应用深度学习联合健康记录与乳腺X线摄影预测乳腺癌
本回顾性研究纳入2013至2017年间至少一次乳腺X线摄影且有至少1年健康记录的13234名女性,共52936幅图像;算法在9611幅图像及健康记录上训练,用于预测活检恶性及区分正常与异常筛查。测试集2548名女性中,算法识别出71例假阴性中的34例(48%),恶性预测AUC为0.91(95%CI:0.89,0.93),特异度77.3%(95%CI:69.2%,85.4%)时敏感度为87%;仅用临床数据训练时AUC为0.78,优于Gail模型的0.54(P<.004)。
要点
- 算法在测试集中识别出71例乳腺X线假阴性中的34例(48%)。
- 恶性预测AUC为0.91(95%CI:0.89,0.93),特异度77.3%时敏感度87%。
- 仅用临床数据训练时AUC 0.78,优于Gail模型0.54(P<.004)。
核心结论
- 结合机器学习和深度学习的方法评估乳腺癌的水平与放射科医师相当,并可能大幅减少乳腺癌漏诊。
研究设计与样本
- 回顾性研究,收集13234名女性于2013至2017年间至少一次乳腺X线摄影的52936幅图像,且均有检查前至少1年的健康记录。
- 算法在9611幅乳腺X线图像及健康记录上训练,用于预测活检恶性及区分正常与异常筛查检查。
- 结果在1055名女性中验证,并在2548名女性(平均年龄55岁±10)中测试。
诊断标准与关键数值
- 测试集中,算法识别出71例乳腺X线假阴性中的34例(48%)。
- 恶性预测目标下,算法AUC为0.91(95%CI:0.89,0.93),敏感度87%时特异度为77.3%(95%CI:69.2%,85.4%)。
- 仅用临床数据训练时,模型AUC为0.78,优于Gail模型的0.54(P<.004)。
临床应用与阅片要点
- 作者认为,该算法可用于评估乳腺癌,水平与放射科医师相当,并可能大幅减少乳腺癌漏诊。
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
Background Computational models on the basis of deep neural networks are increasingly used to analyze health care data. However, the efficacy of traditional computational models in radiology is a matter of debate. Purpose To evaluate the accuracy and efficiency of a combined machine and deep learning approach for early breast cancer detection applied to a linked set of digital mammography images and electronic health records. Materials and Methods In this retrospective study, 52 936 images were collected in 13 234 women who underwent at least one mammogram between 2013 and 2017, and who had health records for at least 1 year before undergoing mammography. The algorithm was trained on 9611 mammograms and health records of women to make two breast cancer predictions: to predict biopsy malignancy and to differentiate normal from abnormal screening examinations. The study estimated the association of features with outcomes by using t test and Fisher exact test. The model comparisons were performed with a 95% confidence interval (CI) or by using the DeLong test. Results The resulting algorithm was validated in 1055 women and tested in 2548 women (mean age, 55 years ± 10 [standard deviation]). In the test set, the algorithm identified 34 of 71 (48%) false-negative findings on mammograms. For the malignancy prediction objective, the algorithm obtained an area under the receiver operating characteristic curve (AUC) of 0.91 (95% CI: 0.89, 0.93), with specificity of 77.3% (95% CI: 69.2%, 85.4%) at a sensitivity of 87%. When trained on clinical data alone, the model performed significantly better than the Gail model (AUC, 0.78 vs 0.54, respectively; P < .004). Conclusion The algorithm, which combined machine-learning and deep-learning approaches, can be applied to assess breast cancer at a level comparable to radiologists and has the potential to substantially reduce missed diagnoses of breast cancer. © RSNA, 2019 Online supplemental material is available for this article.
引用
- Akselrod-Ballin A, Chorev M, Shoshan Y, et al. Predicting Breast Cancer by Applying Deep Learning to Linked Health Records and Mammograms. Radiology. 2019. PMID: 31210611. doi:10.1148/radiol.2019182622
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。