Cardiovascular diseases is the leading cause of threat to human life and health worldwide. Early risk assessment, timely diagnosis, and prognosis evaluation are critical to the treatment of cardiovascular diseases. Currently, the evaluation of diagnosis and prognosis of cardiovascular diseases mainly relies on imaging examinations such as coronary CT and coronary angiography, which are expensive, time-consuming, partly invasive, and require high professional competence of the operator, making it difficult to promote in the community or in areas where medical resources are scarce. The fundus microcirculation is a part of the human microcirculation and has similar embryological origins and physiopathological features to cardiovascular circulation. Several studies have revealed fundus imaging biomarkers associated with cardiovascular diseases, and developed and validated intelligent diagnosis and treatment models for cardiovascular diseases based on fundus imaging data. Fundus imaging is expected to be an important adjunct to cardiovascular disease diagnosis and treatment given its noninvasive and convenient nature. The purpose of this review is to summarize the current research status, challenges, and future prospects of the application of artificial intelligence based on multimodal fundus imaging data in cardiovascular disease diagnosis and treatment.
ObjectiveTo observe the multimodal imaging characteristics of eyes with peripheral retinoschisis secondary to familial exudative vitreoretinopathy (FEVR). MethodsA retrospective case observation study. Eighteen patients (36 eyes) diagnosed with FEVR combined with peripheral retinoschisis at the Department of Ophthalmology, The Affiliated Hospital of Yunnan University from January 2022 to August 2025 were enrolled. All eyes underwent ultra-widefield fundus imaging (UWFI), swept-source optical coherence tomography (SS-OCT) and swept-source optical coherence tomography angiography (SS-OCTA); 14 eyes received fundus fluorescein angiography (FFA). The VG200D SS-OCT and SS-OCTA system [Vivid View Imaging (Henan) Co., Ltd.] was adopted for examination. Clear and typical linear B-scan images were stored for analysis, and the imaging manifestations of peripheral lesions were observed. The mean follow-up duration was 18 months. ResultsUWFI examination showed that the retina in the temporal or inferotemporal retinal schisis area of all affected eyes presented with a grayish-white, veil-like translucent appearance. No obvious hemorrhage or neovascularization was observed in the lesion area, although vascular dilation presenting a honeycomb-like appearance was seen in 8 eyes. SS-OCT examination revealed that the 36 eyes could be categorized into three types based on the extent and morphology of schisis: mild schisis (12 eyes), characterized by scattered, small optically empty spaces between the retinal layers; grid-like schisis (16 eyes), characterized by enlarged schisis cavities containing fine vertical hyperreflective strands, with band-like posterior vitreous cortical traction above; and spoke-like proliferative schisis (8 eyes), characterized by thickened spoke-like hyperreflective strands within the cavities, some of which appeared disrupted, with schisis involving the full thickness of the retina. Among the 14 eyes receiving FFA, 6 eyes had no abnormal fluorescence staining or leakage of retinal vessels in schisis areas; 8 eyes with severe vitreous traction and extensive retinoschisis displayed patchy multifocal hyperfluorescence in early phase and confluent diffuse hyperfluorescence in late phase. On SS-OCTA, dilated vascular structures within schisis lesions could be detected in eyes with severe retinoschisis besides intrinsic vascular abnormalities of FEVR. ConclusionsPeripheral retinoschisis in FEVR presents progressive morphological changes. Characteristic temporal gauze-like gray-white retinal lesions can be observed, with vascular dilatation and late fluorescence leakage in severe cases. Ultra-widefield SS-OCT clearly visualizes retinal laminar structure and vitreoretinal traction. Combining multiple imaging modalities such as UWFI, FFA and SS-OCTA, it can comprehensively present the imaging characteristics of this type of lesion at different levels.