Dataset Information

Deep Learning-Based Automatic Detection of Ellipsoid Zone Loss in Spectral-Domain OCT for Hydroxychloroquine Retinal Toxicity Screening.

ABSTRACT:

Purpose

Retinal toxicity resulting from hydroxychloroquine use manifests photoreceptor loss and disruption of the ellipsoid zone (EZ) reflectivity band detectable on spectral-domain (SD) OCT imaging. This study investigated whether an automatic deep learning-based algorithm can detect and quantitate EZ loss on SD OCT images with an accuracy comparable with that of human annotations.

Design

Retrospective analysis of data acquired in a prospective, single-center, case-control study.

Participants

Eighty-five patients (168 eyes) who were long-term hydroxychloroquine users (average exposure time, 14 ± 7.2 years).

Methods

A mask region-based convolutional neural network (M-RCNN) was implemented and trained on individual OCT B-scans. Scan-by-scan detections were aggregated to produce an en face map of EZ loss per 3-dimensional SD OCT volume image. To improve the accuracy and robustness of the EZ loss map, a dual network architecture was proposed that learns to detect EZ loss in parallel using horizontal (horizontal mask region-based convolutional neural network [M-RCNN_H]) and vertical (vertical mask region-based convolutional neural network [M-RCNN_V]) B-scans independently. To quantify accuracy, 10-fold cross-validation was performed.

Main outcome measures

Precision, recall, intersection over union (IOU), F1-score metrics, and measured total EZ loss area were compared against human grader annotations and with the determination of toxicity based on the recommended screening guidelines.

Results

The combined projection network demonstrated the best overall performance: precision, 0.90 ± 0.09; recall, 0.88 ± 0.08; and F1 score, 0.89 ± 0.07. The combined model performed superiorly to the M-RCNN_H only model (precision, 0.79 ± 0.17; recall, 0.96 ± 0.04; IOU, 0.78 ± 0.15; and F1 score, 0.86 ± 0.12) and M-RCNN_V only model (precision, 0.71 ± 0.21; recall, 0.94 ± 0.06; IOU, 0.69 ± 0.21; and F1 score, 0.79 ± 0.16). The accuracy was comparable with the variability of human experts: precision, 0.85 ± 0.09; recall, 0.98 ± 0.01; IOU, 0.82 ± 0.12; and F1 score, 0.91 ± 0.06. Automatically generated en face EZ loss maps provide quantitative SD OCT metrics for accurate toxicity determination combined with other functional testing.

Conclusions

The algorithm can provide a fast, objective, automatic method for measuring areas with EZ loss and can serve as a quantitative assistance tool to screen patients for the presence and extent of toxicity.

SUBMITTER: De Silva T

PROVIDER: S-EPMC9560656 | biostudies-literature | 2021 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep Learning-Based Automatic Detection of Ellipsoid Zone Loss in Spectral-Domain OCT for Hydroxychloroquine Retinal Toxicity Screening.

De Silva Tharindu T Jayakar Gopal G Grisso Peyton P Hotaling Nathan N Chew Emily Y EY Cukras Catherine A CA

Ophthalmology science 20210925 4

<h4>Purpose</h4>Retinal toxicity resulting from hydroxychloroquine use manifests photoreceptor loss and disruption of the ellipsoid zone (EZ) reflectivity band detectable on spectral-domain (SD) OCT imaging. This study investigated whether an automatic deep learning-based algorithm can detect and quantitate EZ loss on SD OCT images with an accuracy comparable with that of human annotations.<h4>Design</h4>Retrospective analysis of data acquired in a prospective, single-center, case-control study. ...[more]

PMID: 36246938

Similar Datasets

Project description:New methods are needed to quantify the change in the outer retinal structures in retinitis pigmentosa (RP).To implement an alternate method for tracking ellipsoid zone (EZ) changes in RP by quantifying the EZ area on en face spectral domain-optical coherence tomographic (SD-OCT) images.Data for this observational case study were collected at the Department of Ophthalmology, University of California, Los Angeles, from May 1 to July 30, 2015, and included SD-OCT images of a subset of patients from the Trial of Oral Valproic Acid for Retinitis Pigmentosa. To be eligible for the en face OCT subanalysis, the preserved EZ area was required to be limited to the SD-OCT scanning field. Cases in which the EZ band extended to the margins of any B-scan or the most superior or inferior B-scan were excluded. The SD-OCT images of all included cases were imported into the manufacturer's software to generate en face images at the level of the EZ. Two certified SD-OCT graders independently delineated the boundaries of the preserved EZ on the en face images.Comparison of the 2 masked gradings of the generated en face images of patients with RP for agreement between the graders and the validity of the method.Of the 43 available patients with volume SD-OCT data, 45 eyes of 24 patients met the eligibility criteria and were included in this subanalysis. Every patient had 2 visits that were 1 year apart, which included a total of 90 en face OCT images that were graded. The mean (SD) absolute difference and percentage difference between the 2 independent graders for each visit were 0.08 (0.10) mm2 and 4.5% (5.9%), respectively. The EZ area determined by the 2 graders showed excellent agreement with an intraclass correlation coefficient of 0.996 (95% CI, 0.995-0.997; P?<?.001).Quantification of the preserved EZ area on en face SD-OCT images of patients with RP is a valid and reproducible method. En face SD-OCT quantification may be a useful tool for monitoring the EZ changes of patients with advanced RP and a useful outcome measurement variable in therapeutic trials.

Project description:PURPOSE:To compare the diagnostic ability of wide-field swept-source optical coherence tomography (SS-OCT) retinal nerve fiber layer (RNFL) maps with spectral-domain OCT (SD-OCT) maps for detection of preperimetric (PPG) and early glaucoma (EG). PATIENTS AND METHODS:One hundred and forty-six eyes, including 37 healthy eyes, 38 eyes with PPG, and 71 eyes with EG, were analyzed. The patients underwent both SD-OCT (Cirrus HD-OCT; Carl Zeiss Meditec, Dublin, CA, USA) and wide-field SS-OCT scanning (DRI-OCT-1 Atlantis; Topcon, Tokyo, Japan). By SD-OCT, circumpapillary RNFL and macular ganglion cell analyses were performed. SS-OCT provides a wide-field RNFL thickness map and a SuperPixel map, which are composed of an RNFL deviation map of the peripapillary area and a deviation map of the composition of the ganglion cell layer with the inner plexiform layer and RNFL [GC-IPL+RNFL] in the macular area. The ability to discriminate PPG and EG from healthy eyes was assessed according to sensitivity, specificity and area under the receiver operating characteristic curve for parameters and criteria provided by SD-OCT and wide-field SS-OCT scanning. RESULTS:The wide-field RNFL thickness map obtained by SS-OCT showed the highest sensitivity to PPG and EG (92.1 and 97.2%, respectively) as compared with the other, SD-OCT criteria. The wide-field RNFL thickness map showed PPG-diagnostic performance comparable to the SD-OCT RNFL thickness and GC-IPL deviation maps (p = 0.453 and 0.180), and PPG-diagnostic performance superior to the SD-OCT RNFL deviation and GC-IPL thickness maps (p = 0.003 and 0.039). In EG, the wide-field RNFL thickness and SuperPixel maps showed diagnostic performance comparable to the SD-OCT thickness and deviation maps (p = 0.065 to 0.100), except for the GC-IPL thickness map (p = 0.004). CONCLUSIONS:The wide-field SS-OCT RNFL thickness maps showed a diagnostic ability for distinguishing PPG and EG from healthy eyes that was similar to that of SD-OCT. In the clinical setting, these maps can be effective for detection of early-glaucomatous changes.

Project description:PurposeBedside examination of premature infants at risk for retinopathy of prematurity (ROP) is predominantly performed with ophthalmoscopic en face viewing of the retina. While postmortem retinal microstructures have been studied at the vascular-avascular junction, a critical location for pathogenesis of ROP, to date this has not been possible in vivo. Here we present bedside, non-sedated in vivo cross-sectional imaging and analysis of retinal microstructures at the vascular-avascular junction in infants with ROP using handheld spectral-domain optical coherence tomography (SDOCT).DesignProspective observational study.ParticipantsEleven preterm infants consented for research imaging during ROP screening examinations.MethodsWe imaged the vascular-avascular junction in the temporal retina using a SDOCT system (Envisu, Bioptigen Inc., NC) in 18 eyes from 11 preterm infants with zone I or II, stage 0 through 4 ROP. B-scan and en face images were analyzed and compared to historical light micrographs.Main outcome measuresSDOCT morphology at the vascular-avascular junction.ResultsMultiple bedside SDOCT findings at the vascular-avascular junction were comparable to historic light micrographs: thickened inner retinal ridge structure in stage 2 ROP was comparable to thickened vanguard and rear guard cells in micrographs; vascular tufts on the posterior retinal surface in stage 2 ROP, broad arcs of neovascularization above the retina in stage 3 ROP, and splitting of inner retinal layers into clefts on either side of neovascularization mimicked findings of historic light micrographs. A unique findings was thickening of the avascular inner retinal band adjacent to neovascularization. On SDOCT imaging over several weeks, neovascularization and retinal clefts diminished after intravitreal bevacizumab therapy.ConclusionsRetinal morphology at the vascular-avascular junction imaged with handheld SDOCT is consistent with known histopathology, and provide the advantage of monitoring change in vivo over time. These unique findings provide new insights into preterm retinal neurovascular development in ROP.

Dataset Information

Deep Learning-Based Automatic Detection of Ellipsoid Zone Loss in Spectral-Domain OCT for Hydroxychloroquine Retinal Toxicity Screening.

Purpose

Design

Participants

Methods

Main outcome measures

Results

Conclusions

Publications

Deep Learning-Based Automatic Detection of Ellipsoid Zone Loss in Spectral-Domain OCT for Hydroxychloroquine Retinal Toxicity Screening.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets