WGAN-Based Synthetic Minority Over-Sampling Technique: Improving Semantic Fine-Grained Classification for Lung Nodules in CT Images
Open Access
- 30 January 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 18450-18463
Abstract
Data imbalance issue generally exists in most medical image analysis problems, and may be getting important with the popularization of data-hungry deep learning paradigms. We explore the cutting-edge wasserstein generative adversarial networks (WGAN) to address the data imbalance problem with over-sampling on the minority classes. The WGAN can estimate the underlying distribution of a minority class to synthesize more plausible and helpful samples for the classification model. In this paper, the WGAN-based over-sampling technique is applied to augment the data to balance for the fine-grained classification of 7 semantic attributes of lung nodules in CT images. The fine-grained classification is carried out with a normal convolutional neural network (CNN). To further illustrate the efficacy of the WGAN-based over-sampling technique, the conventional data augmentation method commonly used in many deep learning works, the generative adversarial networks (GAN) and the deep convolutional generative adversarial networks (DCGAN) are implemented for comparison. The whole schemes of the minority over-sampling and fine-grained classification are tested with the public Lung Imaging Database Consortium (LIDC) dataset. The experimental results suggest that the WGAN-based over-sampling technique can synthesize helpful samples for the minority classes to assist the training of the CNN model and to boost the fine-grained classification performance better than the conventional data augmentation method and the two schemes of the GAN and DCGAN techniques do. It may thus suggest that the WGAN technique offers an alternative methodological option for the further deep learning on imbalanced classification studies.Keywords
Funding Information
- National Key Research and Development Program of China (2017YFA0700900)
- National Natural Science Foundation of China (61772482, 61501305, 61672438)
- Youth Innovation Promotion Association CAS (2017497)
- Natural Science Foundation of Anhui Province (BJ2150110002)
- Sichuan Provincial Open Foundation of Civil-Military Integration Research Institute (2017SCII0219, 2017SCII0220)
- Key Project of Sichuan Provincial Science and Technology Innovation (19MZGC0123)
This publication has 28 references indexed in Scilit:
- Improving Computer-Aided Detection UsingConvolutional Neural Networks and Random View AggregationIEEE Transactions on Medical Imaging, 2015
- To Combat Multi-Class Imbalanced Problems by Means of Over-Sampling TechniquesIEEE Transactions on Knowledge and Data Engineering, 2015
- Multi-scale Convolutional Neural Networks for Lung Nodule Classification2015
- A large-scale car dataset for fine-grained categorization and verification2015
- Fine-grained histopathological image analysis via robust segmentation and large-scale retrieval2015
- A texture feature analysis for diagnosis of pulmonary nodules using LIDC-IDRI database2013
- Evolutionary rule-based systems for imbalanced data setsSoft Computing, 2008
- The Lung Image Database Consortium (LIDC)Academic Radiology, 2007
- The Lung Image Database Consortium (LIDC)Academic Radiology, 2007
- The Lung Image Database Consortium (LIDC) Data Collection Process for Nodule Detection and AnnotationAcademic Radiology, 2007