{"title":"使用生成对抗性网络进行高质量的半监督异常检测。","authors":"Yuki Sato, Junya Sato, Noriyuki Tomiyama, Shoji Kido","doi":"10.1007/s11548-023-03031-9","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>The visualization of an anomaly area is easier in anomaly detection methods that use generative models rather than classification models. However, achieving both anomaly detection accuracy and a clear visualization of anomalous areas is challenging. This study aimed to establish a method that combines both detection accuracy and clear visualization of anomalous areas using a generative adversarial network (GAN).</p><p><strong>Methods: </strong>In this study, StyleGAN2 with adaptive discriminator augmentation (StyleGAN2-ADA), which can generate high-resolution and high-quality images with limited number of datasets, was used as the image generation model, and pixel-to-style-to-pixel (pSp) encoder was used to convert images into intermediate latent variables. We combined existing methods for training and proposed a method for calculating anomaly scores using intermediate latent variables. The proposed method, which combines these two methods, is called high-quality anomaly GAN (HQ-AnoGAN).</p><p><strong>Results: </strong>The experimental results obtained using three datasets demonstrated that HQ-AnoGAN has equal or better detection accuracy than the existing methods. The results of the visualization of abnormal areas using the generated images showed that HQ-AnoGAN could generate more natural images than the existing methods and was qualitatively more accurate in the visualization of abnormal areas.</p><p><strong>Conclusion: </strong>In this study, HQ-AnoGAN comprising StyleGAN2-ADA and pSp encoder was proposed with an optimal anomaly score calculation method. The experimental results show that HQ-AnoGAN can achieve both high abnormality detection accuracy and clear visualization of abnormal areas; thus, HQ-AnoGAN demonstrates significant potential for application in medical imaging diagnosis cases where an explanation of diagnosis is required.</p>","PeriodicalId":51251,"journal":{"name":"International Journal of Computer Assisted Radiology and Surgery","volume":" ","pages":"2121-2131"},"PeriodicalIF":2.3000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"High-quality semi-supervised anomaly detection with generative adversarial networks.\",\"authors\":\"Yuki Sato, Junya Sato, Noriyuki Tomiyama, Shoji Kido\",\"doi\":\"10.1007/s11548-023-03031-9\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>The visualization of an anomaly area is easier in anomaly detection methods that use generative models rather than classification models. However, achieving both anomaly detection accuracy and a clear visualization of anomalous areas is challenging. This study aimed to establish a method that combines both detection accuracy and clear visualization of anomalous areas using a generative adversarial network (GAN).</p><p><strong>Methods: </strong>In this study, StyleGAN2 with adaptive discriminator augmentation (StyleGAN2-ADA), which can generate high-resolution and high-quality images with limited number of datasets, was used as the image generation model, and pixel-to-style-to-pixel (pSp) encoder was used to convert images into intermediate latent variables. We combined existing methods for training and proposed a method for calculating anomaly scores using intermediate latent variables. The proposed method, which combines these two methods, is called high-quality anomaly GAN (HQ-AnoGAN).</p><p><strong>Results: </strong>The experimental results obtained using three datasets demonstrated that HQ-AnoGAN has equal or better detection accuracy than the existing methods. The results of the visualization of abnormal areas using the generated images showed that HQ-AnoGAN could generate more natural images than the existing methods and was qualitatively more accurate in the visualization of abnormal areas.</p><p><strong>Conclusion: </strong>In this study, HQ-AnoGAN comprising StyleGAN2-ADA and pSp encoder was proposed with an optimal anomaly score calculation method. The experimental results show that HQ-AnoGAN can achieve both high abnormality detection accuracy and clear visualization of abnormal areas; thus, HQ-AnoGAN demonstrates significant potential for application in medical imaging diagnosis cases where an explanation of diagnosis is required.</p>\",\"PeriodicalId\":51251,\"journal\":{\"name\":\"International Journal of Computer Assisted Radiology and Surgery\",\"volume\":\" \",\"pages\":\"2121-2131\"},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2024-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Computer Assisted Radiology and Surgery\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s11548-023-03031-9\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2023/11/9 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, BIOMEDICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Computer Assisted Radiology and Surgery","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s11548-023-03031-9","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/11/9 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
High-quality semi-supervised anomaly detection with generative adversarial networks.
Purpose: The visualization of an anomaly area is easier in anomaly detection methods that use generative models rather than classification models. However, achieving both anomaly detection accuracy and a clear visualization of anomalous areas is challenging. This study aimed to establish a method that combines both detection accuracy and clear visualization of anomalous areas using a generative adversarial network (GAN).
Methods: In this study, StyleGAN2 with adaptive discriminator augmentation (StyleGAN2-ADA), which can generate high-resolution and high-quality images with limited number of datasets, was used as the image generation model, and pixel-to-style-to-pixel (pSp) encoder was used to convert images into intermediate latent variables. We combined existing methods for training and proposed a method for calculating anomaly scores using intermediate latent variables. The proposed method, which combines these two methods, is called high-quality anomaly GAN (HQ-AnoGAN).
Results: The experimental results obtained using three datasets demonstrated that HQ-AnoGAN has equal or better detection accuracy than the existing methods. The results of the visualization of abnormal areas using the generated images showed that HQ-AnoGAN could generate more natural images than the existing methods and was qualitatively more accurate in the visualization of abnormal areas.
Conclusion: In this study, HQ-AnoGAN comprising StyleGAN2-ADA and pSp encoder was proposed with an optimal anomaly score calculation method. The experimental results show that HQ-AnoGAN can achieve both high abnormality detection accuracy and clear visualization of abnormal areas; thus, HQ-AnoGAN demonstrates significant potential for application in medical imaging diagnosis cases where an explanation of diagnosis is required.
期刊介绍:
The International Journal for Computer Assisted Radiology and Surgery (IJCARS) is a peer-reviewed journal that provides a platform for closing the gap between medical and technical disciplines, and encourages interdisciplinary research and development activities in an international environment.