Replication and Refinement of an Algorithm for Automated Drusen Segmentation on Optical Coherence Tomography

Artificial Intelligence in Cataract Surgery: A Systematic Review

Purpose

The purpose of this study was to assess the current use and reliability of artificial intelligence (AI)-based algorithms for analyzing cataract surgery videos.

Methods

A systematic review of the literature about intra-operative analysis of cataract surgery videos with machine learning techniques was performed. Cataract diagnosis and detection algorithms were excluded. Resulting algorithms were compared, descriptively analyzed, and metrics summarized or visually reported. The reproducibility and reliability of the methods and results were assessed using a modified version of the Medical Image Computing and Computer-Assisted (MICCAI) checklist.

Results

Thirty-eight of the 550 screened studies were included, 20 addressed the challenge of instrument detection or tracking, 9 focused on phase discrimination, and 8 predicted skill and complications. Instrument detection achieves an area under the receiver operator characteristic curve (ROC AUC) between 0.976 and 0.998, instrument tracking an mAP between 0.685 and 0.929, phase recognition an ROC AUC between 0.773 and 0.990, and complications or surgical skill performs with an ROC AUC between 0.570 and 0.970.

Conclusions

The studies showed a wide variation in quality and pose a challenge regarding replication due to a small number of public datasets (none for manual small incision cataract surgery) and seldom published source code. There is no standard for reported outcome metrics and validation of the models on external datasets is rare making comparisons difficult. The data suggests that tracking of instruments and phase detection work well but surgical skill and complication recognition remains a challenge for deep learning.

Translational Relevance

This overview of cataract surgery analysis with AI models provides translational value for improving training of the clinician by identifying successes and challenges.

Accurate drusen segmentation in optical coherence tomography via order-constrained regression of retinal layer heights

Drusen are an important biomarker for age-related macular degeneration (AMD). Their accurate segmentation based on optical coherence tomography (OCT) is therefore relevant to the detection, staging, and treatment of disease. Since manual OCT segmentation is resource-consuming and has low reproducibility, automatic techniques are required. In this work, we introduce a novel deep learning based architecture that directly predicts the position of layers in OCT and guarantees their correct order, achieving state-of-the-art results for retinal layer segmentation. In particular, the average absolute distance between our model's prediction and the ground truth layer segmentation in an AMD dataset is 0.63, 0.85, and 0.44 pixel for Bruch's membrane (BM), retinal pigment epithelium (RPE) and ellipsoid zone (EZ), respectively. Based on layer positions, we further quantify drusen load with excellent accuracy, achieving 0.994 and 0.988 Pearson correlation between drusen volumes estimated by our method and two human readers, and increasing the Dice score to 0.71 ± 0.16 (from 0.60 ± 0.23) and 0.62 ± 0.23 (from 0.53 ± 0.25), respectively, compared to a previous state-of-the-art method. Given its reproducible, accurate, and scalable results, our method can be used for the large-scale analysis of OCT data.

Comparability of automated drusen volume measurements in age-related macular degeneration: a MACUSTAR study report

Drusen are hallmarks of early and intermediate age-related macular degeneration (AMD) but their quantification remains a challenge. We compared automated drusen volume measurements between different OCT devices. We included 380 eyes from 200 individuals with bilateral intermediate (iAMD, n = 126), early (eAMD, n = 25) or no AMD (n = 49) from the MACUSTAR study. We assessed OCT scans from Cirrus (200 × 200 macular cube, 6 × 6 mm; Zeiss Meditec, CA) and Spectralis (20° × 20°, 25 B-scans; 30° × 25°, 241 B-scans; Heidelberg Engineering, Germany) devices. Sensitivity and specificity for drusen detection and differences between modalities were assessed with intra-class correlation coefficients (ICCs) and mean difference in a 5 mm diameter fovea-centered circle. Specificity was > 90% in the three modalities. In eAMD, we observed highest sensitivity in the denser Spectralis scan (68.1). The two different Spectralis modalities showed a significantly higher agreement in quantifying drusen volume in iAMD (ICC 0.993 [0.991-0.994]) than the dense Spectralis with Cirrus scan (ICC 0.807 [0.757-0.847]). Formulae for drusen volume conversion in iAMD between the two devices are provided. Automated drusen volume measures are not interchangeable between devices and softwares and need to be interpreted with the used imaging devices and software in mind. Accounting for systematic difference between methods increases comparability and conversion formulae are provided. Less dense scans did not affect drusen volume measurements in iAMD but decreased sensitivity for medium drusen in eAMD.Trial registration: ClinicalTrials.gov NCT03349801. Registered on 22 November 2017.

Validation of an Automated Quantification of Relative Ellipsoid Zone Reflectivity on Spectral Domain-Optical Coherence Tomography Images

Purpose

Relative ellipsoid zone reflectivity (rEZR) represents a potential biomarker of photoreceptor health on spectral-domain optical coherence tomography (SD-OCT). Because manual quantification of rEZR is laborious and lacks of spatial resolution, automated quantification of the rEZR would be beneficial. The purpose of this study was to evaluate the reliability and reproducibility of an automated rEZR quantification method.

Methods

The rEZR was acquired using a manual and an automated approach in eyes with age-related macular degeneration (AMD) and healthy controls. The rEZR obtained from both methods was compared and the agreement between the methods and their reproducibility assessed.

Results

Forty eyes of 40 participants with a mean (± standard deviation) age of 65.2 ± 7.8 years were included. Both the manual and automated method showed that control eyes exhibit a greater rEZR than AMD eyes (P < 0.001). Overall, the limits of agreement between the manual and automated method were -7.5 to 7.3 arbitrary units (AU) and 95% of the data points had a difference in the rEZR between the methods of ±8.2%. An expected perfect reproducibility was observed for the automated method, whereas the manual method had a coefficient of repeatability of 6.3 arbitrary units.

Conclusions

The automated quantification of rEZR method is reliable and reproducible. Further studies of the rEZR as a novel biomarker for AMD severity and progression are warranted.

Translational Relevance

Automated quantification of SD-OCT-based rEZR allows for its comprehensive and longitudinal characterization evaluating its relevance as an in vivo biomarker of photoreceptor function and its prognostic value for AMD progression.