Lung cancer has become one of the most severe cancers in the world. The detection and classification of pulmonary nodules is of great importance for the lung cancer diagnosis in early stage. However, traditional pulmonary nodule identification methods require doctors to locate the lesion in hundreds of CT images, which is very time-consuming and has the problem of missed diagnosis. In addition, CT images of pulmonary nodule have low resolution and little interclass variability, which affects the performance of the model. Existing deep learning based methods can’t solve it well. Therefore, we propose a space to depth convolution neural network (SPD-CNN) based classification algorithm to implement pulmonary nodule classification automatically and accurately. In particular, in the proposed algorithm, we introduce a non-strided module called space to depth convolution (SPD-Conv) to extract and refine feature maps. Moreover, we also utilize convolution based attention module (CBAM) to enable the model to concentrate on the critical features related to pulmonary nodules classification. Simulation results show that the proposed SPD-CNN algorithm can achieve higher classification accuracy than the compared baselines.
Deep learning (DL) techniques have been widely applied in medical image analysis. In particular, the DL-based medical image classification has been adequately investigated on large-size annotated datasets. However, it is cost-expensive to collect a large amount of high-quality and large-scale annotated medical images. Our proposal is addressing this problem by a few-shot medical image classification method that uses contrastive learning and linear discriminant analysis (FSCCLLDA). A well-performing encoder is pre-trained using contrastive learning to extract more extensive semantic information that is unrelated to the label. Moreover, the features are transformed into low-dimensional space using linear discriminant analysis (LDA). The transformed features are similar within each class and discriminatory among classes. Experiments on ISIC2018 and BreakHis datasets show that the proposed FSC-CLLDA algorithm outperforms the compared baselines in accuracy.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.