Feature-shared adaptive-boost deep learning for invasiveness classification of pulmonary subsolid nodules in CT images
Feature-shared adaptive-boost deep learning for invasiveness classification of pulmonary subsolid nodules in CT images
复制标题
DOI：
10.1002/mp.14068
复制
发表时间：
2020-02-26
期刊：
影响因子：
3.8
通讯作者：
Qian, Dahong
中科院分区：
文献类型：
--
作者：
Wang, Jun;Chen, Xiaorong;Qian, Dahong
目的在临床上，侵袭性是鉴别肺实质下结节恶性程度的重要参考指标。这些结节可分为非典型腺瘤样增生（AAH）、原位腺癌（AIS）、微创腺癌（MIA）或浸润性腺癌（IAC）。基于胸部CT扫描自动确定结节的侵袭性可以指导治疗计划。然而，由于训练数据的不足以及它们的类间相似性和类内变化，这是具有挑战性的。为了应对这些挑战，我们提出了一个两阶段的深度学习策略：先验特征学习，然后是自适应增强深度学习。方法自适应增强深度学习提出了一个强分类器，用于胸部CT图像中亚实性结节的侵入性分类，使用多个3D卷积神经网络（CNN）为基础的弱分类器。由于多个深度3D CNN模型的集合具有大量的参数，并且需要大量的计算资源沿着更多的训练和测试时间，因此提出了先验特征学习，以通过在所有弱分类器之间共享CNN层来减少计算。结果对1357个结节进行了10次交叉验证，其中非侵袭性结节（AAH和AIS）765个，侵袭性结节（MIA和IAC）592个。消融实验结果表明，所提出的二元分类器实现了73.4\%+/- 1.4的准确度与AUC为81.3\%+/- 2.2。这些结果上级三位经验丰富的胸部影像学专家的结果，他们的准确率分别为69.1%、69.3%和67.9%。另外还采集了约200个结核。这些结节涵盖每个类别（分别为AAH、AIS、MIA和IAC）的50例病例。对这些数据进行了二进制和多重分类，结果表明，所提出的方法明显优于非集成深度学习方法的性能。结论可以得出结论，所提出的自适应增强深度学习可以显着提高CT图像中肺亚实性结节的侵入性分类性能，而先验特征学习可以显著减小深度模型的总大小。在临床数据上的有希望的结果表明，训练的模型可以用作医院中有效的肺癌筛查工具。此外，所提出的策略可以很容易地扩展到其他类似的分类任务，在三维医学图像。
Purpose In clinical practice, invasiveness is an important reference indicator for differentiating the malignant degree of subsolid pulmonary nodules. These nodules can be classified as atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma (IAC). The automatic determination of a nodule's invasiveness based on chest CT scans can guide treatment planning. However, it is challenging, owing to the insufficiency of training data and their interclass similarity and intraclass variation. To address these challenges, we propose a two-stage deep learning strategy for this task: prior-feature learning followed by adaptive-boost deep learning.Methods The adaptive-boost deep learning is proposed to train a strong classifier for invasiveness classification of subsolid nodules in chest CT images, using multiple 3D convolutional neural network (CNN)-based weak classifiers. Because ensembles of multiple deep 3D CNN models have a huge number of parameters and require large computing resources along with more training and testing time, the prior-feature learning is proposed to reduce the computations by sharing the CNN layers between all weak classifiers. Using this strategy, all weak classifiers can be integrated into a single network.Results Tenfold cross validation of binary classification was conducted on a total of 1357 nodules, including 765 noninvasive (AAH and AIS) and 592 invasive nodules (MIA and IAC). Ablation experimental results indicated that the proposed binary classifier achieved an accuracy of 73.4\%+/- 1.4 with an AUC of 81.3\%+/- 2.2. These results are superior compared to those achieved by three experienced chest imaging specialists who achieved an accuracy of 69.1\%, 69.3\%, and 67.9\%, respectively. About 200 additional nodules were also collected. These nodules covered 50 cases for each category (AAH, AIS, MIA, and IAC, respectively). Both binary and multiple classifications were performed on these data and the results demonstrated that the proposed method definitely achieves better performance than the performance achieved by nonensemble deep learning methods.Conclusions It can be concluded that the proposed adaptive-boost deep learning can significantly improve the performance of invasiveness classification of pulmonary subsolid nodules in CT images, while the prior-feature learning can significantly reduce the total size of deep models. The promising results on clinical data show that the trained models can be used as an effective lung cancer screening tool in hospitals. Moreover, the proposed strategy can be easily extended to other similar classification tasks in 3D medical images.