Abstract
PURPOSE: To achieve an accurate diagnosis of idiopathic epiretinal membrane (iERM) through analyzing retinal blood vessel oxygen saturation (SO2) and vascular morphological features in fundus images. METHODS: Dual-modal fundus camera was used to obtain color fundus image, 570-nm, and 610-nm images. As iERM affects the macular area, a macular-centered semicircle area as region of interest (MROI) was selected and analyzed SO2 and vascular morphologies in it. Eventually, random forest (RF) and support vector machine (SVM) were as classifiers to diagnose iERM patients. RESULTS: The arterial and venous SO2 levels of the iERM group were significantly higher than that of the control group. There were significant differences in the vessel density and fractal dimension on the artery for vascular morphology, while the tortuosity had a significant difference in the vein. By feeding the SO2 and the vascular morphological features into classifiers, an accuracy of over 82% was obtained, which is significantly better than the two separate inputs for classification. CONCLUSION: Significant differences in SO2 and vascular morphologies between control and iERM groups confirmed that the occurrence of iERM may affect blood supply and vascular structures. Benefiting from the dual-modal fundus camera and machine learning models, accurate judgments can be made on fundus images. Extensive experiments proved the importance of blood vessel SO2 and vascular morphologies for diagnosis, which is of great significance for clinical screening.