Feature-shared adaptive-boost deep learning for invasiveness classification of pulmonary sub-solid nodules in CT images.

Researchers

Journal

Modalities

Models

Abstract

In clinical practice, invasiveness is an important reference indicator for differentiating the malignant degree of sub-solid 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 inter-class similarity and intra-class variation. To address these challenges, we propose a two-stage deep learning strategy for this task: prior-feature learning followed by adaptive-boost learning.
The adaptive-boost learning is proposed to train a strong classifier for invasiveness classification of sub-solid 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.
Ten-fold cross validation of binary classification was conducted on a total of 1357 nodules, including 765 non-invasive (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. 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 non-ensemble deep learning methods.
It can be concluded that the proposed adaptive-boost learning can significantly improve the performance of invasiveness classification of pulmonary sub-solid nodules in CT images, while the prior-feature learning can significantly reduce the total size of deep models. The promising results on clinical data shows 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.
This article is protected by copyright. All rights reserved.