文献速递骨肌技术与安全DR

AI骨病变分类器用于X线片:以敏感度为导向的优化

AI bone lesion classifier with sensitivity-driven optimization for radiographs.
PubMed 文献 · Clin Radiol · 2025-09-05

本研究开发了用于X线片检测原发性骨病变的深度学习分类器,采用MobileNetV2架构并以敏感度为导向优化以减少假阴性。数据集含310例患者的1177张上下肢X线片(异常547张、正常630张),在独立测试集上敏感度96.6%、特异度82.2%、准确率87.9%、AUC 0.94(95%CI 0.901–0.981)。

要点

  • 模型在测试集上敏感度96.6%、特异度82.2%,以高敏感度减少骨病变漏诊为目标。
  • AUC 0.94(95%CI 0.901–0.981),提示对正常与异常X线片有较好的区分能力。
  • 研究生成注意力图以增强模型可解释性并可视化决策相关区域。

核心结论

  • 研究显示,以敏感度为导向优化的AI工具用于X线片骨肿瘤检测具有可行性,可能提高诊断准确性、减少诊断延迟并支持人群健康举措。

研究设计与样本

  • 由委员会认证的放射科医师审核上下肢X线片,分为「正常」(无骨病变)与「异常」(有骨病变)两组;最终数据集为310例患者的1177张X线片(异常547张、正常630张)。

关键影像表现/征象

  • 模型基于MobileNetV2架构训练,采用以敏感度为导向的方法以尽量减少假阴性。
  • 生成注意力图以增强可解释性并可视化对模型决策有贡献的区域。

诊断标准与关键数值

  • 在独立测试集上,敏感度为96.6%、特异度为82.2%、准确率为87.9%。
  • AUC为0.94,95%CI为[0.901, 0.981]。

临床应用与阅片要点

  • 作者认为,以敏感度为导向优化的AI工具用于X线片骨肿瘤检测具有可行性,可能提高诊断准确性、减少诊断延迟并支持人群健康举措。

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)。

英文原文(摘要)· 点击展开

AIM: This study aims to develop a deep learning classifier for detecting primary bone lesions on radiographs, emphasizing high sensitivity while maintaining practical clinical usability.

MATERIAL AND METHODS: Radiographs of the upper and lower extremities were reviewed by board-certified radiologists and categorized into two groups: "Normal" (without bone lesions) and "Abnormal" (with bone lesions). The final dataset comprised 1,177 radiographs from 310 patients, including 547 abnormal and 630 normal cases. The MobileNetV2 architecture was trained with a sensitivity-driven approach designed to minimize false negatives. Model performance was evaluated on a hold-out test set, and attention maps were generated to enhance interpretability and visualize regions contributing to the model's decisions.

RESULTS: The model was tested on a naïve hold-out test set. The results received on the test set: sensitivity of 96.6%, specificity of 82.2%, accuracy of 87.9%, area under the curve (AUC) of 0.94, and 95% confidence interval of [0.901, 0.981].

CONCLUSION: The study demonstrates the feasibility of deploying AI-based tools for radiographic detection of bone tumors with a sensitivity-focused optimization. These tools have the potential to enhance diagnostic accuracy, reduce diagnostic delays, and support population health initiatives.

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Rinott B, Dekel CZ, Ilivitzki A, et al. AI bone lesion classifier with sensitivity-driven optimization for radiographs. Clin Radiol. 2025. PMID: 41016074. doi:10.1016/j.crad.2025.107075

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。