DEEP LEARNING-BASED PREDICTION OF OUTCOMES FOLLOWING NONCOMPLICATED EPIRETINAL MEMBRANE SURGERY. Issue 8 (August 2022)

• Record Type: Journal Article
• Authors: Kim, Soo Han; Ahn, Honggi; Yang, Sejung; Soo Kim, Sung; Lee, Jong Hyuck
• Is Part Of: Retina. Volume 42:Issue 8(2022)
• Page Start: 1465
• Page End: 1471
• Publication Date: 2022-08
• Subjects: central foveal thickness -- deep learning -- epiretinal membrane surgery -- optical coherence tomography -- vitrectomy; Retina -- Diseases -- Periodicals; Retinal Diseases; Vitreous Body; 617.735
• DOI: 10.1097/IAE.0000000000003480
• Languages: English
• ISSNs: 0275-004X

Abstract

Abstract : Supplemental Digital Content is Available in the Text. Deep learning can predict the final central foveal thickness and its changes after noncomplicated epiretinal membrane removal surgery. Demographics, comorbidities, and surgical methods affect central foveal thickness. Inner retinal layer may importantly influence the final central foveal thickness. Abstract : Purpose: We used deep learning to predict the final central foveal thickness (CFT), changes in CFT, final best corrected visual acuity, and best corrected visual acuity changes following noncomplicated idiopathic epiretinal membrane surgery. Methods: Data of patients who underwent noncomplicated epiretinal membrane surgery at Severance Hospital from January 1, 2010, to December 31, 2018, were reviewed. Patient age, sex, hypertension and diabetes statuses, and preoperative optical coherence tomography scans were noted. For image analysis and model development, a pre-trained VGG16 was adopted. The mean absolute error and coefficient of determination (R 2 ) were used to evaluate the model performances. The study involved 688 eyes of 657 patients. Results: For final CFT, the mean absolute error was the lowest in the model that considered only clinical and demographic characteristics; the highest accuracy was achieved by the model that considered all clinical and surgical information. For CFT changes, models utilizing clinical and surgical information showed the best performance. However, our best model failed to predict the final best corrected visual acuity and best corrected visual acuity changes. Conclusion: A deep learning model predicted the final CFT and CFT changes in patients 1 year after epiretinal membrane surgery. Central foveal thickness prediction showed the best results when demographic factors, comorbid diseases, and surgical techniques were considered.