95%CI 0.8432-0.9238)。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

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

Owing to the complexity of the clinical manifestations in patients with osteonecrosis of the jaw (ONJ), particularly in settings lacking oral and maxillofacial surgery, timely and accurate treatment remains challenging. Here, we developed an integrated vision-language interactive system (namely, the Osteonecrosis of the Jaw Treatment Supporting [ONJ-TS] system), which is designed to provide clinical support for the diagnosis and treatment of ONJ. We retrospectively collected panoramic radiography (PR) images and medical records of 366 patients with ONJ to develop the ONJ-TS system. In the ONJ-TS system, the core Qwen2-VL was fine-tuned for natural language question answering on ONJ treatment. To support the primary functionality of the Qwen2-VL, we trained the SwinTransformer and the U-Net to identify ONJ cases and segment the ONJ regions in the PR images, respectively. Human evaluation of the output responses indicated that the ONJ-TS system exceeded the accuracy levels of junior oral and maxillofacial surgeons (OMFSs) with accuracy scores of 0.9598 (95% confidence interval [CI], 0.9351-0.9845) and 0.8835 (95% CI, 0.8432-0.9238), respectively (P = 0.003). Notably, in comparative analyses with the senior OMFSs (accuracy, 0.9959 [95% CI, 0.8432-0.9238]), the ONJ-TS system demonstrated comparable efficacy in disease management (P < 0.001). Extensive experiments showed that the ONJ-TS system outperformed baseline models in generating accurate responses to treatment support. Given its multifaceted capabilities, the ONJ-TS system holds promise as a digital solution for supporting clinical decisions in managing ONJ and enhancing clinical efficiency and treatment accuracy.

来源:J Dent Res,查看原文。版权归原作者所有。

引用

  1. Gao X, Zhao L, Zhang Q, et al. Multimodal Language Model for Jaw Osteonecrosis Diagnosis and Treatment. J Dent Res. 2025. PMID: 40552509. doi:10.1177/00220345251334575

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。