Using Radiomic Features to Predict Visual Prognosis of Idiopathic Macular Hole Surgery

Abstract

Idiopathic macular holes (IMH) are a leading cause of vision loss in middle-aged and older people. IMH is usually treated surgically by vitrectomy. Improvement in visual acuity is used to assess the prognosis of macular hole surgery. To achieve better diagnosis and treatment of IMH, Optical coherence tomography (OCT) technology is widely used. It will improve patient outcomes if parameters that are correlated with favorable prognoses are identified in OCT images. Both 2D OCT images and 3D OCT images can be obtained, which allows for the possibility of extracting 3D features. We propose the use of radiomic features as predictors of IMH prognosis. In this study, radiomic techniques were used to identify shape and texture features of IMH. OCT images were sliced into 2D images to enable experts to segment the region of interest before feature extraction. Elements of an initial set of mined features were selected as predictors based on correlation analysis and least absolute shrinkage and selection operator data analysis. P-values between selected features and best-corrected visual acuity were calculated to identify significant features. Nine features were found that influence surgical outcomes. Receiver operating characteristic curve analyses of positive samples (post-surgical visual outcome improved more than 0.3) and negative samples (all nonpositive samples) showed the area under the ROC curve of the radiomic feature set reached 0.81. Analysis showed that radiomic features of preoperative OCT images accurately predict visual prognosis, and thus identifying the features can be a powerful diagnostic technique.