Deep learning detection of retinal detachment: Optical coherence tomography staging and estimation of duration of macular detachment

Abstract

Objective: To test the applicability of deep learning models for detecting and staging rhegmatogenous retinal detachment (RRD) based on morphological features using two- and three-dimensional optical coherence tomography (OCT) scans.

Design: Retrospective study using deep learning-based image classification analysis of 2D and 3D OCT scans combined with clinical baseline data.

Subjects: Adult patients presenting to the University Medical Center Hamburg-Eppendorf in Germany.

Methods: A total of 252 eyes with RRD and 770 control eyes were included. All OCT scans and clinical baseline data were reviewed and graded. Binary and multiclass classification approaches were applied.

Main outcome measures: Area under the curve (AUC) and precision-recall area under the curve (PR AUC) for detection, stage classification and duration estimation of RRD.

Results: We employed both statistical and deep learning-based approaches using 2D and 3D OCT data. We evaluated an automated 3D OCT classification model in a multiclass analysis to distinguish RRD scans by macula status from a non-RRD group with macula-on cases (PR AUC = 0.66 ± 0.12, AUC = 0.96 ± 0.01) vs. macula-off cases (PR AUC = 0.86 ± 0.07, 0.98 ± 0.01) against non-RRD cases (PR AUC = 1.00, AUC = 1.00) Furthermore, the 3D model was able to classify the duration of macula-off status (< 3 days) with a PR AUC of 0.68 ± 0.2 and a AUC of 0.97 ± 0.2 when compared to a mixed group including longer macular-off, macular-on and non RRD cases. Lastly, manually graded RRD Stages were correlated with best corrected visual acuity (BCVA), as well as macula-off Duration and classified via a 2D model. A 2D model used for RRD stage classification achieved its best performance for stage 4, with a PR AUC of 0.56 ± 0.11 and an AUC of 0.94 ± 0.02.

Conclusion: The machine learning models demonstrated strong performance in classifying RRD stages, macula status and duration based on OCT imaging. These findings highlight the potential of deep learning methods to support clinical decision-making and surgical planning in RRD management.

Fig 1. Multiclass classification of non-RRD, macula-on RRD and macula-off RRD scans.

PR AUC values of 0.66 for macula-on and 0.86 for macula-off indicate moderate performance with some variability. ROC curves show high classification performance, with AUC values exceeding 0.95 for all classes demonstrating strong sensitivity and specificity.

Fig 2. Binary classification distinguishing recent macula-off RRD (≤ 3 days) from other cases (non-RRD, macula-on and longer (> 3 days) macula-off cases).

The PR AUC of 0.68 ± 0.2 indicates moderate performance with some variability. The ROC curve shows strong classification performance, with an AUC of 0.97 ± 0.2, reflecting high sensitivity and specificity.

Fig 3. Multiclass classification performance across different RRD stages and non-RRD controls.

The models shows variability in performance across the six classes. The non-RRD class achieved the highest PR AUC (1.00), while Stage 2 showed the lowest performance (0.56 ± 0.11). The highest PR AUC among the RRD stages was observed for stage 3b (0.56 ± 0.11). AUC values ranged from 0.90 to 1.00 across all classes, reflecting overall high sensitivity and specificity.

Fig 4. Grad-CAM visualizations highlighting model attention for RRD stage classification.

Two-dimensional GRAD-CAM feature map illustrate the estimated regions used by the model to classify RRD stages. On the left side is the true stage depicted and, on the right, the correctly estimated stage. Panels A-C show original OCT scans labeled as Stage 1, Stage 3 and Stage 4, respectively. Panels D-F display the corresponding correctly predicted scans for the same stages.

Fig 5. BCVA (LogMAR) at initial presentation across OCT-based RRD stages.

The boxplot shows BCVA values, measured in LogMAR, at the first clinical assessment across different manually graded OCT stages of RRD. A trend toward poorer visual acuity (higher LogMAR values) is observed in more advanced stages (3a, 3b, 4, and 5).

Fig 6. BCVA (LogMAR) at final follow-up across OCT-based RRD stages.

The boxplot shows the distribution of BCVA (LogMAR) values, at the time of the last clinical follow-up across the different manually graded OCT stages. Visual outcomes remain worse in higher stages, indicating that initial OCT grading may correlate with long-term visual prognosis.

Fig 7. Duration of macula-off status across OCT-based RRD stages.

The boxplot illustrates the duration of macular detachment (in days) across different manually graded OCT stages of RRD. A trend toward longer macula-off duration is observed in more advanced stages, particularly Stage 4 and Stage 5.