medRxiv - Ophthalmology最新文献

{"title":"Biomarker potential of vitreous microRNA in retinal disease: a meta-analysis","authors":"Diana Joseph, Brian Grover, Michael Telias","doi":"10.1101/2024.03.25.24304858","DOIUrl":"https://doi.org/10.1101/2024.03.25.24304858","url":null,"abstract":"Acquired retinal diseases such as proliferative diabetic retinopathy and age-related macular degeneration pose significant challenges in diagnosis and prognosis. The vitreous fluid, situated in the posterior chamber of the eye behind the lens, holds a close relationship with the inner retina. Within this milieu, retinal cells secrete a diverse array of biomolecules, potentially harboring vital biomarkers. Among these, short, non-coding micro-RNAs (miRNAs) emerge as promising candidates. Their dynamic regulation by various gene signaling mechanisms, enhanced resistance to degradation, and secretion via separate exocytotic pathways make them particularly significant. Alterations in vitreal miRNA profiles may reflect pathological states and offer insights into disease etiology and progression. We conducted a comprehensive meta-analysis of 22 peer-reviewed studies to assess the potential of vitreous miRNAs as biomarkers for retinal diseases. Our analysis demonstrates the potential utility of miRNAs as biomarkers in specific retinal pathologies. We show that miR-142, miR-9, and miR-21 emerge as robust biomarker candidates, displaying consistent and significant alterations correlating with proliferative vitreoretinal diseases. We also address the methodological challenges encountered in characterizing vitreous miRNA content, including the absence of standardized purification, amplification, and analysis protocols, as well as the scarcity of true control samples. Moreover, we make the case for the adoption of specific housekeeping genes and data normalization techniques to standardize miRNA analysis in the vitreous and explore potential methodologies for obtaining vitreous samples from healthy individuals. Vitreous miRNAs hold promise as potential biomarkers for various retinal diseases, with miR-142, miR-9, and miR-21 emerging as particularly promising candidates. Enhancing methodologies for vitreous sampling and miRNA analysis presents an opportunity to expand the repertoire and utility of miRNA biomarkers in retinal disease diagnosis and prognosis.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":"71 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140303036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Three-Month Interim Analyses of Repeated Low-Level Red-Light Therapy in Myopia Control in Schoolchildren: A Multi-Ethnic Randomized Controlled Trial","authors":"Nellie Deen, Zhuoting Zhu, Ziyi Qi, Yuri Yin-Moe Aung, Gabriella Bulloch, Di Mao, Mingguang He","doi":"10.1101/2024.03.16.24304399","DOIUrl":"https://doi.org/10.1101/2024.03.16.24304399","url":null,"abstract":"Purpose: To assess the efficacy and safety of repeated low-level red-light (RLRL) therapy in controlling myopia progression among multi-ethnic school-aged children. This report focuses on 3-month interim analysis.\u0000Design: Multi-ethnic, parallel controlled randomized trial\u0000Participants: A total of 34 children aged 8-13 years with myopia of cycloplegic spherical equivalent (SE) of − 0.50 to − 5.00 (inclusive) diopters (D), astigmatism of 2.50 D or less, anisometropia of 1.50 D or less, and monocular best-corrected visual acuity (BCVA) of 20/20 or better were enrolled.\u0000Methods: Participants were randomly assigned to the RLRL group (n = 16) or the single-vision spectacles (SVS) group (n = 18). RLRL therapy was administered twice daily on weekdays for 3-minute sessions, while the SVS group continued routine activities. Assessments were scheduled at baseline and follow-up visits at 1, 3, 6, and 12 months, with compliance monitoring and safety assessments throughout.\u0000Main Outcome Measures: The primary outcome and a key secondary outcome included axial length (AL) change and cycloplegic spherical equivalent (SE) change. Results: A total of 31 (91.2%) participated in the 3-month follow-up visit. The RLRL group demonstrated a significant shortening in AL (-0.07 ± 0.07 mm) compared to the SVS group (0.03 ± 0.05 mm, P<0.001). Similarly, SE progression was hyperopic shift in the RLRL group (0.26 ± 0.14 D) while the SVS group exhibited a myopic shift (-0.03 ± 0.38 D, P=0.009). No severe adverse events were reported.\u0000Conclusions: The 3-month interim analysis shows that the efficacy of RLRL therapy in controlling myopia progression among multi-ethnic children is comparable to, or even better than, that idenfied in Chinese patients in previous trials.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":"37 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140165245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Macular Structure Characteristics in Unilateral Idiopathic Full-Thickness Macular Hole and the Healthy Fellow Eyes","authors":"Yi-Ting Hou, Chung-May Yang, Yi-Ting Hsieh","doi":"10.1101/2024.03.16.24304402","DOIUrl":"https://doi.org/10.1101/2024.03.16.24304402","url":null,"abstract":"Purpose: To investigate the characteristics of the macular structure and foveal pit in eyes with lesions and healthy fellow eyes of patients with unilateral full-thickness macular holes (FTMH).\u0000Methods: Patients with unilateral FTMH were retrospectively enrolled as the study group, and their age- and sex-matched individuals with no vitreomacular diseases as the control group in a medical center. FTMHs were classified as FTMH with lamellar hole-associated epiretinal proliferation (LHEP), FTMH without LHEP or FTMH without vitreomacular separation. Macular structure parameters, including foveal base width (FBW), central foveolar thickness (CFT), central subfield thickness (CST), central subfield volume (CSV), and retinal artery trajectory (RAT), were measured using optical coherence tomography and fundus photography. These parameters were compared among different FTMH groups.\u0000Results: A total of 68 patients (39 women) with unilateral FTMH and 68 healthy controls were enrolled. The RAT of the lesioned eyes (0.19 ± 0.06) and the healthy fellow eyes (0.14 ± 0.04) were both smaller than those of the normal controls (0.37 ± 0.14) (P<0.001 for both). The FBW of the healthy fellow eyes (446.8 ± 98.2 μm) were significantly larger than those in the control group (338.4 ± 80.6 μm, P<0.001). No significant differences in any macular parameters were noted among the three different types of FTMH.\u0000Conclusions: Patients with unilateral FTMH had a wider RAT in both the lesioned and healthy eyes, and a wider foveal base in their healthy fellow eyes than in normal controls. Such macular structure characteristics may be prone to macular hole formation.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":"56 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140165240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Computational Framework for Intraoperative Pupil Analysis in Cataract Surgery","authors":"Binh Duong Giap, Karthik Srinivasan,, Ossama Mahmoud, Dena Ballouz, Jefferson Lustre, Keely Likosky, Shahzad I. Mian, Bradford L. Tannen, Nambi Nallasamy","doi":"10.1101/2024.03.13.24304223","DOIUrl":"https://doi.org/10.1101/2024.03.13.24304223","url":null,"abstract":"Purpose: Pupillary instability is a known risk factor for complications in cataract surgery. This study aims to develop and validate an innovative and reliable computational framework for the automated assessment of pupil morphologic changes during the various phases of cataract surgery. Design: Retrospective surgical video analysis. Subjects: Two hundred forty complete surgical video recordings, among which 190 surgeries were conducted without the use of pupil expansion devices and 50 were performed with the use of a pupil expansion device. Methods: The proposed framework consists of three stages: feature extraction, deep learning (DL)-based anatomy recognition, and obstruction detection/compensation. In the first stage, surgical video frames undergo noise reduction using a tensor-based wavelet feature extraction method. In the second stage, DL-based segmentation models are trained and employed to segment the pupil, limbus, and palpebral fissure. In the third stage, obstructed visualization of the pupil is detected and compensated for using a DL-based algorithm. A dataset of 5,700 intraoperative video frames across 190 cataract surgeries in the BigCat database was collected for validating algorithm performance. Main Outcome Measures: The pupil analysis framework was assessed on the basis of segmentation performance for both obstructed and unobstructed pupils. Classification performance of models utilizing the segmented pupil time series to predict surgeon use of a pupil expansion device was also assessed. Results: An architecture based on the FPN model with VGG16 backbone integrated with the AWTFE feature extraction method demonstrated the highest performance in anatomy segmentation, with Dice coefficient of 96.52%. Incorporation of an obstruction compensation algorithm improved performance further (Dice 96.82%). Downstream analysis of framework output enabled the development of an SVM-based classifier that could predict surgeon usage of a pupil expansion device prior to its placement with 96.67% accuracy and AUC of 99.44%. Conclusions: The experimental results demonstrate that the proposed framework 1) provides high accuracy in pupil analysis compared to human-annotated ground truth, 2) substantially outperforms isolated use of a DL segmentation model, and 3) can enable downstream analytics with clinically valuable predictive capacity.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140148507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Creating an Early Diagnostic Method for Glaucoma Using Convolutional Neural Networks","authors":"Areej A. Alqarni, Sanad H. Al Harbi, Irshad A. Subhan","doi":"10.1101/2024.03.14.24304273","DOIUrl":"https://doi.org/10.1101/2024.03.14.24304273","url":null,"abstract":"According to the World Health Organization, glaucoma\u0000is a leading cause of blindness, accounting for over 12% of global\u0000blindness as it affects one in every 100 people. In fact, 79.6 million\u0000people worldwide live with blindness caused by glaucoma. This is\u0000because the current method for diagnosing glaucoma is by\u0000examining retinal fundus images. However, it is considerably\u0000difficult to distinguish the lesions' features solely through manual\u0000observations by ophthalmologists, especially in the early phases.\u0000This study proposes a new diagnosis method using convolutional\u0000neural networks. The attention mechanism is utilized to learn\u0000pixel-wise features for accurate prediction. Several attention\u0000strategies have been developed to guide the networks in learning\u0000the important features and factors that affect localization accuracy.\u0000The algorithms were trained for glaucoma detection using Python\u00002.7, TensorFlow, Py Torch, and Keras. The methods were\u0000evaluated on Drishti-GS and RIM-ONE datasets with 361 training\u0000and 225 test sets, consisting of 344 healthy and 242 glaucomatous\u0000images. The proposed algorithms can achieve impressive results\u0000that show an increase in overall diagnostic efficiency, as the\u0000algorithm displays a 30-second detection time with 98.9%\u0000accuracy compared to the 72.3% accuracy of traditional testing\u0000methods. Finally, this algorithm has been implemented as a\u0000webpage, allowing patients to test for glaucoma. This webpage\u0000offers various services such as: connecting the patient to the\u0000nearest care setup; offering scientific articles regarding glaucoma;\u0000and a video game that supports eye-treatment yogic exercises to\u0000strengthen vision and focus. This early diagnostic method has the\u0000near future potential to decrease the percentage of irreversible\u0000vision loss due to glaucoma by 42.79% (the percentage was\u0000calculated using the mean absolute error function), which could\u0000prevent glaucoma from remaining the leading cause of blindness\u0000worldwide.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":"19 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140148390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Great expectations: Aligning visual prosthetic development with implantee needs","authors":"Lucas Gil Nadolskis, Lily M Turkstra, Ebenezer Larnyo, Michael Beyeler","doi":"10.1101/2024.03.12.24304186","DOIUrl":"https://doi.org/10.1101/2024.03.12.24304186","url":null,"abstract":"Purpose: Visual prosthetics have emerged as a promising assistive technology for individuals with vision loss, yet research often overlooks the human aspects of this technology. While previous studies have concentrated on the perceptual experiences of implant recipients (implantees) or the attitudes of potential implantees towards near-future implants, a systematic account of how current implants are being used in everyday life is still lacking.\u0000Methods: We interviewed six recipients of the most widely used visual implants (Argus II and Orion) and six leading researchers in the field. Through thematic and statistical analyses, we explored the daily usage of these implants by implantees and compared their responses to the expectations of researchers. We also sought implantees' input on desired features for future versions, aiming to inform the development of the next generation of implants.\u0000Results: Although implants are designed to facilitate various daily activities, we found that implantees use them less frequently than researchers expected. This discrepancy primarily stems from issues with usability and reliability, with implantees finding alternative methods to accomplish tasks, reducing the need to rely on the implant. For future implants, implantees emphasized the desire for improved vision, smart integration, and increased independence.\u0000Conclusions: Our study reveals a significant gap between researcher expectations and implantee experiences with visual prostheses, underscoring the importance of focusing future research on usability and real-world application.\u0000Translational relevance: This work advocates for a better alignment between technology development and implantee needs to enhance clinical relevance and practical utility of visual prosthetics.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140128680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring WNT2 Polymorphisms in Comitant Strabismus: A Genetic Association Study","authors":"Zainab Zehra, Christopher S von Bartheld, Andrea B. Agarwal, Hans Vasquez-Gross, Sorath Noorani Siddiqui, Maleeha Azam, Raheel Qamar","doi":"10.1101/2024.03.12.24304190","DOIUrl":"https://doi.org/10.1101/2024.03.12.24304190","url":null,"abstract":"Abstract\u0000Background: Strabismus is a complex oculomotor condition characterized by a misalignment of the visual axis. The genetics of strabismus are poorly defined although a few candidate genes have been identified, among which is the WNT2 gene. Our study was designed to assess the association of single nucleotide polymorphisms (SNPs) of WNT2 in Pakistani strabismus patients.\u0000Methods: A total of six SNPs, three intronic and three in the 3 untranslated region, were screened in the current study. Logistic regression was performed using a dominant, recessive and additive model to determine the association of SNPs with strabismus and its clinical subtypes: esotropia and exotropia. Furthermore, haplotype analysis was performed.\u0000Results: Regression analysis revealed an association of rs2896218, rs3779550, rs2285544 and rs4730775 with strabismus under the dominant model. When analyzed separately, rs2896218 and rs2285544 were found to be associated with both esotropia and exotropia, while rs4730775 was significantly associated only with exotropia under the dominant model. Based on clinical parameters, rs2896218, rs2285544 and rs4730775 were also found to be associated with the group of strabismus patients who were diagnosed at birth, but not in the group of patients who were diagnosed later in life. Haplotype analysis revealed that the haplotype A T T (corresponding to rs2896218, rs3779550 and rs2285544) was significantly more prevalent in the strabismus group. Conclusion: Overall, the results of the present study suggests an association of WNT2 polymorphisms with strabismus and its subtypes in the Pakistani population, though further studies are needed to elucidate their role in strabismus etiology.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":"22 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140128522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated Detection of Keratorefractive Laser Surgeries on Optical Coherence Tomography using Deep Learning","authors":"Jad F. Assaf, Hady Yazbeck, Dan Reinstein, Timothy Archer, Roland Assaf, Diego de Ortueta, Juan Arbelaez, Maria Clara Arbelaez, Shady T Awwad","doi":"10.1101/2024.03.08.24304001","DOIUrl":"https://doi.org/10.1101/2024.03.08.24304001","url":null,"abstract":"PURPOSE: To report a deep learning neural network on anterior segment optical coherence tomography (AS-OCT) for automated detection of different keratorefractive laser surgeries, including Laser In-Situ Keratomileusis with femtosecond microkeratome (Femto-LASIK), LASIK with mechanical microkeratome, photorefractive keratectomy (PRK), keratorefractive lenticule extraction (KLEx), and non-operated eyes, while also distinguishing the targeted ametropias, such as myopic and hyperopic treatments, within these procedures. DESIGN: Cross-sectional retrospective study. METHODS: A total of 14,948 eye scans from 2,278 eyes of 1,166 subjects were used to develop a deep learning neural network algorithm with an 80/10/10 patient distribution for training, validation, and testing phases, respectively. The algorithm was evaluated for its accuracy, F1-scores, area under precision-recall curve (AUPRC), and area under receiver operating characteristic curve (AUROC). RESULTS: On the test dataset, the neural network was able to detect the different surgical classes with an accuracy of 96%, a weighted-average F1-score of 96% and a macro-average F1-score of 96%. The neural network was further able to detect hyperopic and myopic subclasses within each surgical class, with an accuracy of 90%, weighted-average F1 score of 90%, and macro-average F1-score of 83%. CONCLUSIONS: Determining a patient's keratorefractive laser history is vital for customizing treatments, performing precise intraocular lens (IOL) calculations, and enhancing ectasia risk assessments, especially when electronic health records are incomplete or unavailable. Neural networks can be used to accurately classify keratorefractive laser history from AS-OCT scans, a step in transforming the AS-OCT from a diagnostic to a screening tool in the refractive clinic.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":"127 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140097355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating the Safety and Efficacy of Topical Insulin for Ocular Disease: A Systematic Review","authors":"Luis Jesuino de Oliveira Andrade, Gabriela Correia Matos de Oliveira, Caroline Santos Franca, Luis Matos de Oliveira","doi":"10.1101/2024.02.24.24303321","DOIUrl":"https://doi.org/10.1101/2024.02.24.24303321","url":null,"abstract":"Introduction: Ocular surface disorders are prevalent, impacting millions worldwide and causing significant morbidity. Conventional treatments often fall short in addressing refractory cases. Topical insulin has emerged as a potential therapeutic option.\u0000Objective: This systematic review aimed to evaluate the safety and efficacy of topical insulin for ocular diseases.\u0000Methods: We conducted a systematic review in major databases including the PubMed, MEDLINE, and EMBASE for studies published from (1976 Jan - 2024 Feb) investigating topical insulin for ocular conditions. Studies were screened and selected based on predefined inclusion/exclusion criteria. Data on safety and efficacy were extracted and analyzed. Results: Ten studies (1 case-control, 3 randomized prospective, 3 retrospective, and 3 double-blind designs) met the inclusion criteria. Studies explored various indications, including neurotrophic corneal ulcers, persistent epithelial defects, recurrent epithelial erosions, dry eye disease, and postoperative corneal wound healing in diabetic patients. Overall, findings suggested promising outcomes with topical insulin: promoting healing of refractory neurotrophic corneal ulcers, accelerating reepithelialization in persistent epithelial defects, reducing recurrence of recurrent epithelial erosions, improving symptoms and reducing corneal staining in dry eye disease, enhancing postoperative corneal epithelial wound healing in diabetic patients. Adverse events were minimal and primarily reported as transient stinging or discomfort.\u0000Conclusion: This review provides encouraging evidence for the therapeutic potential of topical insulin in diverse ocular diseases. While methodological limitations exist, particularly in non-randomized studies, the current body of literature suggests topical insulin may offer a safe and effective treatment option for patients with refractory corneal disorders.\u0000Keywords: Topical insulin, Ocular conditions, Systematic review.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140010266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantitative Characterization of Retinal Features in Translated OCTA","authors":"Rashadul Hasan Badhon, Atalie Carina Thompson, Jennifer I. Lim, Theodore Leng, Minhaj Nur Alam","doi":"10.1101/2024.02.23.24303275","DOIUrl":"https://doi.org/10.1101/2024.02.23.24303275","url":null,"abstract":"Purpose: This study explores the feasibility of using generative machine learning (ML) to translate Optical Coherence Tomography (OCT) images into Optical Coherence Tomography Angiography (OCTA) images, potentially bypassing the need for specialized OCTA hardware.\u0000Methods: The method involved a generative adversarial network framework that includes a 2D vascular segmentation model and a 2D OCTA image translation model. This framework is designed to enhance the accuracy, resolution, and continuity of vascular regions in the translated OCTA (TR-OCTA) images. The study utilizes a public dataset of 500 patients, divided into subsets based on resolution and disease status, to validate the quality of TR-OCTA images. The validation employs several quality and quantitative metrics to compare the translated images with ground truth OCTAs (GT-OCTA).\u0000Result: TR-OCTAs showed high image quality in both 3 and 6 mm datasets (high-resolution, moderate structural similarity and contrast quality compared to GT-OCTAs). There were slight discrepancies in vascular metrics, especially in diseased patients. Blood vessel features like tortuosity and vessel perimeter index showed a better trend compared to density features which are affected by local vascular distortions.\u0000Conclusion: This study presents a promising solution to the limitations of OCTA adoption in clinical practice by using ML to translate OCT data into OCTA images.\u0000Translation relevance: This study has the potential to significantly enhance the diagnostic process for retinal diseases by making detailed vascular imaging more widely available and reducing dependency on costly OCTA equipment.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139978642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}