The eye is the unique organ in the body which allows for the direct observation and imaging of the neurological and vascular system. In recent years, researchers have harnessed the noninvasive nature of colour fundus photographs (CFPs) to examine changes of the retina as possible biomarkers of the systemic diseasesSystemic disease’ risks. Building on large-scale epidemiological and clinical studies that have reported relationships of retinal features such as retinal vascular calibre with systemic diseasesSystemic disease, the application of artificial intelligence (AIArtificial Intelligence (AI)) technology, specifically in deep learningDeep learning (DL), on ocular images, especially CFPs, is advancing new research that focuses on retina-systemic diseaseSystemic disease relationships. In this relatively new field, current studies fall into 3 basic groups: (1) cross-sectional studies that use AIArtificial Intelligence (AI)-DL technology on CFPs to detect or estimate systemic risk factors (e.g., age, blood pressure, smoking); (2) cross-sectional studies that use AIArtificial Intelligence (AI)-DL technology on CFPs to replace established examination results, such as carotid ultrasound, cardiac computerized tomography, and magnetic resonance imaging, to detect the systemic biomarkersSystemic biomarker (e.g., coronary artery calcium); (3) longitudinal studies that use AIArtificial Intelligence (AI)-DL technology on CFPs to predict the incidence or risk of systemic diseaseSystemic disease (e.g., cardiovascular event or mortality). The range of systemic factors studied from CFPs via AIArtificial Intelligence (AI)-DL approaches is reviewed based on these cross-sectional and longitudinal studies, and areas of future research are discussed while acknowledging the limitations that AIArtificial Intelligence (AI)-DL on CFPs presents. In addition, with the updates and developments of eye imaging, more advanced ocular imagingOcular imaging like optical coherence tomographyOptical coherence tomography (OCT), OCT-angiography, ultra-wide field images, adaptic optives and external eye photos have also been applied in AIArtificial Intelligence (AI)-DL technology to predict systemic diseasesSystemic disease.

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

Artificial Intelligence Using the Eye as a Biomarker of Systemic Risk

  • Jinyuan Wang,
  • Rachel Marjorie Wei Wen Tseng,
  • Tyler Hyungtaek Rim,
  • Carol Y. Cheung,
  • Tien Yin Wong

摘要

The eye is the unique organ in the body which allows for the direct observation and imaging of the neurological and vascular system. In recent years, researchers have harnessed the noninvasive nature of colour fundus photographs (CFPs) to examine changes of the retina as possible biomarkers of the systemic diseasesSystemic disease’ risks. Building on large-scale epidemiological and clinical studies that have reported relationships of retinal features such as retinal vascular calibre with systemic diseasesSystemic disease, the application of artificial intelligence (AIArtificial Intelligence (AI)) technology, specifically in deep learningDeep learning (DL), on ocular images, especially CFPs, is advancing new research that focuses on retina-systemic diseaseSystemic disease relationships. In this relatively new field, current studies fall into 3 basic groups: (1) cross-sectional studies that use AIArtificial Intelligence (AI)-DL technology on CFPs to detect or estimate systemic risk factors (e.g., age, blood pressure, smoking); (2) cross-sectional studies that use AIArtificial Intelligence (AI)-DL technology on CFPs to replace established examination results, such as carotid ultrasound, cardiac computerized tomography, and magnetic resonance imaging, to detect the systemic biomarkersSystemic biomarker (e.g., coronary artery calcium); (3) longitudinal studies that use AIArtificial Intelligence (AI)-DL technology on CFPs to predict the incidence or risk of systemic diseaseSystemic disease (e.g., cardiovascular event or mortality). The range of systemic factors studied from CFPs via AIArtificial Intelligence (AI)-DL approaches is reviewed based on these cross-sectional and longitudinal studies, and areas of future research are discussed while acknowledging the limitations that AIArtificial Intelligence (AI)-DL on CFPs presents. In addition, with the updates and developments of eye imaging, more advanced ocular imagingOcular imaging like optical coherence tomographyOptical coherence tomography (OCT), OCT-angiography, ultra-wide field images, adaptic optives and external eye photos have also been applied in AIArtificial Intelligence (AI)-DL technology to predict systemic diseasesSystemic disease.