arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1806.05083cs.CV
收藏

异构图像的多实例学习:训练一个用于历史学的CNN

Multiple Instance Learning for Heterogeneous Images: Training a CNN for Histopathology

University of North Carolina(北卡罗来纳大学)

Heather D. Couture, J. S. Marron, Charles M. Perou, Melissa A. Troester, Marc Niethammer

摘要:

使用卷积神经网络的多实例(MI)学习能够在存在弱图像级标签的情况下进行端到端训练。我们提出了一种新的方法,通过使用分位数函数将来自图像的较小区域的预测聚集到图像级分类中。分位数函数提供了对每个图像内的异质性的更完整的描述,从而改进了图像级分类。我们还通过随机选择在每个训练阶段应用MI聚合的裁剪区域来适应MI框架的图像增强。这为研究多元智能学习的重要性提供了一种机制。我们验证了我们的方法在五个不同的分类任务的乳腺肿瘤组织学,并提供了一个可视化的方法来解释当地的图像分类,可能会导致未来的见解肿瘤异质性。

英文摘要:

Multiple instance (MI) learning with a convolutional neural network enables end-to-end training in the presence of weak image-level labels. We propose a new method for aggregating predictions from smaller regions of the image into an image-level classification by using the quantile function. The quantile function provides a more complete description of the heterogeneity within each image, improving image-level classification. We also adapt image augmentation to the MI framework by randomly selecting cropped regions on which to apply MI aggregation during each epoch of training. This provides a mechanism to study the importance of MI learning. We validate our method on five different classification tasks for breast tumor histology and provide a visualization method for interpreting local image classifications that could lead to future insights into tumor heterogeneity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑