基于X线平片的深度学习模型提升放射科医生对原发性骨肿瘤组织学分型的分类表现:一项多中心研究
本回顾性多中心研究纳入两中心878例经病理确诊的原发性骨肿瘤患者,基于EfficientNet-B3构建结合X线平片与临床特征的深度学习模型,对五种组织学类型进行五分类,内部/外部测试集宏观平均AUC为0.904/0.873。观察者研究显示,模型辅助可提高初级和高级放射科医生的准确率、缩短解读时间并提升信心。
要点
- 模型在内部/外部测试集五分类宏观平均AUC为0.904/0.873,外部测试准确率68.7%。
- 模型辅助使初级医生准确率由50.6%升至72.3%,高级医生由68.7%升至75.3%(P<0.05)。
- 模型将初级医生解读时间由53.07秒缩短至18.55秒,高级医生由32.50秒缩短至21.42秒。
核心结论
- 结合X线平片与临床特征的深度学习模型可有效对原发性骨肿瘤的组织学类型进行五分类,并辅助放射科医生获得优于其独立视觉评估的分类结果。
研究设计与样本
- 回顾性研究,纳入两中心878例经病理确诊的原发性骨肿瘤患者,训练集638例、验证集77例、内部测试集80例、外部测试集83例;基于EfficientNet-B3构建结合X线平片与临床特征的深度学习模型进行五分类;以病理为参考标准;由四名放射科医生参与观察者研究评估临床效用。
诊断标准与关键数值
- 五分类类别为软骨源性肿瘤、成骨性肿瘤、破骨细胞巨细胞丰富肿瘤、其他骨间叶肿瘤及其他组织学类型原发性骨肿瘤;结合模型在内部/外部测试集宏观平均AUC为0.904/0.873,准确率67.5%/68.7%,宏观平均敏感度66.9%/57.2%,宏观平均特异度92.1%/91.6%。
临床应用与阅片要点
- 观察者研究中,模型辅助使初级医生准确率由50.6%升至72.3%、解读时间由53.07秒缩短至18.55秒、5点Likert信心评分由3.10升至3.73(各项P<0.05);高级医生准确率由68.7%升至75.3%、解读时间由32.50秒缩短至21.42秒、信心评分由4.19升至4.37(各项P<0.05)。
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
PURPOSE: To develop a deep learning (DL) model for classifying histological types of primary bone tumors (PBTs) using radiographs and evaluate its clinical utility in assisting radiologists.
METHODS: This retrospective study included 878 patients with pathologically confirmed PBTs from two centers (638, 77, 80, and 83 for the training, validation, internal test, and external test sets, respectively). We classified PBTs into five categories by histological types: chondrogenic tumors, osteogenic tumors, osteoclastic giant cell-rich tumors, other mesenchymal tumors of bone, or other histological types of PBTs. A DL model combining radiographs and clinical features based on the EfficientNet-B3 was developed for five-category classification. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were calculated to evaluate model performance. The clinical utility of the model was evaluated in an observer study with four radiologists.
RESULTS: The combined model achieved a macro average AUC of 0.904/0.873, with an accuracy of 67.5 %/68.7 %, a macro average sensitivity of 66.9 %/57.2 %, and a macro average specificity of 92.1 %/91.6 % on the internal/external test set, respectively. Model-assisted analysis improved accuracy, interpretation time, and confidence for junior (50.6 % vs. 72.3 %, 53.07[s] vs. 18.55[s] and 3.10 vs. 3.73 on a 5-point Likert scale [P < 0.05 for each], respectively) and senior radiologists (68.7 % vs. 75.3 %, 32.50[s] vs. 21.42[s] and 4.19 vs. 4.37 [P < 0.05 for each], respectively).
CONCLUSION: The combined DL model effectively classified histological types of PBTs and assisted radiologists in achieving better classification results than their independent visual assessment.
引用
- Xie Z, Zhao H, Song L, et al. A radiograph-based deep learning model improves radiologists' performance for classification of histological types of primary bone tumors: A multicenter study. Eur J Radiol. 2024. PMID: 38733705. doi:10.1016/j.ejrad.2024.111496
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。