Lung cancer is one of the highest causes of cancer-related death in both men and women. Therefore, various diagnostic methods for lung nodules classification have been proposed to implement the early detection. Due to the limited amount and diversity of samples, these methods encounter some bottlenecks. In this paper, we intend to develop a method to enlarge the dataset and enhance the performance of pulmonary nodules classification. We propose a data augmentation method based on generative adversarial network (GAN), called Forward and Backward GAN (F&BGAN), which can generate high-quality synthetic medical images. F&BGAN has two stages, Forward GAN (FGAN) generates diverse images, and Backward GAN (BGAN) is used to improve the quality of images. Besides, a hierarchical learning framework, multi-scale VGG16 (M-VGG16) network, is proposed to extract discriminative features from alternating stacked layers. The methodology was evaluated on the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset, with the best accuracy of 95.24%, sensitivity of 98.67%, specificity of 92.47% and area under ROC curve (AUROC) of 0.980. Experimental results demonstrate the feasibility of F&BGAN in generating medical images and the effectiveness of M-VGG16 in classifying malignant and benign nodules.

Previous saliency detection methods usually focused on extracting powerful discriminative features to describe images with a complex background. Recently, the generative adversarial network (GAN) has shown a great ability in feature learning for synthesizing high quality natural images. Since the GAN shows a superior feature learning ability, we present a new multi-scale adversarial feature learning (MAFL) model for image saliency detection. In particular, we build this model, which is composed of two convolutional neural network (CNN) modules: the multi-scale G-network takes natural images as inputs and generates the corresponding synthetic saliency map, and we design a novel layer in the D-network, namely a correlation layer, which is used to determine whether one image is a synthetic saliency map or ground-truth saliency map. Quantitative and qualitative comparisons on several public datasets show the superiority of our approach.

Lung cancer mortality is currently the highest among all kinds of fatal cancers. With the help of computer-aided detection systems, a timely detection of malignant pulmonary nodule at early stage could improve the patient survival rate efficiently. However, the sizes of the pulmonary nodules are usually various, and it is more difficult to detect small diameter nodules. The traditional convolution neural network uses pooling layers to reduce the resolution progressively, but it hampers the network’s ability to capture the tiny but vital features of the pulmonary nodules. To tackle this problem, we propose a novel 3D spatial pyramid dilated convolution network to classify the malignancy of the pulmonary nodules. Instead of using the pooling layers, we use 3D dilated convolution to learn the detailed characteristic information of the pulmonary nodules. Furthermore, we show that the fusion of multiple receptive fields from different dilated convolutions could further improve the classification performance of the model. Extensive experimental results demonstrate that our model achieves a better result with an accuracy of $88.6\%$ , which outperforms other state-of-the-art methods.