PHOTODIAGNOSIS WITH DEEP LEARNING: A GAN AND AUTOENCODER-BASED APPROACH FOR DIABETIC RETINOPATHY DETECTION.

Kerem Gencer, Gülcan Gencer, Tuğçe Horozoğlu Ceran, Aynur Er Bilir, Mustafa Doğan
{"title":"PHOTODIAGNOSIS WITH DEEP LEARNING: A GAN AND AUTOENCODER-BASED APPROACH FOR DIABETIC RETINOPATHY DETECTION.","authors":"Kerem Gencer, Gülcan Gencer, Tuğçe Horozoğlu Ceran, Aynur Er Bilir, Mustafa Doğan","doi":"10.1016/j.pdpdt.2025.104552","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Diabetic retinopathy (DR) is a leading cause of visual impairment and blindness worldwide, necessitating early detection and accurate diagnosis. This study proposes a novel framework integrating Generative Adversarial Networks (GANs) for data augmentation, denoising autoencoders for noise reduction, and transfer learning with EfficientNetB0 to enhance the performance of DR classification models.</p><p><strong>Methods: </strong>GANs were employed to generate high-quality synthetic retinal images, effectively addressing class imbalance and enriching the training dataset. Denoising autoencoders further improved image quality by reducing noise and eliminating common artifacts such as speckle noise, motion blur, and illumination inconsistencies, providing clean and consistent inputs for the classification model. EfficientNetB0 was fine-tuned on the augmented and denoised dataset.</p><p><strong>Results: </strong>The framework achieved exceptional classification metrics, including 99.00% accuracy, recall, and specificity, surpassing state-of-the-art methods. The study employed a custom-curated OCT dataset featuring high-resolution and clinically relevant images, addressing challenges such as limited annotated data and noisy inputs.</p><p><strong>Conclusions: </strong>Unlike existing studies, our work uniquely integrates GANs, autoencoders, and EfficientNetB0, demonstrating the robustness, scalability, and clinical potential of the proposed framework. Future directions include integrating interpretability tools to enhance clinical adoption and exploring additional imaging modalities to further improve generalizability. This study highlights the transformative potential of deep learning in addressing critical challenges in diabetic retinopathy diagnosis.</p>","PeriodicalId":94170,"journal":{"name":"Photodiagnosis and photodynamic therapy","volume":" ","pages":"104552"},"PeriodicalIF":0.0000,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Photodiagnosis and photodynamic therapy","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1016/j.pdpdt.2025.104552","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Diabetic retinopathy (DR) is a leading cause of visual impairment and blindness worldwide, necessitating early detection and accurate diagnosis. This study proposes a novel framework integrating Generative Adversarial Networks (GANs) for data augmentation, denoising autoencoders for noise reduction, and transfer learning with EfficientNetB0 to enhance the performance of DR classification models.

Methods: GANs were employed to generate high-quality synthetic retinal images, effectively addressing class imbalance and enriching the training dataset. Denoising autoencoders further improved image quality by reducing noise and eliminating common artifacts such as speckle noise, motion blur, and illumination inconsistencies, providing clean and consistent inputs for the classification model. EfficientNetB0 was fine-tuned on the augmented and denoised dataset.

Results: The framework achieved exceptional classification metrics, including 99.00% accuracy, recall, and specificity, surpassing state-of-the-art methods. The study employed a custom-curated OCT dataset featuring high-resolution and clinically relevant images, addressing challenges such as limited annotated data and noisy inputs.

Conclusions: Unlike existing studies, our work uniquely integrates GANs, autoencoders, and EfficientNetB0, demonstrating the robustness, scalability, and clinical potential of the proposed framework. Future directions include integrating interpretability tools to enhance clinical adoption and exploring additional imaging modalities to further improve generalizability. This study highlights the transformative potential of deep learning in addressing critical challenges in diabetic retinopathy diagnosis.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Highly malignant tumor cells accumulate less PpIX and enhanced cell dormancy increases PpIX accumulation. PHOTODIAGNOSIS WITH DEEP LEARNING: A GAN AND AUTOENCODER-BASED APPROACH FOR DIABETIC RETINOPATHY DETECTION. Comparative analysis of photodynamic therapy and conization for cervical high-grade squamous intraepithelial lesion: a systematic review and meta-analysis. A novel vaginal manipulator for identifying vaginal canal separation line by visible and near-infrared transillumination light: PHARUS Pipe. In vitro effect of photodynamic therapy with two photosensitizers on Streptococcus mutans load around metal and ceramic brackets bonded to enamel.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1