Screening chronic kidney disease through deep learning utilizing ultra-wide-field fundus images

To address challenges in screening for chronic kidney disease (CKD), we devised a deep learning-based CKD screening model named UWF-CKDS. It utilizes ultra-wide-field (UWF) fundus images to predict the presence of CKD. We validated the model with data from 23 tertiary hospitals across China. Retinal vessels and retinal microvascular parameters (RMPs) were extracted to enhance model interpretability, which revealed a significant correlation between renal function and RMPs. UWF-CKDS, utilizing UWF images, RMPs, and relevant medical history, can accurately determine CKD status. Importantly, UWF-CKDS exhibited superior performance compared to CTR-CKDS, a model developed using the central region (CTR) cropped from UWF images, underscoring the contribution of the peripheral retina in predicting renal function. The study presents UWF-CKDS as a highly implementable method for large-scale and accurate CKD screening at the population level.

Authors

Institutions

Publication Details

Journal
npj Digital Medicine
Published
2024-10-07
DOI
https://doi.org/10.1038/s41746-024-01271-w
Citations
11
Primary Topic
Retinal Imaging and Analysis
Type
article
Field-Weighted Citation Impact
4.45

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Screening chronic kidney disease through deep learning utilizing ultra-wide-field fundus images

Youxin Chen, Anyi Liang, Charumathi Sabanayagam, Shiyu Cheng et al.
11 citations
npj Digital Medicine
Retinal Imaging and Analysis
4.45
article

Screening chronic kidney disease through deep learning utilizing ultra-wide-field fundus images

Youxin Chen, Anyi Liang, Charumathi Sabanayagam, Shiyu Cheng, Hongbin Lv, Shengyin Jiao, Lihui Meng, Guofang Jiao, Xiaowei Ding, Changzheng Chen, Zhengming Shi, Changlong Jiang, Xiaolei Sun, Tien Yin Wong, Mengda Li, Bilei Zhang, Zilong Wang, Hao Zhang, Han Zhang, Dawei Sun, Qiuming Li, Xingwang Gu, Wenfei Zhang, Xinyu Zhao, Qing Zhao, Yongwei Chen, Donglei Zhang, Dan Zhu, Chang Su, Tiantian Cheng, Da Teng, Ling Yuan, Xia Song, Chuting Wang, Rishet Ahmat, Yakun Li, Z. Y. Zhang, Huiqin Lu, Ming-Mei Xue
article en
11 citations

Abstract

To address challenges in screening for chronic kidney disease (CKD), we devised a deep learning-based CKD screening model named UWF-CKDS. It utilizes ultra-wide-field (UWF) fundus images to predict the presence of CKD. We validated the model with data from 23 tertiary hospitals across China. Retinal vessels and retinal microvascular parameters (RMPs) were extracted to enhance model interpretability, which revealed a significant correlation between renal function and RMPs. UWF-CKDS, utilizing UWF images, RMPs, and relevant medical history, can accurately determine CKD status. Importantly, UWF-CKDS exhibited superior performance compared to CTR-CKDS, a model developed using the central region (CTR) cropped from UWF images, underscoring the contribution of the peripheral retina in predicting renal function. The study presents UWF-CKDS as a highly implementable method for large-scale and accurate CKD screening at the population level.

npj Digital MedicineVol. 7(1)
Fujian Medical University (CN), Harbin Medical University (CN), Hebei North University (CN), Hunan Normal University (CN), Shanxi Medical University (CN), Shanghai Jiao Tong University (CN), Capital Medical University (CN), GTx (United States) (US), Chengde Medical University (CN), Chinese Academy of Medical Sciences & Peking Union Medical College (CN), Kunming Medical University (CN), Singapore National Eye Center (SG), Peking Union Medical College Hospital (CN), Wuhan University (CN), Affiliated Hospital of Southwest Medical University (CN), Beijing Tian Tan Hospital (CN), The Fourth People's Hospital (CN), Microsoft Research Asia (China) (CN), Singapore Eye Research Institute (SG), First Affiliated Hospital of Kunming Medical University (CN), First Hospital of Shanxi Medical University (CN), Second Affiliated Hospital of Harbin Medical University (CN), Renmin Hospital of Wuhan University (CN), First Hospital of China Medical University (CN), Guangdong Academy of Medical Sciences (CN), Hunan Provincial People's Hospital (CN), Beijing Tsinghua Chang Gung Hospital (CN), Guangdong Provincial People's Hospital (CN), Guizhou Provincial People's Hospital (CN), First Affiliated Hospital of Zhengzhou University (CN), Shandong Eye Hospital (CN), Shandong First Medical University (CN), Union Hospital (CN), Inner Mongolia Medical University (CN), Southern Medical University (CN), China Medical University (CN), Tsinghua University (CN)
National Natural Science Foundation of China, Peking Union Medical College Hospital
Openalex Percentile: Top 5%
Retinal Imaging and Analysis
4.45
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.