A Hybrid Model Composed of Two Convolutional Neural Networks (CNNs) for Automatic Retinal Layer Segmentation of OCT Images in Retinitis Pigmentosa (RP)

Deep Learning-Assisted Measurements of Photoreceptor Ellipsoid Zone Area and Outer Segment Volume as Biomarkers for Retinitis Pigmentosa

The manual segmentation of retinal layers from OCT scan images is time-consuming and costly. The deep learning approach has potential for the automatic delineation of retinal layers to significantly reduce the burden of human graders. In this study, we compared deep learning model (DLM) segmentation with manual correction (DLM-MC) to conventional manual grading (MG) for the measurements of the photoreceptor ellipsoid zone (EZ) area and outer segment (OS) volume in retinitis pigmentosa (RP) to assess whether DLM-MC can be a new gold standard for retinal layer segmentation and for the measurement of retinal layer metrics. Ninety-six high-speed 9 mm 31-line volume scans obtained from 48 patients with RPGR-associated XLRP were selected based on the following criteria: the presence of an EZ band within the scan limit and a detectable EZ in at least three B-scans in a volume scan. All the B-scan images in each volume scan were manually segmented for the EZ and proximal retinal pigment epithelium (pRPE) by two experienced human graders to serve as the ground truth for comparison. The test volume scans were also segmented by a DLM and then manually corrected for EZ and pRPE by the same two graders to obtain DLM-MC segmentation. The EZ area and OS volume were determined by interpolating the discrete two-dimensional B-scan EZ-pRPE layer over the scan area. Dice similarity, Bland-Altman analysis, correlation, and linear regression analyses were conducted to assess the agreement between DLM-MC and MG for the EZ area and OS volume measurements. For the EZ area, the overall mean dice score (SD) between DLM-MC and MG was 0.8524 (0.0821), which was comparable to 0.8417 (0.1111) between two MGs. For the EZ area > 1 mm2, the average dice score increased to 0.8799 (0.0614). When comparing DLM-MC to MG, the Bland-Altman plots revealed a mean difference (SE) of 0.0132 (0.0953) mm2 and a coefficient of repeatability (CoR) of 1.8303 mm2 for the EZ area and a mean difference (SE) of 0.0080 (0.0020) mm3 and a CoR of 0.0381 mm3 for the OS volume. The correlation coefficients (95% CI) were 0.9928 (0.9892-0.9952) and 0.9938 (0.9906-0.9958) for the EZ area and OS volume, respectively. The linear regression slopes (95% CI) were 0.9598 (0.9399-0.9797) and 1.0104 (0.9909-1.0298), respectively. The results from this study suggest that the manual correction of deep learning model segmentation can generate EZ area and OS volume measurements in excellent agreement with those of conventional manual grading in RP. Because DLM-MC is more efficient for retinal layer segmentation from OCT scan images, it has the potential to reduce the burden of human graders in obtaining quantitative measurements of biomarkers for assessing disease progression and treatment outcomes in RP.

Deep Learning-Facilitated Study of the Rate of Change in Photoreceptor Outer Segment Metrics in RPGR-Related X-Linked Retinitis Pigmentosa

Purpose

The aim of this retrospective cohort study was to obtain three-dimensional (3D) photoreceptor outer segment (OS) metrics measurements with the assistance of a deep learning model (DLM) and to evaluate the longitudinal change in OS metrics and associated factors in retinitis pigmentosa GTPase regulator (RPGR) X-linked retinitis pigmentosa (XLRP).

Methods

The study included 34 male patients with RPGR-associated XLRP who had preserved ellipsoid zone (EZ) within their spectral-domain optical coherence tomography volume scans and an approximate 2-year or longer follow-up. Volume scans were segmented using a DLM with manual correction for EZ and apical retinal pigment epithelium (RPE). OS metrics were measured from 3D EZ-RPE layers of volume scans. Linear mixed-effects models were used to calculate the rate of change in OS metrics and the associated factors, including baseline age, baseline OS metrics, and follow-up duration.

Results

The mean (standard deviation) of progression rates were -0.28 (0.43) µm/y, -0.73 (0.61) mm2/y, and -0.014 (0.012) mm3/y for OS thickness, EZ area, and OS volume, respectively. In multivariable analysis, the progression rates of EZ area and OS volume were strongly associated with their baseline values, with faster decline in eyes with larger baseline values (P ≤ 0.003), and nonlinearly associated with the baseline age (P ≤ 0.003). OS thickness decline was not associated with its baseline value (P = 0.32).

Conclusions

These results provide evidence to support using OS metrics as biomarkers to assess the progression of XLRP and as the outcome measures of clinical trials. Given that their progression rates are dependent on their baseline values, the baseline EZ area and OS volume should be considered in the design and statistical analysis of future clinical trials. Deep learning may provide a useful tool to reduce the burden of human graders to analyze OCT scan images and to facilitate the assessment of disease progression and treatment trials for retinitis pigmentosa.

Deep learning: applications in retinal and optic nerve diseases

Deep learning (DL) represents a paradigm-shifting, burgeoning field of research with emerging clinical applications in optometry. Unlike traditional programming, which relies on human-set specific rules, DL works by exposing the algorithm to a large amount of annotated data and allowing the software to develop its own set of rules (i.e. learn) by adjusting the parameters inside the model (network) during a training process in order to complete the task on its own. One major limitation of traditional programming is that, with complex tasks, it may require an extensive set of rules to accurately complete the assignment. Additionally, traditional programming can be susceptible to human bias from programmer experience. With the dramatic increase in the amount and the complexity of clinical data, DL has been utilised to automate data analysis and thus to assist clinicians in patient management. This review will present the latest advances in DL, for managing posterior eye diseases as well as DL-based solutions for patients with vision loss.

Performance of Deep Learning Models in Automatic Measurement of Ellipsoid Zone Area on Baseline Optical Coherence Tomography (OCT) Images From the Rate of Progression of USH2A-Related Retinal Degeneration (RUSH2A) Study

Purpose

Previously, we have shown the capability of a hybrid deep learning (DL) model that combines a U-Net and a sliding-window (SW) convolutional neural network (CNN) for automatic segmentation of retinal layers from OCT scan images in retinitis pigmentosa (RP). We found that one of the shortcomings of the hybrid model is that it tends to underestimate ellipsoid zone (EZ) width or area, especially when EZ extends toward or beyond the edge of the macula. In this study, we trained the model with additional data which included more OCT scans having extended EZ. We evaluated its performance in automatic measurement of EZ area on SD-OCT volume scans obtained from the participants of the RUSH2A natural history study by comparing the model’s performance to the reading center’s manual grading.

Materials and Methods

De-identified Spectralis high-resolution 9-mm 121-line macular volume scans as well as their EZ area measurements by a reading center were transferred from the management center of the RUSH2A study under the data transfer and processing agreement. A total of 86 baseline volume scans from 86 participants of the RUSH2A study were included to evaluate two hybrid models: the original RP240 model trained on 480 mid-line B-scans from 220 patients with retinitis pigmentosa (RP) and 20 participants with normal vision from a single site, and the new RP340 model trained on a revised RP340 dataset which included RP240 dataset plus an additional 200 mid-line B-scans from another 100 patients with RP. There was no overlap of patients between training and evaluation datasets. EZ and apical RPE in each B-scan image were automatically segmented by the hybrid model. EZ areas were determined by interpolating the discrete 2-dimensional B-scan EZ-RPE layer over the scan area. Dice similarity, correlation, linear regression, and Bland-Altman analyses were conducted to assess the agreement between the EZ areas measured by the hybrid model and by the reading center.

Results

For EZ area > 1 mm2, average dice coefficients ± SD between the EZ band segmentations determined by the DL model and the manual grading were 0.835 ± 0.132 and 0.867 ± 0.105 for RP240 and RP340 hybrid models, respectively (p < 0.0005; n = 51). When compared to the manual grading, correlation coefficients (95% CI) were 0.991 (0.987–0.994) and 0.994 (0.991–0.996) for RP240 and RP340 hybrid models, respectively. Linear regression slopes (95% CI) were 0.918 (0.896–0.940) and 0.995 (0.975–1.014), respectively. Bland-Altman analysis revealed a mean difference ± SD of -0.137 ± 1.131 mm2 and 0.082 ± 0.825 mm2, respectively.

Conclusion

Additional training data improved the hybrid model’s performance, especially reducing the bias and narrowing the range of the 95% limit of agreement when compared to manual grading. The close agreement of DL models to manual grading suggests that DL may provide effective tools to significantly reduce the burden of reading centers to analyze OCT scan images. In addition to EZ area, our DL models can also provide the measurements of photoreceptor outer segment volume and thickness to further help assess disease progression and to facilitate the study of structure and function relationship in RP.