Department of Computer Science, University of California Los Angeles, Los Angeles, California.
Department of Radiology, University of Cambridge School of Clinical Medicine, Cambridge, United Kingdom; NIHR Cambridge Biomedical Research Center, Cambridge, United Kingdom.
J Am Coll Radiol. 2020 Jan;17(1 Pt A):56-63. doi: 10.1016/j.jacr.2019.05.012. Epub 2019 May 30.
The aim of this study was to determine whether machine learning could reduce the number of mammograms the radiologist must read by using a machine-learning classifier to correctly identify normal mammograms and to select the uncertain and abnormal examinations for radiological interpretation.
Mammograms in a research data set from over 7,000 women who were recalled for assessment at six UK National Health Service Breast Screening Program centers were used. A convolutional neural network in conjunction with multitask learning was used to extract imaging features from mammograms that mimic the radiological assessment provided by a radiologist, the patient's nonimaging features, and pathology outcomes. A deep neural network was then used to concatenate and fuse multiple mammogram views to predict both a diagnosis and a recommendation of whether or not additional radiological assessment was needed.
Ten-fold cross-validation was used on 2,000 randomly selected patients from the data set; the remainder of the data set was used for convolutional neural network training. While maintaining an acceptable negative predictive value of 0.99, the proposed model was able to identify 34% (95% confidence interval, 25%-43%) and 91% (95% confidence interval: 88%-94%) of the negative mammograms for test sets with a cancer prevalence of 15% and 1%, respectively.
Machine learning was leveraged to successfully reduce the number of normal mammograms that radiologists need to read without degrading diagnostic accuracy.
本研究旨在通过使用机器学习分类器正确识别正常乳房 X 光照片，并选择不确定和异常的检查进行放射学解释，从而减少放射科医生需要阅读的乳房 X 光照片数量。
使用来自 7000 多名女性的研究数据集的乳房 X 光片，这些女性因在六个英国国民保健服务乳房筛查计划中心进行评估而被召回。卷积神经网络与多任务学习相结合，从乳房 X 光片中提取成像特征，这些特征模仿放射科医生提供的放射学评估、患者的非成像特征和病理结果。然后，使用深度神经网络将多个乳房 X 光视图串联和融合，以预测诊断和是否需要额外的放射学评估的建议。
在数据集的 2000 名随机选择的患者上进行了 10 倍交叉验证；数据集的其余部分用于卷积神经网络训练。在保持可接受的阴性预测值 0.99 的情况下，所提出的模型能够识别出癌症患病率分别为 15%和 1%的测试集的 34%（95%置信区间：25%-43%）和 91%（95%置信区间：88%-94%）的阴性乳房 X 光照片。
利用机器学习成功减少了放射科医生需要阅读的正常乳房 X 光照片数量，而不会降低诊断准确性。
