Automated Segmentation of Lesions Including Subretinal Hyperreflective Material in Neovascular Age-related Macular Degeneration.

PURPOSE: To evaluate an automated segmentation algorithm with a convolutional neural network (CNN) to quantify and detect intraretinal fluid (IRF), subretinal fluid (SRF), pigment epithelial detachment (PED), and subretinal hyperreflective material (SHRM) through analyses of spectral-domain optical coherence tomography (SD-OCT) images from patients with neovascular age-related macular degeneration (nAMD).
DESIGN: Reliability and validity analysis of a diagnostic tool.
METHODS: We constructed a dataset including 930 B-scans from 93 eyes of 93 patients with nAMD. A CNN-based deep neural network was trained using 11 550 augmented images derived from 550 B-scans. The performance of the trained network was evaluated using a validation set including 140 B-scans and a test set of 240 B-scans. The Dice coefficient, positive predictive value (PPV), sensitivity, relative area difference (RAD), and intraclass correlation coefficient (ICC) were used to evaluate segmentation and detection performance.
RESULTS: Good agreement was observed for both segmentation and detection of lesions between the trained network and clinicians. The Dice coefficients for segmentation of IRF, SRF, SHRM, and PED were 0.78, 0.82, 0.75, and 0.80, respectively; the PPVs were 0.79, 0.80, 0.75, and 0.80, respectively; and the sensitivities were 0.77, 0.84, 0.73, and 0.81, respectively. The RADs were -4.32%, -10.29%, 4.13%, and 0.34%, respectively, and the ICCs were 0.98, 0.98, 0.97, and 0.98, respectively. All lesions were detected with high PPVs (range 0.94-0.99) and sensitivities (range 0.97-0.99).
CONCLUSIONS: A CNN-based network provides clinicians with quantitative data regarding nAMD through automatic segmentation and detection of pathologic lesions, including IRF, SRF, PED, and SHRM.