Prediction of causative genes in inherited retinal disorder from fundus photography and autofluorescence imaging using deep learning techniques

Applications of artificial intelligence to inherited retinal diseases: A systematic review

Artificial intelligence(AI)-based methods have been extensively used for the detection and management of various common retinal conditions, but their targeted development for inherited retinal diseases (IRD) is still nascent. In the context of limited availability of retinal subspecialists, genetic testing and genetic counseling, there is a high need for accurate and accessible diagnostic methods. The currently available AI studies, aiming for detection, classification, and prediction of IRD, remain mainly retrospective and include relatively limited numbers of patients due to their scarcity. We summarize the latest findings and clinical implications of machine-learning algorithms in IRD, highlighting the achievements and challenges of AI to assist ophthalmologists in their clinical practice.

Deep learning aided measurement of outer retinal layer metrics as biomarkers for inherited retinal degenerations: opportunities and challenges

PURPOSE OF REVIEW

The purpose of this review was to provide a summary of currently available retinal imaging and visual function testing methods for assessing inherited retinal degenerations (IRDs), with the emphasis on the application of deep learning (DL) approaches to assist the determination of structural biomarkers for IRDs.

RECENT FINDINGS

(clinical trials for IRDs; discover effective biomarkers as endpoints; DL applications in processing retinal images to detect disease-related structural changes).

SUMMARY

Assessing photoreceptor loss is a direct way to evaluate IRDs. Outer retinal layer structures, including outer nuclear layer, ellipsoid zone, photoreceptor outer segment, RPE, are potential structural biomarkers for IRDs. More work may be needed on structure and function relationship.

Advances and prospects of multi-modal ophthalmic artificial intelligence based on deep learning: a review

BACKGROUND

In recent years, ophthalmology has emerged as a new frontier in medical artificial intelligence (AI) with multi-modal AI in ophthalmology garnering significant attention across interdisciplinary research. This integration of various types and data models holds paramount importance as it enables the provision of detailed and precise information for diagnosing eye and vision diseases. By leveraging multi-modal ophthalmology AI techniques, clinicians can enhance the accuracy and efficiency of diagnoses, and thus reduce the risks associated with misdiagnosis and oversight while also enabling more precise management of eye and vision health. However, the widespread adoption of multi-modal ophthalmology poses significant challenges.

MAIN TEXT

In this review, we first summarize comprehensively the concept of modalities in the field of ophthalmology, the forms of fusion between modalities, and the progress of multi-modal ophthalmic AI technology. Finally, we discuss the challenges of current multi-modal AI technology applications in ophthalmology and future feasible research directions.

CONCLUSION

In the field of ophthalmic AI, evidence suggests that when utilizing multi-modal data, deep learning-based multi-modal AI technology exhibits excellent diagnostic efficacy in assisting the diagnosis of various ophthalmic diseases. Particularly, in the current era marked by the proliferation of large-scale models, multi-modal techniques represent the most promising and advantageous solution for addressing the diagnosis of various ophthalmic diseases from a comprehensive perspective. However, it must be acknowledged that there are still numerous challenges associated with the application of multi-modal techniques in ophthalmic AI before they can be effectively employed in the clinical setting.

Quickly diagnosing Bietti crystalline dystrophy with deep learning

Bietti crystalline dystrophy (BCD) is an autosomal recessive inherited retinal disease (IRD) and its early precise diagnosis is much challenging. This study aims to diagnose BCD and classify the clinical stage based on ultra-wide-field (UWF) color fundus photographs (CFPs) via deep learning (DL). All CFPs were labeled as BCD, retinitis pigmentosa (RP) or normal, and the BCD patients were further divided into three stages. DL models ResNeXt, Wide ResNet, and ResNeSt were developed, and model performance was evaluated using accuracy and confusion matrix. Then the diagnostic interpretability was verified by the heatmaps. The models achieved good classification results. Our study established the largest BCD database of Chinese population. We developed a quick diagnosing method for BCD and evaluated the potential efficacy of an automatic diagnosis and grading DL algorithm based on UWF fundus photography in a Chinese cohort of BCD patients.

Current Status, Hotspots, and Prospects of Artificial Intelligence in Ophthalmology: A Bibliometric Analysis (2003-2023)

PURPOSE

Artificial intelligence (AI) has gained significant attention in ophthalmology. This paper reviews, classifies, and summarizes the research literature in this field and aims to provide readers with a detailed understanding of the current status and future directions, laying a solid foundation for further research and decision-making.

METHODS

Literature was retrieved from the Web of Science database. Bibliometric analysis was performed using VOSviewer, CiteSpace, and the R package Bibliometrix.

RESULTS

The study included 3,377 publications from 4,035 institutions in 98 countries. China and the United States had the most publications. Sun Yat-sen University is a leading institution. Translational Vision Science & Technology"published the most articles, while "Ophthalmology" had the most co-citations. Among 13,145 researchers, Ting DSW had the most publications and citations. Keywords included "Deep learning," "Diabetic retinopathy," "Machine learning," and others.

CONCLUSION

The study highlights the promising prospects of AI in ophthalmology. Automated eye disease screening, particularly its core technology of retinal image segmentation and recognition, has become a research hotspot. AI is also expanding to complex areas like surgical assistance, predictive models. Multimodal AI, Generative Adversarial Networks, and ChatGPT have driven further technological innovation. However, implementing AI in ophthalmology also faces many challenges, including technical, regulatory, and ethical issues, and others. As these challenges are overcome, we anticipate more innovative applications, paving the way for more effective and safer eye disease treatments.

Quantification of Fundus Autofluorescence Features in a Molecularly Characterized Cohort of More Than 3500 Inherited Retinal Disease Patients from the United Kingdom

Purpose

To quantify relevant fundus autofluorescence (FAF) image features cross-sectionally and longitudinally in a large cohort of inherited retinal diseases (IRDs) patients.

Design

Retrospective study of imaging data (55-degree blue-FAF on Heidelberg Spectralis) from patients.

Participants

Patients with a clinical and molecularly confirmed diagnosis of IRD who have undergone FAF 55-degree imaging at Moorfields Eye Hospital (MEH) and the Royal Liverpool Hospital (RLH) between 2004 and 2019.

Methods

Five FAF features of interest were defined: vessels, optic disc, perimacular ring of increased signal (ring), relative hypo-autofluorescence (hypo-AF) and hyper-autofluorescence (hyper-AF). Features were manually annotated by six graders in a subset of patients based on a defined grading protocol to produce segmentation masks to train an AI model, AIRDetect, which was then applied to the entire MEH imaging dataset.

Main Outcome Measures

Quantitative FAF imaging features including area in mm 2 and vessel metrics, were analysed cross-sectionally by gene and age, and longitudinally to determine rate of progression. AIRDetect feature segmentation and detection were validated with Dice score and precision/recall, respectively.

Results

A total of 45,749 FAF images from 3,606 IRD patients from MEH covering 170 genes were automatically segmented using AIRDetect. Model-grader Dice scores for disc, hypo-AF, hyper-AF, ring and vessels were respectively 0.86, 0.72, 0.69, 0.68 and 0.65. The five genes with the largest hypo-AF areas were CHM , ABCC6 , ABCA4 , RDH12 , and RPE65 , with mean per-patient areas of 41.5, 30.0, 21.9, 21.4, and 15.1 mm 2 . The five genes with the largest hyper-AF areas were BEST1 , CDH23 , RDH12 , MYO7A , and NR2E3 , with mean areas of 0.49, 0.45, 0.44, 0.39, and 0.34 mm 2 respectively. The five genes with largest ring areas were CDH23 , NR2E3 , CRX , EYS and MYO7A, with mean areas of 3.63, 3.32, 2.84, 2.39, and 2.16 mm 2 . Vessel density was found to be highest in EFEMP1 , BEST1 , TIMP3 , RS1 , and PRPH2 (10.6%, 10.3%, 9.8%, 9.7%, 8.9%) and was lower in Retinitis Pigmentosa (RP) and Leber Congenital Amaurosis genes. Longitudinal analysis of decreasing ring area in four RP genes ( RPGR, USH2A, RHO, EYS ) found EYS to be the fastest progressor at -0.18 mm 2 /year.

Conclusions

We have conducted the first large-scale cross-sectional and longitudinal quantitative analysis of FAF features across a diverse range of IRDs using a novel AI approach.

Metabolomics facilitates differential diagnosis in common inherited retinal degenerations by exploring their profiles of serum metabolites

The diagnosis of inherited retinal degeneration (IRD) is challenging owing to its phenotypic and genotypic complexity. Clinical information is important before a genetic diagnosis is made. Metabolomics studies the entire picture of bioproducts, which are determined using genetic codes and biological reactions. We demonstrated that the common diagnoses of IRD, including retinitis pigmentosa (RP), cone-rod dystrophy (CRD), Stargardt disease (STGD), and Bietti's crystalline dystrophy (BCD), could be differentiated based on their metabolite heatmaps. Hundreds of metabolites were identified in the volcano plot compared with that of the control group in every IRD except BCD, considered as potential diagnosing markers. The phenotypes of CRD and STGD overlapped but could be differentiated by their metabolomic features with the assistance of a machine learning model with 100% accuracy. Moreover, EYS-, USH2A-associated, and other RP, sharing considerable similar characteristics in clinical findings, could also be diagnosed using the machine learning model with 85.7% accuracy. Further study would be needed to validate the results in an external dataset. By incorporating mass spectrometry and machine learning, a metabolomics-based diagnostic workflow for the clinical and molecular diagnoses of IRD was proposed in our study.

Distinct Clinical Effects of Two RP1L1 Hotspots in East Asian Patients With Occult Macular Dystrophy (Miyake Disease): EAOMD Report 4

Purpose

To characterize the clinical effects of two RP1L1 hotspots in patients with East Asian occult macular dystrophy (OMD).

Methods

Fifty-one patients diagnosed with OMD harboring monoallelic pathogenic RP1L1 variants (Miyake disease) from Japan, South Korea, and China were enrolled. Patients were classified into two genotype groups: group A, p.R45W, and group B, missense variants located between amino acids (aa) 1196 and 1201. The clinical parameters of the two genotypes were compared, and deep learning based on spectral-domain optical coherence tomographic (SD-OCT) images was used to distinguish the morphologic differences.

Results

Groups A and B included 29 and 22 patients, respectively. The median age of onset in groups A and B was 14.0 and 40.0 years, respectively. The median logMAR visual acuity of groups A and B was 0.70 and 0.51, respectively, and the survival curve analysis revealed a 15-year difference in vision loss (logMAR 0.22). A statistically significant difference was observed in the visual field classification, but no significant difference was found in the multifocal electroretinographic classification. High accuracy (75.4%) was achieved in classifying genotype groups based on SD-OCT images using machine learning.

Conclusions

Distinct clinical severities and morphologic phenotypes supported by artificial intelligence-based classification were derived from the two investigated RP1L1 hotspots: a more severe phenotype (p.R45W) and a milder phenotype (1196-1201 aa). This newly identified genotype-phenotype association will be valuable for medical care and the design of therapeutic trials.

Deep learning-derived 12-lead electrocardiogram-based genotype prediction for hypertrophic cardiomyopathy: a pilot study

Objective: Given the psychosocial and ethical burden, patients with hypertrophic cardiomyopathy (HCMs) could benefit from the establishment of genetic probability prior to the test. This study aimed to develop a simple tool to provide genotype prediction for HCMs.Methods: A convolutional neural network (CNN) was built with the 12-lead electrocardiogram (ECG) of 124 HCMs who underwent genetic testing (GT), externally tested by predicting the genotype on another HCMs cohort (n = 54), and compared with the conventional methods (the Mayo and Toronto score). Using a third cohort of HCMs (n = 76), the role of the network in risk stratification was explored by calculating the sudden cardiac death (SCD) risk scorers (HCM risk-SCD) across the predicted genotypes. Score-CAM was employed to provide a visual explanation of the network.Results: Overall, 80 of 178 HCMs (45%) were genotype-positive. Using the 12-lead ECG as input, the network showed an area under the curve (AUC) of 0.89 (95% CI, 0.83-0.96) on the test set, outperforming the Mayo score (0.69 [95% CI, 0.65-0.78], p < 0.001) and the Toronto score (0.69 [95% CI, 0.64-0.75], p < 0.001). The network classified the third cohort into two groups (predicted genotype-negative vs. predicted genotype-positive). Compared with the former, patients predicted genotype-positive had a significantly higher HCM risk-SCD (0.04 ± 0.03 vs. 0.03 ± 0.02, p <0.01). Visualization indicated that the prediction was heavily influenced by the limb lead.Conclusions: The network demonstrated a promising ability in genotype prediction and risk assessment in HCM.

Occult Macular Dysfunction Syndrome: Identification of Multiple Pathologies in a Clinical Spectrum of Macular Dysfunction with Normal Fundus in East Asian Patients: EAOMD Report No. 5

Occult macular dystrophy (OMD) is the most prevalent form of macular dystrophy in East Asia. Beyond RP1L1, causative genes and mechanisms remain largely uncharacterised. This study aimed to delineate the clinical and genetic characteristics of OMD syndrome (OMDS). Patients clinically diagnosed with OMDS in Japan, South Korea, and China were enrolled. The inclusion criteria were as follows: (1) macular dysfunction and (2) normal fundus appearance. Comprehensive clinical evaluation and genetic assessment were performed to identify the disease-causing variants. Clinical parameters were compared among the genotype groups. Seventy-two patients with OMDS from fifty families were included. The causative genes were RP1L1 in forty-seven patients from thirty families (30/50, 60.0%), CRX in two patients from one family (1/50, 2.0%), GUCY2D in two patients from two families (2/50, 4.0%), and no genes were identified in twenty-one patients from seventeen families (17/50, 34.0%). Different severities were observed in terms of disease onset and the prognosis of visual acuity reduction. This multicentre large cohort study furthers our understanding of the phenotypic and genotypic spectra of patients with macular dystrophy and normal fundus. Evidently, OMDS encompasses multiple Mendelian retinal disorders, each representing unique pathologies that dictate their respective severity and prognostic patterns.

Current status and practical considerations of artificial intelligence use in screening and diagnosing retinal diseases: Vision Academy retinal expert consensus

PURPOSE OF REVIEW

The application of artificial intelligence (AI) technologies in screening and diagnosing retinal diseases may play an important role in telemedicine and has potential to shape modern healthcare ecosystems, including within ophthalmology.

RECENT FINDINGS

In this article, we examine the latest publications relevant to AI in retinal disease and discuss the currently available algorithms. We summarize four key requirements underlining the successful application of AI algorithms in real-world practice: processing massive data; practicability of an AI model in ophthalmology; policy compliance and the regulatory environment; and balancing profit and cost when developing and maintaining AI models.

SUMMARY

The Vision Academy recognizes the advantages and disadvantages of AI-based technologies and gives insightful recommendations for future directions.

SynthEye: Investigating the Impact of Synthetic Data on Artificial Intelligence-assisted Gene Diagnosis of Inherited Retinal Disease

Purpose

Rare disease diagnosis is challenging in medical image-based artificial intelligence due to a natural class imbalance in datasets, leading to biased prediction models. Inherited retinal diseases (IRDs) are a research domain that particularly faces this issue. This study investigates the applicability of synthetic data in improving artificial intelligence-enabled diagnosis of IRDs using generative adversarial networks (GANs).

Design

Diagnostic study of gene-labeled fundus autofluorescence (FAF) IRD images using deep learning.

Participants

Moorfields Eye Hospital (MEH) dataset of 15 692 FAF images obtained from 1800 patients with confirmed genetic diagnosis of 1 of 36 IRD genes.

Methods

A StyleGAN2 model is trained on the IRD dataset to generate 512 × 512 resolution images. Convolutional neural networks are trained for classification using different synthetically augmented datasets, including real IRD images plus 1800 and 3600 synthetic images, and a fully rebalanced dataset. We also perform an experiment with only synthetic data. All models are compared against a baseline convolutional neural network trained only on real data.

Main Outcome Measures

We evaluated synthetic data quality using a Visual Turing Test conducted with 4 ophthalmologists from MEH. Synthetic and real images were compared using feature space visualization, similarity analysis to detect memorized images, and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) score for no-reference-based quality evaluation. Convolutional neural network diagnostic performance was determined on a held-out test set using the area under the receiver operating characteristic curve (AUROC) and Cohen's Kappa (κ).

Results

An average true recognition rate of 63% and fake recognition rate of 47% was obtained from the Visual Turing Test. Thus, a considerable proportion of the synthetic images were classified as real by clinical experts. Similarity analysis showed that the synthetic images were not copies of the real images, indicating that copied real images, meaning the GAN was able to generalize. However, BRISQUE score analysis indicated that synthetic images were of significantly lower quality overall than real images (P < 0.05). Comparing the rebalanced model (RB) with the baseline (R), no significant change in the average AUROC and κ was found (R-AUROC = 0.86[0.85-88], RB-AUROC = 0.88[0.86-0.89], R-k = 0.51[0.49-0.53], and RB-k = 0.52[0.50-0.54]). The synthetic data trained model (S) achieved similar performance as the baseline (S-AUROC = 0.86[0.85-87], S-k = 0.48[0.46-0.50]).

Conclusions

Synthetic generation of realistic IRD FAF images is feasible. Synthetic data augmentation does not deliver improvements in classification performance. However, synthetic data alone deliver a similar performance as real data, and hence may be useful as a proxy to real data. Financial Disclosure(s): Proprietary or commercial disclosure may be found after the references.

Federated Learning in Ocular Imaging: Current Progress and Future Direction

Advances in artificial intelligence deep learning (DL) have made tremendous impacts on the field of ocular imaging over the last few years. Specifically, DL has been utilised to detect and classify various ocular diseases on retinal photographs, optical coherence tomography (OCT) images, and OCT-angiography images. In order to achieve good robustness and generalisability of model performance, DL training strategies traditionally require extensive and diverse training datasets from various sites to be transferred and pooled into a "centralised location". However, such a data transferring process could raise practical concerns related to data security and patient privacy. Federated learning (FL) is a distributed collaborative learning paradigm which enables the coordination of multiple collaborators without the need for sharing confidential data. This distributed training approach has great potential to ensure data privacy among different institutions and reduce the potential risk of data leakage from data pooling or centralisation. This review article aims to introduce the concept of FL, provide current evidence of FL in ocular imaging, and discuss potential challenges as well as future applications.

Occult Macular Dystrophy: a case report and major review

BACKGROUND

Occult Macular Dystrophy (OMD), a rare autosomal dominant disorder caused by mutations in the retinitis pigmentosa 1-like protein 1 gene (RP1L1), is characterized by loss of central visual acuity in the absence of fundoscopic abnormalities. In patients suspected of having OMD based on unexplained central vision loss and/or photophobia, changes may be detected with spectral-domain optical coherence tomography. Subsequently, the diagnosis can be confirmed with genetic analysis.We report a case of an 18-year-old White male whose suspected diagnosis of OMD was confirmed by molecular testing. We conducted an extensive review of the literature of previously reported patients with OMD to date.

METHODS

A PubMed search of "RP1L1 and Occult Macular Dystrophy" revealed 34 papers. There were 225 individuals with genetically confirmed, symptomatic OMD; an additional 15 had a confirmed mutation but were asymptomatic and discovered incidentally.

RESULTS

Our patient presented with a 10-year history of unexplained loss of central visual acuity and photophobia. Genetic analysis confirmed the presence of a p.R45W substitution on the RP1L1 gene, the most common pathologic mutation in OMD.

CONCLUSIONS

Due to the lack of appreciable fundoscopic changes, correct identification of the disease can be difficult. Incomplete penetrance has been associated with the condition, and the age of onset is highly variable. Much of the research discussing OMD has come from Eastern Asia, but whether this is due to a heightened awareness and screening protocols, or increased incidence is unclear. Additional research and increased awareness globally will help with more timely and accurate diagnoses.

Deep Learning to Distinguish ABCA4-Related Stargardt Disease from PRPH2-Related Pseudo-Stargardt Pattern Dystrophy

(1) Background: Recessive Stargardt disease (STGD1) and multifocal pattern dystrophy simulating Stargardt disease (“pseudo-Stargardt pattern dystrophy”, PSPD) share phenotypic similitudes, leading to a difficult clinical diagnosis. Our aim was to assess whether a deep learning classifier pretrained on fundus autofluorescence (FAF) images can assist in distinguishing ABCA4-related STGD1 from the PRPH2/RDS-related PSPD and to compare the performance with that of retinal specialists. (2) Methods: We trained a convolutional neural network (CNN) using 729 FAF images from normal patients or patients with inherited retinal diseases (IRDs). Transfer learning was then used to update the weights of a ResNet50V2 used to classify the 370 FAF images into STGD1 and PSPD. Retina specialists evaluated the same dataset. The performance of the CNN and that of retina specialists were compared in terms of accuracy, sensitivity, and precision. (3) Results: The CNN accuracy on the test dataset of 111 images was 0.882. The AUROC was 0.890, the precision was 0.883 and the sensitivity was 0.883. The accuracy for retina experts averaged 0.816, whereas for retina fellows it averaged 0.724. (4) Conclusions: This proof-of-concept study demonstrates that, even with small databases, a pretrained CNN is able to distinguish between STGD1 and PSPD with good accuracy.