Your browser doesn't support javascript.
loading
Ocular biomarkers of cognitive decline based on deep-learning retinal vessel segmentation.
Li, Rui; Hui, Ying; Zhang, Xiaoyue; Zhang, Shun; Lv, Bin; Ni, Yuan; Li, Xiaoshuai; Liang, Xiaoliang; Yang, Ling; Lv, Han; Yin, Zhiyu; Li, Hongyang; Yang, Yingping; Liu, Guangfeng; Li, Jing; Xie, Guotong; Wu, Shouling; Wang, Zhenchang.
Afiliação
  • Li R; Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, China.
  • Hui Y; Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, China.
  • Zhang X; Ping An Healthcare Technology, Beijing, China.
  • Zhang S; Department of Psychiatry, Kailuan Mental Health Centre, Hebei province, Tangshan, China.
  • Lv B; Ping An Healthcare Technology, Beijing, China.
  • Ni Y; Ping An Healthcare Technology, Beijing, China.
  • Li X; Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, China.
  • Liang X; Department of Psychiatry, Kailuan Mental Health Centre, Hebei province, Tangshan, China.
  • Yang L; School of Public Health, North China University of Science and Technology, Hebei province, Tangshan, China.
  • Lv H; Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, China.
  • Yin Z; Longzhen Senior Care, Beijing, China.
  • Li H; Department of Ophthalmology, Beijing Friendship Hospital, Capital Medical University, Beijing, China.
  • Yang Y; Ministry of Education Key Laboratory of Environment and Health, and State Key Laboratory of Environmental Health (Incubating), School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
  • Liu G; Department of Ophthalmology, Peking University International Hospital, Beijing, China.
  • Li J; Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, China. lijingxbhtr@163.com.
  • Xie G; Ping An Healthcare Technology, Beijing, China. xieguotong@pingan.com.cn.
  • Wu S; Department of Cardiology, Kailuan General Hospital, 57 Xinhua E Rd, Tangshan, China. drwusl@163.com.
  • Wang Z; Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, China. cjr.wzhch@vip.163.com.
BMC Geriatr ; 24(1): 28, 2024 01 06.
Article em En | MEDLINE | ID: mdl-38184539
ABSTRACT

BACKGROUND:

The current literature shows a strong relationship between retinal neuronal and vascular alterations in dementia. The purpose of the study was to use NFN+ deep learning models to analyze retinal vessel characteristics for cognitive impairment (CI) recognition.

METHODS:

We included 908 participants from a community-based cohort followed for over 15 years (the prospective KaiLuan Study) who underwent brain magnetic resonance imaging (MRI) and fundus photography between 2021 and 2022. The cohort consisted of both cognitively healthy individuals (N = 417) and those with cognitive impairment (N = 491). We employed the NFN+ deep learning framework for retinal vessel segmentation and measurement. Associations between Retinal microvascular parameters (RMPs central retinal arteriolar / venular equivalents, arteriole to venular ratio, fractal dimension) and CI were assessed by Pearson correlation. P < 0.05 was considered statistically significant. The correlation between the CI and RMPs were explored, then the correlation coefficients between CI and RMPs were analyzed. Random Forest nonlinear classification model was used to predict whether one having cognitive decline or not. The assessment criterion was the AUC value derived from the working characteristic curve.

RESULTS:

The fractal dimension (FD) and global vein width were significantly correlated with the CI (P < 0.05). Age (0.193), BMI (0.154), global vein width (0.106), retinal vessel FD (0.099), and CRAE (0.098) were the variables in this model that were ranked in order of feature importance. The AUC values of the model were 0.799.

CONCLUSIONS:

Establishment of a predictive model based on the extraction of vascular features from fundus images has a high recognizability and predictive power for cognitive function and can be used as a screening method for CI.
Assuntos
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Disfunção Cognitiva / Aprendizado Profundo Tipo de estudo: Observational_studies / Prognostic_studies / Risk_factors_studies Limite: Humans Idioma: En Revista: BMC Geriatr Assunto da revista: GERIATRIA Ano de publicação: 2024 Tipo de documento: Article País de afiliação: China

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Disfunção Cognitiva / Aprendizado Profundo Tipo de estudo: Observational_studies / Prognostic_studies / Risk_factors_studies Limite: Humans Idioma: En Revista: BMC Geriatr Assunto da revista: GERIATRIA Ano de publicação: 2024 Tipo de documento: Article País de afiliação: China