Generative adversarial feature learning for glomerulopathy histological classification. (April 2023)

• Record Type: Journal Article
• Authors: Hai, Jinjin; Yan, Bin; Qiao, Kai; Liang, Ningning; Zhang, Lijie; Cheng, Genyang; Chen, Jian
• Is Part Of: Biomedical signal processing and control. Volume 82(2023)
• Publication Date: 2023-04
• Subjects: Renal ultrasound -- Pathological types -- Generative Adversarial Networks -- Feature generation -- Adversarial learning; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104562
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Noninvasive and convenient ultrasound images are used for discriminating the histological type of glomerulopathy instead of pathological images obtained by renal biopsy. A generative adversarial learning strategy by generating image features rather than images is employed to improve classification performance. Conditional Generative Adversarial Networks with an auxiliary classifier is deployed to generate class-related image features. Adversarial learning makes the feature extraction network learn more informative features. Experiment results demonstrate that our architecture achieves a better classification performance, and the extracted features are more informative and discriminative with image categories. Abstract: Early diagnosis of glomerulopathy is significant for improving disease control and prognosis. Glomerulopathy is diagnosed by pathological images obtained from a renal biopsy, which has many complications and contraindications. In this work, we propose to utilize noninvasive renal ultrasound images to predict the pathological type of glomerulopathy. Due to the difficulty of pathological type recognition on renal ultrasound images and small amounts of annotated data, effective feature learning is more important. Therefore, we employ an adversarial learning approach to generate feature embeddings rather than images. AC-GAN, using conditional image generation and auxiliary classifier, is deployed to synthesize class-related image features. A basic residual network is applied to extract real renal features. After adversarial feature learning, an additional classifier is used for further optimizing and updating the feature extraction network. Through adversarial learning, the feature embeddings extracted by feature extraction network become more informative and discriminative. The t -SNE visualization of extracted features demonstrates that learned features by adversarial feature learning are more discriminative with image categories than others, and this adversarial feature learning architecture achieves 85% accuracy and 0.8542 AUC value, which is better than single classification network and image generation augmentation strategy.