A medical image classification method based on self-regularized adversarial learning

被引:0
|
作者
Fan, Zong [1 ]
Zhang, Xiaohui [1 ]
Ruan, Su [2 ]
Thorstad, Wade [3 ]
Gay, Hiram [3 ]
Song, Pengfei [4 ]
Wang, Xiaowei [5 ]
Li, Hua [1 ,3 ,6 ]
机构
[1] Univ Illinois, Dept Bioengn, Champaign, IL USA
[2] Univ Rouen, EA 4108, Lab LITIS, Equipe Quantif, Rouen, France
[3] Washington Univ St Louis, Dept Radiat Oncol, St Louis, MO 63130 USA
[4] Univ Illinois, Dept Elect & Comp Engn, Champaign, IL USA
[5] Univ Illinois, Dept Pharmacol & Bioengn, Chicago, IL USA
[6] Canc Ctr Illinois, Urbana, IL USA
关键词
adversarial learning; deep learning; medical image classification;
D O I
10.1002/mp.17320
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
BackgroundDeep learning (DL) techniques have been extensively applied in medical image classification. The unique characteristics of medical imaging data present challenges, including small labeled datasets, severely imbalanced class distribution, and significant variations in imaging quality. Recently, generative adversarial network (GAN)-based classification methods have gained attention for their ability to enhance classification accuracy by incorporating realistic GAN-generated images as data augmentation. However, the performance of these GAN-based methods often relies on high-quality generated images, while large amounts of training data are required to train GAN models to achieve optimal performance.PurposeIn this study, we propose an adversarial learning-based classification framework to achieve better classification performance. Innovatively, GAN models are employed as supplementary regularization terms to support classification, aiming to address the challenges described above.MethodsThe proposed classification framework, GAN-DL, consists of a feature extraction network (F-Net), a classifier, and two adversarial networks, specifically a reconstruction network (R-Net) and a discriminator network (D-Net). The F-Net extracts features from input images, and the classifier uses these features for classification tasks. R-Net and D-Net have been designed following the GAN architecture. R-Net employs the extracted feature to reconstruct the original images, while D-Net is tasked with the discrimination between the reconstructed image and the original images. An iterative adversarial learning strategy is designed to guide model training by incorporating multiple network-specific loss functions. These loss functions, serving as supplementary regularization, are automatically derived during the reconstruction process and require no additional data annotation.ResultsTo verify the model's effectiveness, we performed experiments on two datasets, including a COVID-19 dataset with 13 958 chest x-ray images and an oropharyngeal squamous cell carcinoma (OPSCC) dataset with 3255 positron emission tomography images. Thirteen classic DL-based classification methods were implemented on the same datasets for comparison. Performance metrics included precision, sensitivity, specificity, and F1$F_1$-score. In addition, we conducted ablation studies to assess the effects of various factors on model performance, including the network depth of F-Net, training image size, training dataset size, and loss function design. Our method achieved superior performance than all comparative methods. On the COVID-19 dataset, our method achieved 95.4%+/- 0.6%$95.4\%\pm 0.6\%$, 95.3%+/- 0.9%$95.3\%\pm 0.9\%$, 97.7%+/- 0.4%$97.7\%\pm 0.4\%$, and 95.3%+/- 0.9%$95.3\%\pm 0.9\%$ in terms of precision, sensitivity, specificity, and F1$F_1$-score, respectively. It achieved 96.2%+/- 0.7%$96.2\%\pm 0.7\%$ across all these metrics on the OPSCC dataset. The study to investigate the effects of two adversarial networks highlights the crucial role of D-Net in improving model performance. Ablation studies further provide an in-depth understanding of our methodology.ConclusionOur adversarial-based classification framework leverages GAN-based adversarial networks and an iterative adversarial learning strategy to harness supplementary regularization during training. This design significantly enhances classification accuracy and mitigates overfitting issues in medical image datasets. Moreover, its modular design not only demonstrates flexibility but also indicates its potential applicability to various clinical contexts and medical imaging applications.
引用
收藏
页码:8232 / 8246
页数:15
相关论文
共 50 条
  • [11] Enhancing the adversarial robustness in medical image classification: exploring adversarial machine learning with vision transformers-based models
    Elif Kanca Gulsoy
    Selen Ayas
    Elif Baykal Kablan
    Murat Ekinci
    Neural Computing and Applications, 2025, 37 (12) : 7971 - 7989
  • [12] Online Data Stream Analytics for Dynamic Environments Using Self-Regularized Learning Framework
    Lu, Ching-Hu
    Yu, Chun-Hsien
    IEEE SYSTEMS JOURNAL, 2019, 13 (04): : 3697 - 3707
  • [13] Regularized constraint subspace based method for image set classification
    Tan, Hengliang
    Gao, Ying
    Ma, Zhengming
    PATTERN RECOGNITION, 2018, 76 : 434 - 448
  • [14] Towards the Target: Self-regularized Progressive Learning for Unsupervised Domain Adaptation on Semantic Segmentation
    Chang, Jui
    Pang, Yu-Ting
    Hsu, Chiou-Ting
    PATTERN RECOGNITION, ACPR 2021, PT I, 2022, 13188 : 299 - 313
  • [15] Mitigating adversarial evasion attacks by deep active learning for medical image classification
    Usman Ahmed
    Jerry Chun-Wei Lin
    Gautam Srivastava
    Multimedia Tools and Applications, 2022, 81 : 41899 - 41910
  • [16] Mitigating adversarial evasion attacks by deep active learning for medical image classification
    Ahmed, Usman
    Lin, Jerry Chun-Wei
    Srivastava, Gautam
    MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (29) : 41899 - 41910
  • [17] Image Classification by Selective Regularized Subspace Learning
    Luo, Changzhi
    Ni, Bingbing
    Yan, Shuicheng
    Wang, Meng
    IEEE TRANSACTIONS ON MULTIMEDIA, 2016, 18 (01) : 40 - 50
  • [18] An efficient federated learning method based on enhanced classification-GAN for medical image classification
    Liu, Wei
    Zheng, Yurong
    Xiang, Zhihui
    Wang, Yingmeng
    Tian, Zhao
    She, Wei
    MULTIMEDIA SYSTEMS, 2025, 31 (01)
  • [19] Self-supervised learning for medical image analysis: Discriminative, restorative, or adversarial?
    Haghighi, Fatemeh
    Taher, Mohammad Reza Hosseinzadeh
    Gotway, Michael B.
    Liang, Jianming
    MEDICAL IMAGE ANALYSIS, 2024, 94
  • [20] Weather Image Classification based on Generative Adversarial Network and Transfer Learning
    Zou, Yonglong
    Wu, Jiaxin
    Chen, Weizhe
    Liu, Yang
    INTERNATIONAL CONFERENCE ON INTELLIGENT TRAFFIC SYSTEMS AND SMART CITY (ITSSC 2021), 2022, 12165