Scholarlink

Purpose <p>This study aims to address the scarcity of annotated Anterior Segment Optical Coherence Tomography (AS-OCT) datasets in ophthalmology by using Denoising Diffusion Generative Adversarial Networks (DD-GANs) to generate synthetic AS-OCT images to produce predictive models. The goal is to produce high-quality, diverse, and realistic data supporting the training of predictive models without data imbalance issues.</p> Methods <p>AS-OCT images obtained from a tertiary referral hospital were used to train two DD-GAN models—one for healthy images and another for unhealthy AS-OCT images. The generated synthetic datasets were evaluated using Fréchet Inception Distance (FID) and Inception Scores to assess image quality. To further validate the synthetic data, two ResNet-50 models were trained separately on the real and synthetic datasets and evaluated on each other’s test sets to measure performance comparability.</p> Results <p>Two synthetic datasets were created: a smaller set with 15.7&#xa0;k images (6.8&#xa0;k healthy, 8.9&#xa0;k unhealthy) and a larger set with 100&#xa0;k images (50&#xa0;k each). The FID scores were 0.17 for healthy images and 0.23 for unhealthy ones, indicating high-quality synthesis. Inception Scores were 1.46 for healthy data and 1.55 for unhealthy data. ResNet-50 models trained on synthetic data achieved results comparable to models trained on real data.</p> Conclusion <p>DD-GANs effectively generate realistic AS-OCT images, producing high-quality, balanced datasets that can address data scarcity and imbalance in ophthalmology. These synthetic datasets can enhance machine learning model development, advancing medical image analysis. Synthetic medical image generation provides significant advantages in protecting personal data privacy. By using artificially generated data instead of real data, patients’ identities and confidentiality are safeguarded.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Denoising diffusion-based anterior segment optical coherence tomography (AS-OCT) image generation

  • 期刊论文

  • 发表日期：

    2025年10月23日

查看全文
  • Berat Ersarı,
  • Muhammed Görkem Kola,
  • Emine Esra Karaca,
  • Feyza Dicle Işık,
  • Özlem Evren Kemer,
  • Ali Seydi Keçeli,
  • Aydın Kaya,
  • Tuğba Gürgen Erdoğan,
  • Alaettin Uçan

摘要

Purpose

This study aims to address the scarcity of annotated Anterior Segment Optical Coherence Tomography (AS-OCT) datasets in ophthalmology by using Denoising Diffusion Generative Adversarial Networks (DD-GANs) to generate synthetic AS-OCT images to produce predictive models. The goal is to produce high-quality, diverse, and realistic data supporting the training of predictive models without data imbalance issues.

Methods

AS-OCT images obtained from a tertiary referral hospital were used to train two DD-GAN models—one for healthy images and another for unhealthy AS-OCT images. The generated synthetic datasets were evaluated using Fréchet Inception Distance (FID) and Inception Scores to assess image quality. To further validate the synthetic data, two ResNet-50 models were trained separately on the real and synthetic datasets and evaluated on each other’s test sets to measure performance comparability.

Results

Two synthetic datasets were created: a smaller set with 15.7 k images (6.8 k healthy, 8.9 k unhealthy) and a larger set with 100 k images (50 k each). The FID scores were 0.17 for healthy images and 0.23 for unhealthy ones, indicating high-quality synthesis. Inception Scores were 1.46 for healthy data and 1.55 for unhealthy data. ResNet-50 models trained on synthetic data achieved results comparable to models trained on real data.

Conclusion

DD-GANs effectively generate realistic AS-OCT images, producing high-quality, balanced datasets that can address data scarcity and imbalance in ophthalmology. These synthetic datasets can enhance machine learning model development, advancing medical image analysis. Synthetic medical image generation provides significant advantages in protecting personal data privacy. By using artificially generated data instead of real data, patients’ identities and confidentiality are safeguarded.