Scholarlink

Background <p>Brain volume measurement serves as a critical approach for assessing brain health status. Considering the close biological connection between the eyes and brain, this study aims to investigate the feasibility of estimating brain volume through retinal fundus imaging integrated with clinical metadata, and to offer a cost-effective approach for assessing brain health.</p> Methods <p>Based on clinical information, retinal fundus images, and neuroimaging data derived from a multicenter, population-based cohort study, the KaiLuan Study, we proposed a cross-modal correlation representation (CMCR) network to elucidate the intricate co-degenerative relationships between the eyes and brain for 755 subjects. Specifically, individual clinical information, which has been followed up for as long as 12&#xa0;years, was encoded as a prompt to enhance the accuracy of brain volume estimation. Independent internal validation and external validation were performed to assess the robustness of the proposed model. Root mean square error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) metrics were employed to quantitatively evaluate the quality of synthetic brain images derived from retinal imaging data.</p> Results <p>The proposed framework yielded average RMSE, PSNR, and SSIM values of 98.23, 35.78&#xa0;dB, and 0.64, respectively, which significantly outperformed 5 other methods: multi-channel Variational Autoencoder (mcVAE), Pixel-to-Pixel (Pixel2pixel), transformer-based U-Net (TransUNet), multi-scale transformer network (MT-Net), and residual vision transformer (ResViT). The two- (2D) and three-dimensional (3D) visualization results showed that the shape and texture of the synthetic brain images generated by the proposed method most closely resembled those of actual brain images. Thus, the CMCR framework accurately captured the latent structural correlations between the fundus and the brain. The average difference between predicted and actual brain volumes was 61.36&#xa0;cm<sup>3</sup>, with a relative error of 4.54%. When all of the clinical information (including age and sex, daily habits, cardiovascular factors, metabolic factors, and inflammatory factors) was encoded, the difference was decreased to 53.89&#xa0;cm<sup>3</sup>, with a relative error of 3.98%. Based on the synthesized brain MR images from retinal fundus images, the volumes of brain tissues could be estimated with high accuracy.</p> Conclusions <p>This study provides an innovative, accurate, and cost-effective approach to characterize brain health status through readily accessible retinal fundus images.</p> <p><i>Trial registration No</i>. NCT05453877 (<a href="https://clinicaltrials.gov/">https://clinicaltrials.gov/</a>).</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

Clinical information prompt-driven retinal fundus image for brain health evaluation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年8月6日

查看全文
  • Nuo Tong,
  • Ying Hui,
  • Shui-Ping Gou,
  • Ling-Xi Chen,
  • Xiang-Hong Wang,
  • Shuo-Hua Chen,
  • Jing Li,
  • Xiao-Shuai Li,
  • Yun-Tao Wu,
  • Shou-Ling Wu,
  • Zhen-Chang Wang,
  • Jing Sun,
  • Han Lv

摘要

Background

Brain volume measurement serves as a critical approach for assessing brain health status. Considering the close biological connection between the eyes and brain, this study aims to investigate the feasibility of estimating brain volume through retinal fundus imaging integrated with clinical metadata, and to offer a cost-effective approach for assessing brain health.

Methods

Based on clinical information, retinal fundus images, and neuroimaging data derived from a multicenter, population-based cohort study, the KaiLuan Study, we proposed a cross-modal correlation representation (CMCR) network to elucidate the intricate co-degenerative relationships between the eyes and brain for 755 subjects. Specifically, individual clinical information, which has been followed up for as long as 12 years, was encoded as a prompt to enhance the accuracy of brain volume estimation. Independent internal validation and external validation were performed to assess the robustness of the proposed model. Root mean square error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) metrics were employed to quantitatively evaluate the quality of synthetic brain images derived from retinal imaging data.

Results

The proposed framework yielded average RMSE, PSNR, and SSIM values of 98.23, 35.78 dB, and 0.64, respectively, which significantly outperformed 5 other methods: multi-channel Variational Autoencoder (mcVAE), Pixel-to-Pixel (Pixel2pixel), transformer-based U-Net (TransUNet), multi-scale transformer network (MT-Net), and residual vision transformer (ResViT). The two- (2D) and three-dimensional (3D) visualization results showed that the shape and texture of the synthetic brain images generated by the proposed method most closely resembled those of actual brain images. Thus, the CMCR framework accurately captured the latent structural correlations between the fundus and the brain. The average difference between predicted and actual brain volumes was 61.36 cm3, with a relative error of 4.54%. When all of the clinical information (including age and sex, daily habits, cardiovascular factors, metabolic factors, and inflammatory factors) was encoded, the difference was decreased to 53.89 cm3, with a relative error of 3.98%. Based on the synthesized brain MR images from retinal fundus images, the volumes of brain tissues could be estimated with high accuracy.

Conclusions

This study provides an innovative, accurate, and cost-effective approach to characterize brain health status through readily accessible retinal fundus images.

Trial registration No. NCT05453877 (https://clinicaltrials.gov/).