• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Medical Image Computing and Computer-Assisted Intervention >Learning from Longitudinal Mammography Studies
【24h】

Learning from Longitudinal Mammography Studies

机译：从纵向乳房X线摄影研究中学习

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

When reading imaging studies, radiologists often compare the acquired images to one or more prior studies of the patient. Machine learning algorithms that assist in identifying abnormalities in medical images usually do not analyze prior images. This work describes a deep-learning classification framework for mammography studies, which incorporates prior image information using four approaches: (1) late fusion of prediction scores; (2) early fusion of input layers; (3) feature fusion combining a convolutional neural network (CNN) and gradient boosting trees; and (4) feature fusion using CNN and long-short term memory (LSTM) architecture. We demonstrate the advantages and limitations of each approach and compare their performance in identifying biopsy-proven malignancies in mammography screening studies. On an evaluation cohort of 439 patients, adding prior studies to the analysis improved the diagnostic performance of the classification framework. The CNN-LSTM architecture achieved the highest area under the ROC curve of 0.88, with sensitivity and specificity of 0.87 and 0.78, respectively. The methods that were trained using information from prior studies achieved better results than the baseline classifier, with up to 45% reduction in false-positive rate at the same sensitivity. The major advantage of the CNN-LSTM approach is in its flexibility and scalability; it allows to use the same network to classify sequences of multiple priors with variable length. The study demonstrates that longitudinal analysis of images can potentially improve the ability of machine learning algorithms to accurately and reliably interpret imaging studies, thus providing value to the radiology community.
机译：当阅读成像研究时，放射科医师通常将所获取的图像与患者的一个或多个事先研究进行比较。有助于识别医学图像的异常的机器学习算法通常不会分析先前的图像。这项工作描述了乳房X线摄影研究的深度学习分类框架，其使用四种方法结合了先前的图像信息：（1）预测分数的晚期融合; （2）输入层的早期融合; （3）特征融合结合卷积神经网络（CNN）和梯度升压树木; （4）使用CNN和长期内存（LSTM）架构的特征融合。我们展示了各种方法的优缺点，并比较了它们在识别乳房X线摄影筛查研究中的活检证实恶性肿瘤的性能。在439名患者的评估队列中，将先前的研究添加到分析提高了分类框架的诊断性能。 CNN-LSTM架构在ROC曲线下实现了0.88的最高面积，灵敏度和特异性分别为0.87和0.78。使用来自先前研究的信息训练的方法实现了比基线分类器更好的结果，误阳性率降低至相同的灵敏度高达45％。 CNN-LSTM方法的主要优点是其灵活性和可扩展性;它允许使用相同的网络来对具有可变长度的多个前沿的序列进行分类。该研究表明，图像的纵向分析可以潜在地提高机器学习算法的能力，以准确且可靠地解释成像研究，从而为放射学区提供价值。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号