论文标题
通过改善样品胸部X射线分类的正规化自我训练
Self-Training with Improved Regularization for Sample-Efficient Chest X-Ray Classification
论文作者
论文摘要
自动化医疗保健中的诊断助手需要准确的AI模型，这些模型可以通过有限的标记数据进行训练，可以应对严重的类失衡，并且可以支持对多种疾病状况的同时预测。为此，我们提出了一个深入的学习框架，该框架利用许多关键组件在此类挑战的情况下实现了强大的建模。在胸部X射线分类中使用重要的用例，我们提供了一些关键见解，以有效利用数据增强，通过蒸馏进行自我训练以及对医学成像中的小数据学习的自信降低。我们的结果表明，使用标记的数据少85％，我们可以构建与大规模数据设置训练的分类器的性能相匹配的预测模型。
Automated diagnostic assistants in healthcare necessitate accurate AI models that can be trained with limited labeled data, can cope with severe class imbalances and can support simultaneous prediction of multiple disease conditions. To this end, we present a deep learning framework that utilizes a number of key components to enable robust modeling in such challenging scenarios. Using an important use-case in chest X-ray classification, we provide several key insights on the effective use of data augmentation, self-training via distillation and confidence tempering for small data learning in medical imaging. Our results show that using 85% lesser labeled data, we can build predictive models that match the performance of classifiers trained in a large-scale data setting.
