整合乳腺X线摄影与临床因素的双学习模型助力乳腺癌筛查中BI-RADS 4微钙化的恶性预测
本回顾性研究纳入384例患者共414个病理证实的微钙化灶(221恶性、193良性),随机分为训练集、验证集和测试集(272/71/71个病灶),开发了整合乳腺X线摄影与临床变量的联合深度学习模型。联合模型在测试集预测BI-RADS 4恶性微钙化的AUC、敏感度和特异度分别为0.910、85.3%和91.9%,优于临床模型、DL图像模型和BI-RADS(AUC分别为0.799、0.841和0.804)。联合模型性能不劣于高年资放射科医生,并优于低年资放射科医生;人工智能辅助后低年资放射科医生的AUC和观察者间一致性提高。
要点
- 联合模型预测BI-RADS 4微钙化恶性的AUC为0.910,敏感度85.3%,特异度91.9%。
- 联合模型AUC 0.910优于BI-RADS的0.804、DL图像模型的0.841和临床模型的0.799。
- AI辅助后低年资放射科医生AUC由0.816和0.773升至0.854和0.901,kappa由0.331升至0.843。
核心结论
- 联合深度学习模型可提高筛查乳腺X线摄影中BI-RADS 4微钙化的恶性预测,并帮助低年资放射科医生获得更好表现,有助于临床决策。
研究设计与样本
- 回顾性研究,共384例患者414个病理证实的微钙化灶(221恶性、193良性),随机分为训练集、验证集和测试集(272/71/71个病灶)。
- 开发整合乳腺X线摄影与临床变量的联合DL模型,以AUC评价性能,并与临床模型、单独DL图像模型、BI-RADS方法及2名低年资和2名高年资放射科医生比较。
诊断标准与关键数值
- 联合DL模型在测试集预测BI-RADS 4恶性微钙化的AUC、敏感度、特异度分别为0.910、85.3%、91.9%。
- 临床模型、DL图像模型、BI-RADS的AUC分别为0.799、0.841、0.804。
- 联合模型与高年资放射科医生比较p=0.860、p=0.800,与低年资放射科医生比较p=0.155、p=0.029。
- AI辅助后两名低年资放射科医生AUC分别由0.816升至0.854(p=0.556)、由0.773升至0.901(p=0.046),观察者间kappa由0.331升至0.843。
临床应用与阅片要点
- 联合模型可能辅助低年资放射科医生提高BI-RADS 4微钙化恶性预测表现并改善观察者间一致性。
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
OBJECTIVES: To investigate the value of full-field digital mammography-based deep learning (DL) in predicting malignancy of Breast Imaging Reporting and Data System (BI-RADS) 4 microcalcifications.
METHODS: A total of 384 patients with 414 pathologically confirmed microcalcifications (221 malignant and 193 benign) were randomly allocated into the training, validation, and testing datasets (272/71/71 lesions) in this retrospective study. A combined DL model was developed incorporating mammography and clinical variables. Model performance was evaluated by using areas under the receiver operating characteristic curve (AUC) and compared with the clinical model, stand-alone DL image model, and BI-RADS approach. The predictive performance for malignancy was also compared between the combined model and human readers (2 juniors and 2 seniors).
RESULTS: The combined DL model demonstrated favorable AUC, sensitivity, and specificity of 0.910, 85.3%, and 91.9% in predicting BI-RADS 4 malignant microcalcifications in the testing dataset, which outperformed the clinical model, DL image model, and BI-RADS with AUCs of 0.799, 0.841, and 0.804, respectively. The combined model achieved non-inferior performance as senior radiologists (p = 0.860, p = 0.800) and outperformed junior radiologists (p = 0.155, p = 0.029). The diagnostic performance of two junior radiologists was improved after artificial intelligence assistance with AUCs increased to 0.854 and 0.901 from 0.816 (p = 0.556) and 0.773 (p = 0.046), while the interobserver agreement was improved with a kappa value increased to 0.843 from 0.331.
CONCLUSIONS: The combined deep learning model can improve the malignancy prediction of BI-RADS 4 microcalcifications in screening mammography and assist junior radiologists to achieve better performance, which can facilitate clinical decision-making.
KEY POINTS: • The combined deep learning model demonstrated high diagnostic power, sensitivity, and specificity for predicting malignant BI-RADS 4 mammographic microcalcifications. • The combined model achieved similar performance with senior breast radiologists, while it outperformed junior breast radiologists. • Deep learning could improve the diagnostic performance of junior radiologists and facilitate clinical decision-making.
引用
- Liu H, Chen Y, Zhang Y, et al. A deep learning model integrating mammography and clinical factors facilitates the malignancy prediction of BI-RADS 4 microcalcifications in breast cancer screening. Eur Radiol. 2021. PMID: 33496829. doi:10.1007/s00330-020-07659-y
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。