Optical Coherence Tomography Analysis Based Prediction of Humphrey 24-2 Visual Field Thresholds in Patients With Glaucoma

Abstract

PurposeA pilot study showed that prediction of individual Humphrey 24-2 visual field (HVF 24-2) sensitivity thresholds from optical coherence tomography (OCT) image analysis is possible. We evaluate performance of an improved approach as well as 3 other predictive algorithms on a new, fully independent set of glaucoma subjects.MethodsSubjects underwent HVF 24-2 and 9-field OCT (Heidelberg Spectralis) testing. Nerve fiber (NFL), and ganglion cell and inner plexiform (GCL+IPL) layers were cosegmented and partitioned into 52 sectors matching HVF 24-2 test locations. The Wilcoxon rank sum test was applied to test correlation R, root mean square error (RMSE), and limits of agreement (LoA) between actual and predicted thresholds for four prediction models. The training data consisted of the 9-field OCT and HVF 24-2 thresholds of 111 glaucoma patients from our pilot study.ResultsWe studied 112 subjects (112 eyes) with early, moderate, or advanced primary and secondary open angle glaucoma. Subjects with less than 9 scans (15/112) or insufficient quality segmentations (11/97) were excluded. Retinal ganglion cell axonal complex (RGC-AC) optimized had superior average R = 0.74 (95% confidence interval [CI], 0.67–0.76) and RMSE = 5.42 (95% CI, 5.1–5.7) dB, which was significantly better (P < 0.05/3) than the other three models: Naïve (R = 0.49; 95% CI, 0.44–0.54; RMSE = 7.24 dB; 95% CI, 6.6–7.8 dB), Garway-Heath (R = 0.66; 95% CI, 0.60–0.68; RMSE = 6.07 dB; 95% CI, 5.7–6.5 dB), and Donut (R = 0.67; 95% CI, 0.61–0.69; RMSE = 6.08 dB, 95% CI, 5.8–6.4 dB).ConclusionsThe proposed RGC-AC optimized predictive algorithm based on 9-field OCT image analysis and the RGC-AC concept is superior to previous methods and its performance is close to the reproducibility of HVF 24-2.

Development of a Spatial Model of Age-Related Change in the Macular Ganglion Cell Layer to Predict Function From Structural Changes

“…Similarly, Leite and associates 9 grouped RNFL thickness and VF sensitivity measurements according to the structure-function map proposed by Garway-Heath and associates 57 and demonstrated that 87%-88% of their data points fell within the 95% prediction interval of the resulting model. On the other hand, models proposed by Guo and associates 48 to predict VF sensitivity from RNFL and GC-IPL measurements performed relatively poorly, with 95% prediction intervals exceeding 20 dB for VF sensitivities of up to 26 dB. The strategies developed in the present study may form the basis of future technologies to facilitate earlier detection of glaucoma.…”

“…Although other models describing the structurefunction relationship at the central retina have been previously reported, 9,10,33,47,48 not only were these models based on assumptions of standard anatomical RNFL projections which may vary between individuals, [49][50][51] the VF paradigms used in these studies sample the macula sparsely and typically utilized GIII stimuli that do not account for variable spatial summation characteristics within the macula. 7 Additionally, models investigating the structure-function relationship of the macular GCL were based on global measurement indices and spatially oriented based on a semiarbitrary distribution of OCT-derived macular GCL measurements, rather than incorporating structural or functional considerations.…”

Artificial Intelligence Mapping of Structure to Function in Glaucoma

“…Several attempts used previous clinical knowledge to improve their predictions. 13,15,16,[26][27][28][29][30][31][32] As an example, Guo et al 13 reported a root mean square error of 5.42 dB when predicting pointwise SAP sensitivity thresholds using RNFL and ganglion cell layer measurements as inputs. In their model, the use of selected regions presented better results than a naive approach that used all peripapillary RNFL.…”

Three Dimensional Pulse Coupled Neural Network Based on Hybrid Optimization Algorithm for Oil Pollution Image Segmentation

“…We statistically analyze the experimental results to better observe the differences between algorithms. We use Wilcoxon rank sum test [70], a nonparametric statistical test that checks whether one of two independent samples is larger than the other. We calculate the p-value of FSIM of HSOA algorithm and WOA, FPA, PSO, and BA algorithm.…”