Unsupervised Multi-Discriminator Generative Adversarial Network for Lung Nodule Malignancy Classification

Abstract

Computer-aided diagnosis systems with deep learning frameworks have been used to identify benign and malignant pulmonary nodules in lung cancer diagnosis. It's commonly known that a premise of training complex deep neural nets is the large-scale labeled datasets. However, the abundance of labeled datasets is usually unavailable in many medical image domains. This factor can lead to the poor generalization performance of deep learning models. In this paper, we propose a novel multi-discriminator generative adversarial network model combined with an encoder for the classification of benign and malignant pulmonary nodules. To the best of our knowledge, we are the first to apply unsupervised learning to identify benign and malignant lung nodules. Firstly, we use a multi-discriminator generative adversarial network to build a generative model trained with unlabeled benign lung nodule images. Then an encoder is combined with the trained generative model to establish a mapping of benign pulmonary nodule images to the latent space. The benign and malignant lung nodules are scored by calculating the GAN discriminator feature loss and image reconstruction loss. The model yields high anomaly scores on malignant images and low anomaly scores on benign images. Experimental results show that our method with only a small number of unlabeled datasets could achieve more competitive results compared with other supervised deep learning approaches. INDEX TERMS Computer-aided diagnosis (CAD), lung nodule, malignancy classification, unsupervised learning, generative adversarial networks.

Towards Machine Learning-Aided Lung Cancer Clinical Routines: Approaches and Open Challenges

“…Regarding training techniques, the possibility of making use of ImageNet [ 99 ] pre-trained architectures, as in [ 111 , 113 , 132 , 133 ], was shown to provide improvements in the predictive ability. In works that explored multi-task learning strategies, taking advantage of related tasks to enhance the extraction of relevant information, features captured by generative models while discriminating real and fake lung nodules, have also shown valuable roles in training options [ 134 , 135 ], as well as the use of knowledge obtained by learning to reconstruct nodule images [ 120 , 124 , 136 ].…”

A Review of Generative Adversarial Networks in Cancer Imaging: New Applications, New Solutions

“…In ssDAAE, not only the adversarial autoencoder's chosen prior distribution [230], but also the class label distribution is discriminated by a discriminator, the latter distinguishing between predicted continuous labels and real binary (malignant/benign) labels. Kuang et al [351] applied unsupervised learning to distinguish between benign and malignant lung nodules. In their multi-discriminator GAN (MDGAN) various discriminators scrutinise the realness of generated lung nodule images.…”

RF‐GANs: A Method to Synthesize Retinal Fundus Images Based on Generative Adversarial Network

“…Applying GAN to synthesize images to address the shortage of large and diverse datasets has been widely used in medical image processing. Kuang et al [ 23 ] employed an encoder to map the latent space of benign lung nodules and malignant lung nodules to guide generator to synthesize corresponding lung CT images. Yang et al [ 24 ] proposed an extra structure-consistency loss based on the modality of independent neighborhood descriptor to improve CycleGAN for unsupervised MR-to-CT synthesis.…”