Dataset Information

Foveal Therapy in Blue Cone Monochromacy: Predictions of Visual Potential From Artificial Intelligence.

ABSTRACT: Novel therapeutic approaches for treating inherited retinal degenerations (IRDs) prompt a need to understand which patients with impaired vision have the anatomical potential to gain from participation in a clinical trial. We used supervised machine learning to predict foveal function from foveal structure in blue cone monochromacy (BCM), an X-linked congenital cone photoreceptor dysfunction secondary to mutations in the OPN1LW/OPN1MW gene cluster. BCM patients with either disease-associated large deletion or missense mutations were studied and results compared with those from subjects with other forms of IRD and various degrees of preserved central structure and function. A machine learning technique was used to associate foveal sensitivities and best-corrected visual acuities to foveal structure in IRD patients. Two random forest (RF) models trained on IRD data were applied to predict foveal function in BCM. A curve fitting method was also used and results compared with those of the RF models. The BCM and IRD patients had a comparable range of foveal structure. IRD patients had peak sensitivity at the fovea. Machine learning could successfully predict foveal sensitivity (FS) results from segmented or un-segmented optical coherence tomography (OCT) input. Application of machine learning predictions to BCM at the fovea showed differences between predicted and measured sensitivities, thereby defining treatment potential. The curve fitting method provided similar results. Given a measure of visual acuity (VA) and foveal outer nuclear layer thickness, the question of how many lines of acuity would represent the best efficacious result for each BCM patient could be answered. We propose that foveal vision improvement potential in BCM is predictable from retinal structure using machine learning and curve fitting approaches. This should allow estimates of maximal efficacy in patients being considered for clinical trials and also guide decisions about dosing.

SUBMITTER: Sumaroka A

PROVIDER: S-EPMC7416698 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Foveal Therapy in Blue Cone Monochromacy: Predictions of Visual Potential From Artificial Intelligence.

Sumaroka Alexander A Cideciyan Artur V AV Sheplock Rebecca R Wu Vivian V Kohl Susanne S Wissinger Bernd B Jacobson Samuel G SG

Frontiers in neuroscience 20200803

Novel therapeutic approaches for treating inherited retinal degenerations (IRDs) prompt a need to understand which patients with impaired vision have the anatomical potential to gain from participation in a clinical trial. We used supervised machine learning to predict foveal function from foveal structure in blue cone monochromacy (BCM), an X-linked congenital cone photoreceptor dysfunction secondary to mutations in the <i>OPN1LW/OPN1MW</i> gene cluster. BCM patients with either disease-associa ...[more]

PMID: 32848570

Similar Datasets

Project description:BackgroundBlue Cone Monochromacy (BCM) is an X-linked retinopathy caused by mutations in the OPN1LW / OPN1MW gene cluster, encoding long (L)- and middle (M)-wavelength sensitive cone opsins. Recent evidence shows sufficient structural integrity of cone photoreceptors in BCM to warrant consideration of a gene therapy approach to the disease. In the present study, the vision in BCM is examined, specifically seeking clinically-feasible outcomes for a future clinical trial.MethodsBCM patients (n = 25, ages 5-72) were studied with kinetic and static chromatic perimetry, full-field sensitivity testing, and eye movement recordings. Vision at the fovea and parafovea was probed with chromatic microperimetry.ResultsKinetic fields with a Goldmann size V target were generally full. Short-wavelength (S-) sensitive cone function was normal or near normal in most patients. Light-adapted perimetry results on conventional background lights were abnormally reduced; 600-nm stimuli were seen by rods whereas white stimuli were seen by both rods and S-cones. Under dark-adapted conditions, 500-nm stimuli were seen by rods in both BCM and normals. Spectral sensitivity functions in the superior retina showed retained rod and S-cone functions in BCM under dark-adapted and light-adapted conditions. In the fovea, normal subjects showed L/M-cone mediation using a 650-nm stimulus under dark-adapted conditions, whereas BCM patients had reduced sensitivity driven by rod vision. Full-field red stimuli on bright blue backgrounds were seen by L/M-cones in normal subjects whereas BCM patients had abnormally reduced and rod-mediated sensitivities. Fixation location could vary from fovea to parafovea. Chromatic microperimetry demonstrated a large loss of sensitivity to red stimuli presented on a cyan adapting background at the anatomical fovea and surrounding parafovea.ConclusionsBCM rods continue to signal vision under conditions normally associated with daylight vision. Localized and retina-wide outcome measures were examined to evaluate possible improvement of L/M-cone-based vision in a clinical trial.

Project description:PurposeBlue cone monochromacy (BCM) is an X-linked congenital vision disorder characterized by complete loss or severely reduced L- and M-cone function. Patients with BCM display poor visual acuity, severely impaired color discrimination, myopia, nystagmus, and minimally detectable cone-mediated electroretinogram. Recent studies of patients with BCM with adaptive optics scanning laser ophthalmoscopy (AOSLO) showed that they have a disrupted cone mosaic with reduced numbers of cones in the fovea that is normally dominated by L- and M-cones. The remaining cones in the fovea have significantly shortened outer segments but retain sufficient structural integrity to serve as potential gene therapy targets. In this study, we tested whether exogenously expressed human L- and M-opsins can rescue M-cone function in an M-opsin knockout (Opn1mw-/- ) mouse model for BCM.MethodsAdeno-associated virus type 5 (AAV5) vectors expressing OPN1LW, OPN1MW, or C-terminal tagged OPN1LW-Myc, or OPN1MW-HA driven by a cone-specific promoter were injected subretinally into one eye of Opn1mw-/- mice, while the contralateral eye served as the uninjected control. Expression of cone pigments was determined with western blotting and their cellular localization identified with immunohistochemistry. M-cone function was analyzed with electroretinogram (ERG). Antibodies against cone phototransduction proteins were used to study cone outer segment (OS) morphology in untreated and treated Opn1mw-/- eyes.ResultsWe showed that cones in the dorsal retina of the Opn1mw-/- mouse do not form outer segments, resembling cones that lack outer segments in the human BCM fovea. We further showed that AAV5-mediated expression of either human M- or L-opsin individually or combined promotes regrowth of cone outer segments and rescues M-cone function in the treated Opn1mw-/- dorsal retina.ConclusionsExogenously expressed human opsins can regenerate cone outer segments and rescue M-cone function in Opn1mw-/- mice, thus providing a proof-of-concept gene therapy in an animal model of BCM.

Dataset Information

Foveal Therapy in Blue Cone Monochromacy: Predictions of Visual Potential From Artificial Intelligence.

Publications

Foveal Therapy in Blue Cone Monochromacy: Predictions of Visual Potential From Artificial Intelligence.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets