Performance of retinal fluid monitoring in OCT imaging by automated deep learning versus human expert grading in neovascular AMD

Abstract

Purpose: To evaluate the reliability of automated fluid detection in identifying retinal fluid activity in OCT scans of patients treated with anti-VEGF therapy for neovascular age-related macular degeneration by correlating human expert and automated measurements with central retinal subfield thickness (CSFT) and fluid volume values.

Methods: We utilized an automated deep learning approach to quantify macular fluid in SD-OCT volumes (Cirrus, Spectralis, Topcon) from patients of HAWK and HARRIER Studies. Three-dimensional volumes for IRF and SRF were measured at baseline and under therapy in the central millimeter and compared to fluid gradings, CSFT and foveal centerpoint thickness (CPT) values measured by the Vienna Reading Center.

Results: 41.906 SD-OCT volume scans were included into the analysis. Concordance between human expert grading and automated algorithm performance reached AUC values of 0.93/0.85 for IRF and 0.87 for SRF in HARRIER/HAWK in the central millimeter. IRF volumes showed a moderate correlation with CSFT at baseline (HAWK: r = 0.54; HARRIER: r = 0.62) and weaker correlation under therapy (HAWK: r = 0.44; HARRIER: r = 0.34). SRF and CSFT correlations were low at baseline (HAWK: r = 0.29; HARRIER: r = 0.22) and under therapy (HAWK: r = 0.38; HARRIER: r = 0.45). The residual standard error (IRF: 75.90 µm; SRF: 95.26 µm) and marginal residual standard deviations (IRF: 46.35 µm; SRF: 44.19 µm) of fluid volume were high compared to the range of CSFT values.

Conclusion: Deep learning-based segmentation of retinal fluid performs reliably on OCT images. CSFT values are weak indicators for fluid activity in nAMD. Automated quantification of fluid types, highlight the potential of deep learning-based approaches to objectively monitor anti-VEGF therapy.

Fig. 1. Flow diagram of scans processing.

44,903 OCT scans were available from HAWK and HARRIER studies. 3.765 scans had to be excluded leaving 41,147 scans of 1,185 patients for analysis.

Fig. 2. Detection level AUC values of HARRIER and HAWK.

AUC values of the detection of fluid between expert graders and algorithmic reading in HAWK and HARRIER.

Fig. 3

Median fluid volumes (IRF and SRF) with interquartile range over time.

Fig. 4

a Correlation of fluid volumes (IRF and SRF) at baseline and under therapy with CSFT in HARRIER´. b Correlation of Fluid volumes at baseline and under therapy with CSFT in HAWK.