An attempt to generate panoramic radiographs including jaw cysts using StyleGAN3.

IF 2.9 2区医学 Q1 DENTISTRY, ORAL SURGERY & MEDICINE

Dento maxillo facial radiology Pub Date : 2024-09-02 DOI:10.1093/dmfr/twae044

Motoki Fukuda, Shinya Kotaki, Michihito Nozawa, Kaname Tsuji, Masahiro Watanabe, Hironori Akiyama, Yoshiko Ariji

{"title":"An attempt to generate panoramic radiographs including jaw cysts using StyleGAN3.","authors":"Motoki Fukuda, Shinya Kotaki, Michihito Nozawa, Kaname Tsuji, Masahiro Watanabe, Hironori Akiyama, Yoshiko Ariji","doi":"10.1093/dmfr/twae044","DOIUrl":null,"url":null,"abstract":"Objectives: The purpose of this study was to generate radiographs including dentigerous cysts by applying the latest generative adversarial network (GAN; StyleGAN3) to panoramic radiography.Methods: A total of 459 cystic lesions were selected, and 409 images were randomly assigned as training data and 50 images as test data. StyleGAN3 training was performed for 500 000 images. Fifty generated images were objectively evaluated by comparing them with 50 real images according to four metrics: Fréchet inception distance (FID), kernel inception distance (KID), precision and recall, and inception score (IS). A subjective evaluation of the generated images was performed by three specialists who compared them with the real images in a visual Turing test.Results: The results of the metrics were as follows: FID, 199.28; KID, 0.14; precision, 0.0047; recall, 0.00; and IS, 2.48. The overall results of the visual Turing test were 82.3%. No significant difference was found in the human scoring of root resorption.Conclusions: The images generated by StyleGAN3 were of such high quality that specialists could not distinguish them from the real images.","PeriodicalId":11261,"journal":{"name":"Dento maxillo facial radiology","volume":" ","pages":""},"PeriodicalIF":2.9000,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Dento maxillo facial radiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/dmfr/twae044","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"DENTISTRY, ORAL SURGERY & MEDICINE","Score":null,"Total":0}

引用次数: 0

Abstract

Objectives: The purpose of this study was to generate radiographs including dentigerous cysts by applying the latest generative adversarial network (GAN; StyleGAN3) to panoramic radiography.

Methods: A total of 459 cystic lesions were selected, and 409 images were randomly assigned as training data and 50 images as test data. StyleGAN3 training was performed for 500 000 images. Fifty generated images were objectively evaluated by comparing them with 50 real images according to four metrics: Fréchet inception distance (FID), kernel inception distance (KID), precision and recall, and inception score (IS). A subjective evaluation of the generated images was performed by three specialists who compared them with the real images in a visual Turing test.

Results: The results of the metrics were as follows: FID, 199.28; KID, 0.14; precision, 0.0047; recall, 0.00; and IS, 2.48. The overall results of the visual Turing test were 82.3%. No significant difference was found in the human scoring of root resorption.

Conclusions: The images generated by StyleGAN3 were of such high quality that specialists could not distinguish them from the real images.

查看原文本刊更多论文

尝试使用 StyleGAN3 生成包括颌骨囊肿在内的全景 X 光片。

研究目的本研究的目的是将最新的生成对抗网络（GAN；StyleGAN3）应用于全景放射摄影，生成包括齿槽囊肿在内的放射影像：方法：共选取 459 个囊肿病灶，随机分配 409 张图像作为训练数据，50 张图像作为测试数据。对 500 000 张图像进行了 StyleGAN3 训练。将生成的 50 张图像与 50 张真实图像进行比较，根据四项指标对生成的图像进行客观评估：弗雷谢特起始距离（FID）、核起始距离（KID）、精确度和召回率以及起始分数（IS）。三位专家对生成的图像进行了主观评价，他们在视觉图灵测试中将生成的图像与真实图像进行了比较：指标结果如下：FID，199.28；KID，0.14；精确度，0.0047；召回率，0.00；IS，2.48。视觉图灵测试的总体结果为 82.3%。人类对牙根吸收的评分没有发现明显差异：StyleGAN3生成的图像质量非常高，专家们无法将其与真实图像区分开来。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Dento maxillo facial radiology 医学-核医学

CiteScore

5.60

自引率

9.10%

发文量

审稿时长

4-8 weeks

期刊介绍： Dentomaxillofacial Radiology (DMFR) is the journal of the International Association of Dentomaxillofacial Radiology (IADMFR) and covers the closely related fields of oral radiology and head and neck imaging. Established in 1972, DMFR is a key resource keeping dentists, radiologists and clinicians and scientists with an interest in Head and Neck imaging abreast of important research and developments in oral and maxillofacial radiology. The DMFR editorial board features a panel of international experts including Editor-in-Chief Professor Ralf Schulze. Our editorial board provide their expertise and guidance in shaping the content and direction of the journal. Quick Facts: - 2015 Impact Factor - 1.919 - Receipt to first decision - average of 3 weeks - Acceptance to online publication - average of 3 weeks - Open access option - ISSN: 0250-832X - eISSN: 1476-542X