Scholarlink

Background <p>Labelled data scarcity and class imbalance are common deep learning system (DLS) development challenges. We investigated if synthetic retinal images from a conditional cascaded diffusion model (CCDM) improves prognostic DLS (pDLS) performance for 2-year incident referable diabetic retinopathy or maculopathy (rDR/rM) prediction.</p> Methods <p>Macula images from 72,559 eyes (September 2013 to December 2019) from the UK South-East London Diabetic Eye Screening Programme (SEL-DESP) formed the development dataset, whilst 9,071 eyes were used for internal testing. Images from 2,842 eyes from Birmingham DESP were used for external testing. Prognostic DLS were augmented with ×1, ×2, and ×4 additional synthetic positive cases (pDLS-G) and compared to unaugmented (pDLS-N) and ×1 positive-case resampled pDLS (pDLS-R) using the Area-Under-the Receiver Operating Characteristic curve (AUROC).</p> Results <p>Here we show that CCDM generate realistic synthetic retinal images that are comparable to real images and demonstrate the utility of synthetic retinal images in augmenting the development of a pDLS. The internal and external test AUROC for the pDLS are 0.827 (95% CI: 0.794–0.861) and 0.756 (0.680–0.831), respectively. Augmentation with ×2 additional synthetic positive cases (pDLS-G ×2) significantly improves the internal test AUROC to 0.845 (95% CI: 0.812–0.877, <i>p</i> = 0.044) but does not improve the external test AUROC 0.717 (0.633–0.828, <i>p</i> = 0.243). Resampling positive real cases alone does not improve pDLS-R performance.</p> Conclusions <p>Augmenting pDLS with synthetic retinal images significantly improves pDLS performance on internal testing but not external testing suggesting further research is required to enhance the generalisability of synthetic retinal image augmentation.</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

Augmenting a prognostic deep learning system for referable diabetic retinopathy and maculopathy with synthetic retinal images

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月20日

查看全文
  • Paul Nderitu,
  • Joan M. Nunez do Rio,
  • Laura Webster,
  • Samantha S. Mann,
  • David Hopkins,
  • Christos Bergeles,
  • Timothy L. Jackson

摘要

Background

Labelled data scarcity and class imbalance are common deep learning system (DLS) development challenges. We investigated if synthetic retinal images from a conditional cascaded diffusion model (CCDM) improves prognostic DLS (pDLS) performance for 2-year incident referable diabetic retinopathy or maculopathy (rDR/rM) prediction.

Methods

Macula images from 72,559 eyes (September 2013 to December 2019) from the UK South-East London Diabetic Eye Screening Programme (SEL-DESP) formed the development dataset, whilst 9,071 eyes were used for internal testing. Images from 2,842 eyes from Birmingham DESP were used for external testing. Prognostic DLS were augmented with ×1, ×2, and ×4 additional synthetic positive cases (pDLS-G) and compared to unaugmented (pDLS-N) and ×1 positive-case resampled pDLS (pDLS-R) using the Area-Under-the Receiver Operating Characteristic curve (AUROC).

Results

Here we show that CCDM generate realistic synthetic retinal images that are comparable to real images and demonstrate the utility of synthetic retinal images in augmenting the development of a pDLS. The internal and external test AUROC for the pDLS are 0.827 (95% CI: 0.794–0.861) and 0.756 (0.680–0.831), respectively. Augmentation with ×2 additional synthetic positive cases (pDLS-G ×2) significantly improves the internal test AUROC to 0.845 (95% CI: 0.812–0.877, p = 0.044) but does not improve the external test AUROC 0.717 (0.633–0.828, p = 0.243). Resampling positive real cases alone does not improve pDLS-R performance.

Conclusions

Augmenting pDLS with synthetic retinal images significantly improves pDLS performance on internal testing but not external testing suggesting further research is required to enhance the generalisability of synthetic retinal image augmentation.