Deep CNN models for pulmonary nodule classification: Model modification, model integration, and transfer learning
Deep CNN models for pulmonary nodule classification: Model modification, model integration, and transfer learning
复制标题
用于肺结节分类的深度 CNN 模型：模型修改、模型集成和迁移学习
DOI：
10.3233/xst-180490
复制
发表时间：
2019-01-01
影响因子：
3
通讯作者：
Sun, Jianjun
中科院分区：
文献类型：
--
作者：
Zhao, Xinzhuo;Qi, Shouliang;Sun, Jianjun
背景技术背景：深度学习在分析自然图像方面取得了惊人的成就，但由于图像不足，它在医学应用中面临挑战。目的：针对利用CT图像进行肺结节良恶性分类的问题，探索利用最先进的深度卷积神经网络（CNN）的不同策略。方法：使用肺图像数据库联盟图像集合（LIDC-IDRI）进行实验，该图像集合是包含1018个病例的公共数据库。实现了三种策略，包括1）修改一些最先进的CNN架构，2）集成不同的CNN，3）采用迁移学习。结果：研究表明，对于模型修改方案，简洁的CifarNet比其他具有更复杂架构的修改后的CNN表现更好，达到AUC = 0.90的ROC曲线下面积。集成的CNN模型不会显著提高分类性能，但模型复杂度降低。迁移学习的性能优于其他两种方法，其中ResNet的AUC为0.94，灵敏度为91%，总体准确率为88%。结论：模型修改、模型集成和迁移学习可以在基于CT图像的肺结节分类中有效识别和生成最佳深度CNN模型。在将深度学习应用于医学成像应用时，迁移学习是首选。
BACKGROUND: Deep learning has made spectacular achievements in analysing natural images, but it faces challenges for medical applications partly due to inadequate images.OBJECTIVE: Aiming to classify malignant and benign pulmonary nodules using CT images, we explore different strategies to utilize the state-of-the-art deep convolutional neural networks (CNN).METHODS: Experiments are conducted using the Lung Image Database Consortium image collection (LIDC-IDRI), which is a public database containing 1018 cases. Three strategies are implemented including to 1) modify some state-of-the-art CNN architectures, 2) integrate different CNNs and 3) adopt transfer learning. Totally, 11 deep CNN models are compared using the same dataset.RESULTS: Study demonstrates that, for the model modification scheme, a concise CifarNet performs better than the other modified CNNs with more complex architectures, achieving an area under ROC curve of AUC = 0.90. Integrated CNN models do not significantly improve the classification performance, but the model complexity is reduced. Transfer learning outperforms the other two schemes and ResNet with fine-tuning leads to the best performance with an AUC = 0.94, as well as the sensitivity of 91% and an overall accuracy of 88%.CONCLUSIONS: Model modification, model integration, and transfer learning can play important roles to identify and generate optimal deep CNN models in classifying pulmonary nodules based on CT images efficiently. Transfer learning is preferred when applying deep learning to medical imaging applications.