Geographic Atrophy Segmentation Using Multimodal Deep Learning

Strong versus Weak Data Labeling for Artificial Intelligence Algorithms in the Measurement of Geographic Atrophy

Purpose

To gain an understanding of data labeling requirements to train deep learning models for measurement of geographic atrophy (GA) with fundus autofluorescence (FAF) images.

Design

Evaluation of artificial intelligence (AI) algorithms.

Subjects

The Age-Related Eye Disease Study 2 (AREDS2) images were used for training and cross-validation, and GA clinical trial images were used for testing.

Methods

Training data consisted of 2 sets of FAF images; 1 with area measurements only and no indication of GA location (Weakly labeled) and the second with GA segmentation masks (Strongly labeled).

Main Outcome Measures

Bland-Altman plots and scatter plots were used to compare GA area measurement between ground truth and AI measurements. The Dice coefficient was used to compare accuracy of segmentation of the Strong model.

Results

In the cross-validation AREDS2 data set (n = 601), the mean (standard deviation [SD]) area of GA measured by human grader, Weakly labeled AI model, and Strongly labeled AI model was 6.65 (6.3) mm2, 6.83 (6.29) mm2, and 6.58 (6.24) mm2, respectively. The mean difference between ground truth and AI was 0.18 mm2 (95% confidence interval, [CI], -7.57 to 7.92) for the Weakly labeled model and -0.07 mm2 (95% CI, -1.61 to 1.47) for the Strongly labeled model. With GlaxoSmithKline testing data (n = 156), the mean (SD) GA area was 9.79 (5.6) mm2, 8.82 (4.61) mm2, and 9.55 (5.66) mm2 for human grader, Strongly labeled AI model, and Weakly labeled AI model, respectively. The mean difference between ground truth and AI for the 2 models was -0.97 mm2 (95% CI, -4.36 to 2.41) and -0.24 mm2 (95% CI, -4.98 to 4.49), respectively. The Dice coefficient was 0.99 for intergrader agreement, 0.89 for the cross-validation data, and 0.92 for the testing data.

Conclusions

Deep learning models can achieve reasonable accuracy even with Weakly labeled data. Training methods that integrate large volumes of Weakly labeled images with small number of Strongly labeled images offer a promising solution to overcome the burden of cost and time for data labeling.

Financial Disclosures

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

AI-based support for optical coherence tomography in age-related macular degeneration

Artificial intelligence (AI) has emerged as a transformative technology across various fields, and its applications in the medical domain, particularly in ophthalmology, has gained significant attention. The vast amount of high-resolution image data, such as optical coherence tomography (OCT) images, has been a driving force behind AI growth in this field. Age-related macular degeneration (AMD) is one of the leading causes for blindness in the world, affecting approximately 196 million people worldwide in 2020. Multimodal imaging has been for a long time the gold standard for diagnosing patients with AMD, however, currently treatment and follow-up in routine disease management are mainly driven by OCT imaging. AI-based algorithms have by their precision, reproducibility and speed, the potential to reliably quantify biomarkers, predict disease progression and assist treatment decisions in clinical routine as well as academic studies. This review paper aims to provide a summary of the current state of AI in AMD, focusing on its applications, challenges, and prospects.

Visual Sensitivity Loss in Geographic Atrophy: Structure-Function Evaluation Using Defect-Mapping Microperimetry

Purpose

To examine the structure-function relationship in eyes with geographic atrophy (GA) using defect-mapping microperimetry, a testing strategy optimized to quantify the spatial extent of deep visual sensitivity losses.

Methods

Fifty participants with GA underwent defect-mapping microperimetry testing of the central 8°-radius region (208 locations tested once with a 10-decibel stimuli) and fundus autofluorescence imaging in one eye. The GA extent in the corresponding central 8°-radius was derived by manual annotations and image co-registration to examine the global structure-function relationship. The distance of each test location from the GA margin was also derived, and regions defined, to examine the local structure-function relationship.

Results

GA extent in the central 8° explained a substantial proportion of variance in the percentage of locations missed (nonresponse) on microperimetry at the global level (R2 = 0.90). At a local level, the probability of missing stimuli at the outer junctional zone (0-500 µm outside the GA margin) and GA margin (probability = 7% and 34%, respectively) was higher than at the outer nonlesional zone (>500 µm outside the GA margin; probability = 2%; P < 0.001 for both). The probability of missing stimuli at the inner junctional zone (0-250 µm inside the GA margin) was also lower than at the inner lesional zone (>250 µm inside the GA margin; probability = 64% and 88%; P < 0.001).

Conclusions

This study confirms the expected functional relevance of the region with GA on fundus autofluorescence imaging and underscores the potential effectiveness of defect-mapping microperimetry testing for capturing visual function changes when evaluating new GA treatments.