A GAN-Based Data Augmentation Method for Imbalanced Multi-Class Skin Lesion Classification

被引:18
作者
Su, Qichen [1 ]
Hamed, Haza Nuzly Abdull [1 ]
Isa, Mohd Adham [1 ]
Hao, Xue [1 ]
Dai, Xin [1 ]
机构
[1] Univ Teknol Malaysia UTM, Fac Comp, Johor Baharu 81310, Malaysia
关键词
Skin; Training; Lesions; Image color analysis; Data augmentation; Generative adversarial networks; Data models; data imbalance; generative adversarial networks; skin lesion classification; DIAGNOSIS;
D O I
10.1109/ACCESS.2024.3360215
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Skin cancer is one of the most common types of cancer globally. Despite the remarkable advancements of deep learning methods in computer vision, automatic diagnosis of skin diseases still faces challenges such as limited data and class imbalance. Generative Adversarial Networks (GANs), which can synthesize realistic data, appear as an alternative to mitigate these issues. However, for imbalanced data, unconditional GANs either generate uneven data distribution or neglect universal knowledge of the whole dataset, while state-of-the-art (SOTA) conditional GANs suffer from performance degradation due to the mode collapse of minority classes. This paper proposes a two-stage GAN-based method to synthesize fine-grained and diverse 256x256 pixels skin lesion images for the imbalanced dataset, named Self-Transfer GAN (STGAN). STGAN first learns universal knowledge from all classes then transfers this shared knowledge to each class and fuses it with class-specific knowledge to synthesize high-quality images. Furthermore, based on STGAN, a framework to enhance the classification performance is established. Both data generation and classification tasks are evaluated on HAM10000 dataset. In terms of Frechet Inception Distance (FID), Inception Score, Precision, and Recall, STGAN improved by 16%, 16%, 4%, 33% compared with SOTA conditional StyleGAN2. For classification, the STGAN-based framework achieves remarkable results, with an Accuracy of 98.23%, Sensitivity of 88.85%, Precision of 90.23%, F1-score of 89.48%, and Specificity of 98.34%.
引用
收藏
页码:16498 / 16513
页数:16
相关论文
共 50 条
[21]   GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification [J].
Frid-Adar, Maayan ;
Diamant, Idit ;
Klang, Eyal ;
Amitai, Michal ;
Goldberger, Jacob ;
Greenspan, Hayit .
NEUROCOMPUTING, 2018, 321 :321-331
[22]   Enhancing human action recognition with GAN-based data augmentation [J].
Pulakurthi, Prasanna Reddy ;
de Melo, Celso M. ;
Rao, Raghuveer ;
Rabbani, Majid .
SYNTHETIC DATA FOR ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING: TOOLS, TECHNIQUES, AND APPLICATIONS II, 2024, 13035
[23]   A GAN-Based Data Augmentation Method for Multimodal Emotion Recognition [J].
Luo, Yun ;
Zhu, Li-Zhen ;
Lu, Bao-Liang .
ADVANCES IN NEURAL NETWORKS - ISNN 2019, PT I, 2019, 11554 :141-150
[24]   Enhancement of Image Classification Using Transfer Learning and GAN-Based Synthetic Data Augmentation [J].
Chatterjee, Subhajit ;
Hazra, Debapriya ;
Byun, Yung-Cheol ;
Kim, Yong-Woon .
MATHEMATICS, 2022, 10 (09)
[25]   GAN-based one dimensional medical data augmentation [J].
Ye Zhang ;
Zhixiang Wang ;
Zhen Zhang ;
Junzhuo Liu ;
Ying Feng ;
Leonard Wee ;
Andre Dekker ;
Qiaosong Chen ;
Alberto Traverso .
Soft Computing, 2023, 27 :10481-10491
[26]   GAN-based one dimensional medical data augmentation [J].
Zhang, Ye ;
Wang, Zhixiang ;
Zhang, Zhen ;
Liu, Junzhuo ;
Feng, Ying ;
Wee, Leonard ;
Dekker, Andre ;
Chen, Qiaosong ;
Traverso, Alberto .
SOFT COMPUTING, 2023, 27 (15) :10481-10491
[27]   A Survey on GAN-Based Data Augmentation for Hand Pose Estimation Problem [J].
Farahanipad, Farnaz ;
Rezaei, Mohammad ;
Nasr, Mohammad Sadegh ;
Kamangar, Farhad ;
Athitsos, Vassilis .
TECHNOLOGIES, 2022, 10 (02)
[28]   GAN-based Data Augmentation of Railway Track Irregularities for Fault Diagnosis [J].
Bobadilla, Hector A. Fernandez ;
Martin, Ullrich .
2024 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN 2024, 2024,
[29]   Multi-class skin lesion classification using prism- and segmentation-based fractal signatures [J].
Ariel Camacho-Gutierrez, Jose ;
Solorza-Calderon, Selene ;
Alvarez-Borrego, Josue .
EXPERT SYSTEMS WITH APPLICATIONS, 2022, 197
[30]   Multi-class imbalanced image classification using conditioned GANs [J].
Kumar, M. R. Pavan ;
Jayagopal, Prabhu .
INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL, 2021, 10 (03) :143-153