Automated measurement of macular neovascularization lesion size in nAMD using AI segmentation

TL;DR

This study shows that AI can accurately measure macular neovascularization in AMD patients using OCT scans, comparable to manual methods.

Contribution

AI-based segmentation of hyperreflective material correlates well with manual measurements of macular neovascularization over time.

Findings

AI-based HRM segmentation showed strong correlation (r = 0.78) with manual MNV measurements.

Longitudinal assessments showed comparable lesion growth between AI and manual methods.

AI measurements occasionally overestimated HRM at baseline, while manual measurements underestimated during follow-up.

Abstract

To compare artificial intelligence (AI)-based annotations of hyperreflective material (HRM) and manual demarcation of macular neovascularization (MNV) on optical coherence tomography (OCT) volume scans in neovascular age-related macular degeneration (nAMD), and to assess the suitability of AI-driven OCT segmentation for longitudinal lesion monitoring.

In this retrospective study, 42 eyes from 36 patients (21 f, 15 m; mean age baseline 76.6 y) with exudative nAMD were analyzed using longitudinal spectral-domain OCT data. Manual MNV demarcations on en-face OCT projections served as ground truth and were compared to AI-predicted HRM segmentations generated by a 3D nU-Net model on OCT scans. HRM and MNV lesion areas were quantified at multiple time points, and agreement between manual and AI-based measurements was evaluated using Pearson correlation, ordinary least squares regression and robust regression.

A highly similar mean lesion growth was observed when comparing HRM/MNV lesion sizes in longitudinal measurements. Point-by-point comparison revealed a strong overall correlation (r = 0.78) between AI-predicted and manually annotated HRM areas with increasing significance with longer follow-up. However, two aspects were responsible for some AI measurements being larger than manual measurements: At baseline, AI measurements included hyperreflective subretinal fluid as HRM, which was resorbed after three anti-VEGF injections, and during longer-term follow-up, manually annotated MNV areas were occasionally smaller than those derived from AI-based HRM segmentation due to the manual underestimation of very thin HRM.

AI-based segmentation of HRM on OCT scans demonstrates strong overall agreement with manual MNV measurements, particularly on longitudinal assessments. Despite some AI-based overestimations occurring at baseline and some manual MNV underestimations during follow-up, measurements between both methods were highly comparable over time.

What is known

Quantifying macular neovascularization (MNV) lesion size in neovascular age-related macular degeneration (nAMD) is essential for characterizing disease severity.Manual delineation of MNV on OCT scans is time-consuming, whereas AI-based segmentation enables automated, precise and reproducible quantification.

Quantifying macular neovascularization (MNV) lesion size in neovascular age-related macular degeneration (nAMD) is essential for characterizing disease severity.

Manual delineation of MNV on OCT scans is time-consuming, whereas AI-based segmentation enables automated, precise and reproducible quantification.

What is new

We demonstrate that automated measurements of hyperreflective material (HRM) size correlate well with manual MNV size annotations over time.AI-based automated measurements of HRM size can be used as a surrogate for MNV size and enables automated, precise and reproducible quantification of HRM/MNV over time.

We demonstrate that automated measurements of hyperreflective material (HRM) size correlate well with manual MNV size annotations over time.

AI-based automated measurements of HRM size can be used as a surrogate for MNV size and enables automated, precise and reproducible quantification of HRM/MNV over time.

Figures