Automated Volumetric Segmentation of Microaneurysms on OCT Using Artificial Intelligence

To develop and validate a deep learning-based method for the automated identification and volumetric segmentation of microaneurysms (MAs) in diabetic retinopathy (DR) using OCT.

Cross-sectional study with a representative longitudinal case analysis.

A total of 125 participants were enrolled, including 20 healthy eyes, 27 with mild nonproliferative DR (NPDR), 30 with moderate NPDR, 30 with severe NPDR, and 18 with proliferative DR.

We obtained multiple repeated 3 × 3-mm scans from each participant using a commercial 120-kHz spectral-domain OCT system (Solix) which were registered and averaged to generate high-definition volumes. We developed an end-to-end 3-dimensional convolutional neural network, incorporating an encoder-decoder architecture with residual blocks, to segment MAs volumetrically. The input to the network consists of the original OCT volume concatenated with its reflectance-inverted counterpart to enhance feature extraction. Expert graders manually delineated MAs to generate initial annotations, which were later refined into a verified ground truth through an iterative human-in-the-loop refinement process to capture MAs initially overlooked or mischaracterized. Both single-scan volumes and volumes averaged across 4-10 repeated OCT volumes were used to train and test the model. We evaluated model performance at multiple levels, including voxel-level segmentation, lesion-level detection, and eye-level diagnosis. We also analyzed the differences in MA counts across various stages of DR severity and quantified the MA number and volume distribution in different retinal layers. A longitudinal analysis of MA dynamics was performed in a case with severe NPDR and macular edema using the algorithm.

Voxel-level MA segmentation accuracy, MA quantification categorized by retinopathy severity, and longitudinal analysis of MA dynamics in OCT volumes.

In the test data set (20 healthy, 20 DR eyes), when evaluated against the verified ground truth, the algorithm demonstrated high voxel-level accuracy, with F1 scores of 79.2% on single volumes and 86.1% on averaged volumes. Lesion-level detection reached an F1 score of 96.0% (single) and 97.1% (averaged), while scan-level diagnostic accuracy for MA presence was 97.5% (single and averaged). Microaneurysm counts significantly increased from mild to moderate NPDR (7.4 ± 1.5 vs. 12.7 ± 1.6, P = 0.014) but not between any other severity comparisons (P > 0.05). Microaneurysms were primarily localized to the inner nuclear layer and outer plexiform layer. In 1 case with severe NPDR and macular edema, longitudinal analysis tracked 11 resolved MAs and 3 new MAs post-treatment, corresponding to a reduction in fluid volume.

A deep learning-based method can accurately identify and segment MAs volumetrically on OCT, enabling quantification and characterization and potentially aiding in the diagnosis, monitoring, and management of DR.

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.