Abstract：
Generative Adversarial Networks (GANs) can produce synthetic images free from personal data. They hold significant value in medical research, where data protection is increasingly regulated. Panoramic radiographs (PRs) are a well-suited modality due to their significant level of standardization while simultaneously displaying a high degree of personally identifiable data.
We produced synthetic PRs (syPRs) out of real PRs (rePRs) using StyleGAN2-ADA by NVIDIA©. A survey was performed on 54 medical professionals and 33 dentistry students. They assessed 45 radiological images (20 rePRs, 20 syPRs, and 5 syPRcontrols) as real or synthetic and interpreted a single-image syPR according to the image quality (0-10) and 14 different items (agreement/disagreement). They also rated the importance for the profession (0-10). A follow-up was performed for test-retest reliability with >10 % of all participants.
Overall, the sensitivity was 78.2 % and the specificity was 82.5 %. For professionals, the sensitivity was 79.9 % and the specificity was 82.3 %. For students, the sensitivity was 75.5 % and the specificity was 82.7 %. In the single syPR-interpretation image quality was rated at a median of 6 and 11 items were considered as agreement. The importance for the profession was rated at a median score of 7. The Test-retest reliability yielded a value of 0.23 (Cohen\'s kappa).
The study marks a comprehensive testing to demonstrate that GANs can produce synthetic radiological images that even health professionals can sometimes not differentiate from real radiological images, thereby being genuinely considered authentic. This enables their utilization and/or modification free from personally identifiable information.
Synthetic images can be used for university teaching and patient education without relying on patient-related data. They can also be utilized to upscale existing training datasets to improve the accuracy of AI-based diagnostic systems. The study thereby supports clinical teaching as well as diagnostic and therapeutic decision-making.
We produced synthetic PRs (syPRs) out of real PRs (rePRs) using StyleGAN2-ADA by NVIDIA©. A survey was performed on 54 medical professionals and 33 dentistry students. They assessed 45 radiological images (20 rePRs, 20 syPRs, and 5 syPRcontrols) as real or synthetic and interpreted a single-image syPR according to the image quality (0-10) and 14 different items (agreement/disagreement). They also rated the importance for the profession (0-10). A follow-up was performed for test-retest reliability with >10 % of all participants.
Overall, the sensitivity was 78.2 % and the specificity was 82.5 %. For professionals, the sensitivity was 79.9 % and the specificity was 82.3 %. For students, the sensitivity was 75.5 % and the specificity was 82.7 %. In the single syPR-interpretation image quality was rated at a median of 6 and 11 items were considered as agreement. The importance for the profession was rated at a median score of 7. The Test-retest reliability yielded a value of 0.23 (Cohen\'s kappa).
The study marks a comprehensive testing to demonstrate that GANs can produce synthetic radiological images that even health professionals can sometimes not differentiate from real radiological images, thereby being genuinely considered authentic. This enables their utilization and/or modification free from personally identifiable information.
Synthetic images can be used for university teaching and patient education without relying on patient-related data. They can also be utilized to upscale existing training datasets to improve the accuracy of AI-based diagnostic systems. The study thereby supports clinical teaching as well as diagnostic and therapeutic decision-making.
摘要：
目标：生成对抗网络（GAN）可以生成不受个人数据影响的合成图像。它们在医学研究中具有重要价值，数据保护越来越受到监管。全景射线照片（PR）是一种非常适合的模态，因为它们具有显着的标准化水平，同时显示高度的个人可识别数据。
方法：我们使用NVIDIA©的StyleGAN2-ADA从真实PR（rePRs）中生产了合成PR（syPRs）。对54名医学专业人员和33名牙科学生进行了调查。他们评估了45张放射学图像(20张rePRs，20个系统，和5个syPRcontrols）作为真实或合成的，并根据图像质量（0-10）和14个不同的项目（同意/不同意）解释单个图像syPR。他们还对该行业的重要性进行了评分（0-10）。对所有参与者中>10%的测试-重测可靠性进行了随访。
结果：总体而言，敏感性为78.2%,特异性为82.5%.对于专业人士来说,敏感性为79.9%,特异性为82.3%.对于学生来说，敏感性为75.5%,特异性为82.7%.在单个syPR解释中，图像质量的中位数为6，11个项目被认为是一致的。对该行业的重要性评分中位数为7分。测试-重测可靠性得出的值为0.23(科恩的kappa)。
结论：这项研究标志着一项全面的测试，以证明GAN可以产生合成的放射图像，即使是卫生专业人员有时也无法与真实的放射图像区分开，因此，真正被认为是真实的。这使得它们的使用和/或修改不受个人身份信息的影响。
结论：合成图像可用于大学教学和患者教育，而无需依赖患者相关数据。它们还可以用于升级现有的训练数据集，以提高基于AI的诊断系统的准确性。因此，该研究支持临床教学以及诊断和治疗决策。
方法：我们使用NVIDIA©的StyleGAN2-ADA从真实PR（rePRs）中生产了合成PR（syPRs）。对54名医学专业人员和33名牙科学生进行了调查。他们评估了45张放射学图像(20张rePRs，20个系统，和5个syPRcontrols）作为真实或合成的，并根据图像质量（0-10）和14个不同的项目（同意/不同意）解释单个图像syPR。他们还对该行业的重要性进行了评分（0-10）。对所有参与者中>10%的测试-重测可靠性进行了随访。
结果：总体而言，敏感性为78.2%,特异性为82.5%.对于专业人士来说,敏感性为79.9%,特异性为82.3%.对于学生来说，敏感性为75.5%,特异性为82.7%.在单个syPR解释中，图像质量的中位数为6，11个项目被认为是一致的。对该行业的重要性评分中位数为7分。测试-重测可靠性得出的值为0.23(科恩的kappa)。
结论：这项研究标志着一项全面的测试，以证明GAN可以产生合成的放射图像，即使是卫生专业人员有时也无法与真实的放射图像区分开，因此，真正被认为是真实的。这使得它们的使用和/或修改不受个人身份信息的影响。
结论：合成图像可用于大学教学和患者教育，而无需依赖患者相关数据。它们还可以用于升级现有的训练数据集，以提高基于AI的诊断系统的准确性。因此，该研究支持临床教学以及诊断和治疗决策。
