Brolucizumab in recalcitrant neovascular age-related macular degeneration-real-world data in Chinese population.

This retrospective study aimed to determine the short-term efficacy and safety of brolucizumab treatment for recalcitrant neovascular age-related macular degeneration (nAMD) in a real-world setting in Taiwan. Recalcitrant nAMD patients who were treated with brolucizumab from November 2021 to August 2022 at Taipei Veterans General Hospital were included. Patients were followed for 3 months after switching to brolucizumab. The primary outcomes were changes in mean best-corrected visual acuity (BCVA) and central retinal thickness (CRT) from baseline to the third month. The secondary outcomes included the incidence of intraocular inflammation (IOI), proportion of patients with subretinal and intraretinal fluid (SRF and IRF), and change in pigment epithelial detachment (PED) height from baseline to the third month. The significance level was considered as p < .05 in all tests. A total of 38 patients (40 eyes) with a mean (±SD) age of 76.3 (±10.84) years were included. The baseline BCVA was 0.92±0.64 logMAR, and the CRT and PED height were 329.0±171.18 and 189.8±114.94 um, respectively. The patients had a significant reduction in CRT and resolution of IRF and SRF from baseline to the third month. There were numerical improvements in mean BCVA and PED height, but they were not significant. The percentages of achieving at least 0.1, 0.2, and 0.3 logMAR (equivalent to 5, 10, 15 ETDRS letters) visual gain were 50%, 37.5%, and 30%, respectively, during the first 3 months of follow-up. No IOI occurred in these patients. This study demonstrated that brolucizumab had good short-term structural and functional efficacy in recalcitrant nAMD patients.

Dysregulation of the circRNA_0087207/miR-548c-3p/PLSR1-TGFB2 axis in Leber hereditary optic neuropathy in vitro.

BACKGROUND: Leber hereditary optic neuropathy (LHON) is mainly the degeneration of retinal ganglion cells (RGCs) associated with high apoptosis and reactive oxygen species (ROS) levels, which is accepted to be caused by the mutations in the subunits of complex I of the mitochondrial electron transport chain. The treatment is still infant while efforts of correcting genes or using antioxidants do not bring good and consistent results. Unaffected carrier carries LHON mutation but shows normal phenotype, suggesting that the disease's pathogenesis is complex, in which secondary factors exist and cooperate with the primary complex I dysfunction. METHODS: Using LHON patient-specific induced pluripotent stem cells (iPSCs) as the in vitro disease model, we previously demonstrated that circRNA_0087207 had the most significantly higher expression level in the LHON patient-iPSC-derived RGCs compared with the unaffected carrier-iPSC-derived RGCs. To elaborate the underlying pathologies regulated by circRNA_008720 mechanistically, bioinformatics analysis was conducted and elucidated that circRNA_0087207 could act as a sponge of miR-548c-3p and modulate PLSCR1/TGFB2 levels in ND4 mutation-carrying LHON patient-iPSC-derived RGCs. RESULTS: Using LHON iPSC-derived RGCs as the disease-based platform, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis on targeted mRNA of miR-548c-3p showed the connection with apoptosis, suggesting downregulation of miR548c-3p contributes to the apoptosis of LHON patient RGCs. CONCLUSION: We showed that the downregulation of miR548c-3p plays a critical role in modulating cellular dysfunction and the apoptotic program of RGCs in LHON.

Taiwan ocular inflammation society consensus recommendations for the management of juvenile idiopathic arthritis-associated uveitis.

We presented the development of a consensus guideline for managing juvenile idiopathic arthritis-associated uveitis (JIAU) in Taiwan, considering regional differences in manifestation and epidemiology. The Taiwan Ocular Inflammation Society (TOIS) committee formulated this guideline using a modified Delphi approach with two panel meetings. Recommendations were based on a comprehensive evidence-based literature review and expert clinical experiences, and were graded according to the Oxford Centre for Evidence-Based Medicine's "Levels of Evidence" guideline (March 2009). The TOIS consensus guideline consists of 10 recommendations in four categories: screening and diagnosis, treatment, complications, and monitoring, covering a total of 27 items. These recommendations received over 75% agreement from the panelists. Early diagnosis and a coordinated referral system between ophthalmologists and pediatric rheumatologists are crucial to prevent irreversible visual impairment in children with JIAU. However, achieving a balance between disease activity and medication use remains a key challenge in JIAU management, necessitating further clinical studies.

Literature- and Experience-Based Consensus for Acute Post-operative Endophthalmitis and Endogenous Endophthalmitis in Taiwan.

Clinical practices on acute post-operative and endogenous endophthalmitis (EnE) are highly variable among clinicians due to a lack of up-to-date, high-quality evidential support. An expert consensus is thus much needed. A panel consisting of ten retinal specialists in Taiwan was organized. They evaluated relevant literature and developed key questions regarding acute post-operative and EnE that are cardinal for practice but yet to have conclusive evidence. The panel then attempted to reach consensus on all the key questions accordingly. There were eight key questions proposed and their respective consensus statements were summarized as follows: Gram staining and culture are still the standard procedures for the diagnosis of endophthalmitis. Vitrectomy is recommended to be performed earlier than the timing proposed by the Endophthalmitis Vitrectomy Study (EVS). Routine intracameral antibiotic injection for post-cataract surgery endophthalmitis prophylaxis is not recommended because of potential compounding error hazards and a lack of support from high-quality studies. Routine fundus examination is recommended for all patients with pyogenic liver abscess. In EnE, vitrectomy is recommended if diffused and dense vitritis is present, or if the disease progresses. These consensus statements may work as handy guidance or reference for clinical practices of acute post-operative and EnE.

Orbital floor fractures in Taiwan: A 10-year nationwide population-based study.

PURPOSE: To characterize the epidemiology, associated complications, and risk factors of orbital floor fractures in a nationwide longitudinal health insurance database. MATERIALS AND METHODS: Claims data from a million randomly selected registered residents from the Taiwan National Health Insurance Research Database were analyzed between 2001 and 2011 as part of a retrospective cohort review. Patients were identified using the International Classification of Disease-9 diagnosis codes for orbital floor fracture (closed: 802.6; open: 802.7). The cases were categorized as surgical or nonsurgical based on the procedure codes and compared statistically. RESULTS: From 2001 to 2011, 663 patients were diagnosed with orbital floor fractures out of a total population at risk of 9,836,431 person-years (average incidence: 6.78 persons/100,000/year) with overall increasing incidence. Surgical treatments were performed in 213 (32%) patients. Patients who received surgical treatment were younger than those who did not (mean age 25.3 ± 13.6 years vs. 34.2 ± 18.6 years, P < 0.001). The diagnosis with diplopia was a significantly associated factor for surgical treatment (2.2% in nonsurgery group vs. 6.6% in surgery group, P = 0.007). Male gender (adjusted hazard ratios [aHR] = 2.1, 95% confidence interval [CI]: 1.79-2.49) and low monthly income (aHR = 1.76, 95% CI: 1.16-2.67) were the risk factors for orbital floor fracture. CONCLUSION: The incidence of orbital floor fractures increased in the Taiwanese population between 2001 and 2011. Men and low income patients were at increased risk of orbital floor fracture. More research is necessary to clarify what factors are driving the escalating incidence of orbital fractures in this national population.

Acute Necrotizing Retinopathy After Xen Gel Stent Implantation.

PRCIS: We report a case of a 45-year-old woman who developed serous retinal detachment, hypotony, and retinal necrosis after Xen gel stent implantation. ABSTRACT: A 45-year-old woman developed sudden blurring of vision 4 days after Xen gel stent replacement surgery. Persistent hypotony, uveitis, and serious retinal detachment rapidly progressed despite medical and surgical treatments. Retinal necrosis, optic atrophy, and total blindness developed within 2 months. Although infectious and autoimmune-related uveitis were ruled out through negative culture and blood test results, acute postoperative infectious endophthalmitis could not be completely excluded in this case. However, toxic retinopathy related to mitomycin- C was suspected eventually.

Recognizing the Differentiation Degree of Human Induced Pluripotent Stem Cell-Derived Retinal Pigment Epithelium Cells Using Machine Learning and Deep Learning-Based Approaches.

Induced pluripotent stem cells (iPSCs) can be differentiated into mesenchymal stem cells (iPSC-MSCs), retinal ganglion cells (iPSC-RGCs), and retinal pigmental epithelium cells (iPSC-RPEs) to meet the demand of regeneration medicine. Since the production of iPSCs and iPSC-derived cell lineages generally requires massive and time-consuming laboratory work, artificial intelligence (AI)-assisted approach that can facilitate the cell classification and recognize the cell differentiation degree is of critical demand. In this study, we propose the multi-slice tensor model, a modified convolutional neural network (CNN) designed to classify iPSC-derived cells and evaluate the differentiation efficiency of iPSC-RPEs. We removed the fully connected layers and projected the features using principle component analysis (PCA), and subsequently classified iPSC-RPEs according to various differentiation degree. With the assistance of the support vector machine (SVM), this model further showed capabilities to classify iPSCs, iPSC-MSCs, iPSC-RPEs, and iPSC-RGCs with an accuracy of 97.8%. In addition, the proposed model accurately recognized the differentiation of iPSC-RPEs and showed the potential to identify the candidate cells with ideal features and simultaneously exclude cells with immature/abnormal phenotypes. This rapid screening/classification system may facilitate the translation of iPSC-based technologies into clinical uses, such as cell transplantation therapy.

Sympathetic ophthalmia following radiation-induced scleral necrosis in choroidal melanoma.

Sympathetic ophthalmia (SO) is a bilateral granulomatous panuveitis. We report a rare case of SO presenting after scleral necrosis as a late complication of Gamma Knife radiotherapy for choroidal melanoma. A 55-year-old woman presented with primary choroidal melanoma in the right eye and has been treated with Gamma Knife radiotherapy with stable tumor size. Five years after radiotherapy, a pigmented protrusive uveal mass was visibly noted over the superior sclera of the same eye, corresponding to periocular soft tissue enhancement on computed tomography. Biopsies of the pigmented mass showed the absence of malignancy. One month later, acute blurred vision with signs of sympathetic ophthalmia developed in the left eye. The patient received high-dose systemic corticosteroids and immunomodulatory therapy. The intraocular inflammation in the left eye subsided with improving vision, and the uveal mass in the right eye flattened after the anti-inflammatory therapy. Scleral necrosis is a rare complication following radiotherapy for choroidal melanoma and may incite sympathetic ophthalmia, for which prompt and aggressive treatment is important to save vision, especially for the fellow eye.

Temporal fluctuations of cardiovascular parameters after intravitreal injections.

BACKGROUND: Despite the effectiveness of intravitreal injection (IVI) of anti-vascular endothelial growth factor in treating retinal diseases, there remains a paucity of evidence on potential systemic risks associated with this procedure. This study aims to investigate cardiovascular parameters and the risk of hypertensive urgency after IVIs. METHODS: Patients who received IVIs for retinal/macular diseases were enrolled retrospectively. Patients who received cataract surgeries were enrolled as controls. Systolic and diastolic blood pressure (BP) and heart rate were measured 10 minutes before, immediately after, and more than 30 minutes after IVIs and cataract surgery. Multivariate analysis was performed to evaluate risk factors for hypertensive urgency. RESULTS: Seventy patients who received IVIs and 95 patients who received cataract surgeries were enrolled. A higher preoperative systolic BP was found in the IVI groups than in the control group (147.0 ± 22.9 vs 136.3 ± 21.8 mmHg, respectively). The patients who received IVIs had a higher increase in perioperative systolic BP immediately after the procedure than the controls (17.43 ± 20.53 mmHg vs 9.11 ± 18.92 mmHg, p = 0.009). The IVI procedure (odds ratio [OR] 4.84, p = 0.008), preoperative systolic BP ≥160 mmHg (OR 17.891, p = 0.001, compared to preoperative systolic BP <140 mmHg), and underlying hypertension (OR 3.305, p = 0.041) were risk factors for hypertensive urgency immediately after the IVIs. CONCLUSION: We found a transient increase in BP after IVIs, which may have been associated with hypertensive urgency and related cardiovascular disorders in older patients and in those with relevant comorbidities. Clinicians should pay more attention to these patients before performing IVIs.

Pluripotent Stem Cells in Clinical Cell Transplantation: Focusing on Induced Pluripotent Stem Cell-Derived RPE Cell Therapy in Age-Related Macular Degeneration.

Human pluripotent stem cells (PSCs), including both embryonic stem cells (ESCs) and induced pluripotent stem cells (iPSCs), represent valuable cell sources to replace diseased or injured tissues in regenerative medicine. iPSCs exhibit the potential for indefinite self-renewal and differentiation into various cell types and can be reprogrammed from somatic tissue that can be easily obtained, paving the way for cell therapy, regenerative medicine, and personalized medicine. Cell therapies using various iPSC-derived cell types are now evolving rapidly for the treatment of clinical diseases, including Parkinson's disease, hematological diseases, cardiomyopathy, osteoarthritis, and retinal diseases. Since the first interventional clinical trial with autologous iPSC-derived retinal pigment epithelial cells (RPEs) for the treatment of age-related macular degeneration (AMD) was accomplished in Japan, several preclinical trials using iPSC suspensions or monolayers have been launched, or are ongoing or completed. The evolution and generation of human leukocyte antigen (HLA)-universal iPSCs may facilitate the clinical application of iPSC-based therapies. Thus, iPSCs hold great promise in the treatment of multiple retinal diseases. The efficacy and adverse effects of iPSC-based retinal therapies should be carefully assessed in ongoing and further clinical trials.

Automatic Segmentation of Retinal Fluid and Photoreceptor Layer from Optical Coherence Tomography Images of Diabetic Macular Edema Patients Using Deep Learning and Associations with Visual Acuity.

Diabetic macular edema (DME) is a highly common cause of vision loss in patients with diabetes. Optical coherence tomography (OCT) is crucial in classifying DME and tracking the results of DME treatment. The presence of intraretinal cystoid fluid (IRC) and subretinal fluid (SRF) and the disruption of the ellipsoid zone (EZ), which is part of the photoreceptor layer, are three crucial factors affecting the best corrected visual acuity (BCVA). However, the manual segmentation of retinal fluid and the EZ from retinal OCT images is laborious and time-consuming. Current methods focus only on the segmentation of retinal features, lacking a correlation with visual acuity. Therefore, we proposed a modified U-net, a deep learning algorithm, to segment these features from OCT images of patients with DME. We also correlated these features with visual acuity. The IRC, SRF, and EZ of the OCT retinal images were manually labeled and checked by doctors. We trained the modified U-net model on these labeled images. Our model achieved Sørensen-Dice coefficients of 0.80 and 0.89 for IRC and SRF, respectively. The area under the receiver operating characteristic curve (ROC) for EZ disruption was 0.88. Linear regression indicated that EZ disruption was the factor most strongly correlated with BCVA. This finding agrees with that of previous studies on OCT images. Thus, we demonstrate that our segmentation network can be feasibly applied to OCT image segmentation and assist physicians in assessing the severity of the disease.

Evaluation of a remote telemedicine platform using a novel handheld fundus camera: Physician and patient perceptions from real-world experience.

BACKGROUND: Although teleophthalmology has gained traction in recent years, it is at the center of the coronavirus disease pandemic. However, most hospitals are not ready owing to a severe lack of real-world experience. Furthermore, a limited number of studies have evaluated telemedicine applications on remote islands. This study aimed to evaluate real-world clinical and referral accuracy, image quality, physician-perceived diagnostic certainty, and patient satisfaction with telemedicine eye screening using a novel handheld fundus camera in a rural and medically underserved population. METHODS: This prospective study included 176 eyes from a remote island. All participants underwent a comprehensive ophthalmic examination. Nonmydriatic retinal images obtained using a handheld fundus camera were reviewed by two retinal specialists to determine image quality, diagnosis, and need for referrals. The agreement of diagnosis between image-based assessments was compared with that of binocular indirect ophthalmoscopic assessments. RESULTS: Image quality of fundus photographs was considered acceptable or ideal in 97.7% and 95.5% of eyes assessed by two reviewers, respectively. There was considerable agreement in diagnosis between the indirect ophthalmoscopic assessment and image-based assessment by two reviewers (Cohen's kappa = 0.80 and 0.78, respectively). Likewise, substantial agreement was achieved in the referrals. The sensitivity for referable retinopathy from the two reviewers was 78% (95% confidence interval [CI], 57%-91%) and 78% (95% CI, 57%-91%), whereas specificity was 99% (95% CI, 95%-99%] and 98% (95% CI, 93%-99%), respectively. For physicians' perceived certainty of diagnosis, 93.8% and 90.3% were considered either certain or reliable. Overall, 97.4% of participants were satisfied with their experiences and greatly valued the telemedicine services. CONCLUSION: Novel fundus camera-based telemedicine screening demonstrated high accuracy in detecting clinically significant retinopathy in real-world settings. It achieved high patient satisfaction and physician-perceived certainty in diagnosis with reliable image quality, which may be scaled internationally to overcome geographical barriers under the global pandemic.

Clinical Manifestations and Outcomes of Tubercular Uveitis in Taiwan-A Ten-Year Multicenter Retrospective Study.

Background andObjectives: This 10-year multicenter retrospective study reviewed the clinical manifestations, diagnostic tests, and treatment modalities of tubercular uveitis (TBU), including direct infection and indirect immune-mediated hypersensitivity to mycobacterial antigens in Taiwan. Materials and Methods: This retrospective chart review of patients with TBU was conducted at 11 centers from 1 January 2008 to 31 December 2017. We used a multiple regression model to analyze which factors influenced best-corrected visual acuity (BCVA) improvement. Results: A total of 79 eyes from 51 patients were included in the study. The mean age was 48.9 ± 16.4 years. The mean change of LogMAR BCVA at last visit was -0.21 ± 0.45. Diagnostic tools used include chest X-ray, chest computed tomography, Mantoux test, interferon gamma release test (QuantiFERON-TB Gold test), intraocular fluid tuberculosis polymerase chain reaction, and bronchial alveolar lavage. The clinical manifestations included 48% posterior uveitis and 37% panuveitis. In the sample, 55% of the cases were bilateral and 45% unilateral. There was 60.76% retinal vasculitis, 35.44% choroiditis, 21.52% serpiginous-like choroiditis, 17.72% vitreous hemorrhage, 12.66% posterior synechiae, 6.33% retinal detachment, and 3.80% choroidal granuloma. Treatment modalities included rifampicin, isoniazid, pyrazinamide, ethambutol, oral steroid, posterior triamcinolone, non-steroidal anti-inflammatory drugs, vitrectomy, and immunosuppressants. BCVA improved in 53.2% of eyes and remained stable in 32.9% of eyes. In the final model of multiple regression, worse initial BCVA, pyrazinamide, and receiving vitrectomy predicted better BCVA improvement. Ethambutol was associated with worse visual outcomes. Seven eyes experienced recurrence. Conclusions: This is the largest 10-year multicenter retrospective study of TBU in Taiwan to date, demonstrating the distribution of clinical manifestations and clinical associations with better treatment outcomes. The study provides a comprehensive description of TBU phenotypes in Taiwan and highlights considerations for the design of further prospective studies to reliably assess the role of ATT and vitrectomy in patients with TBU.

Clinical manifestation and current therapeutics in X-juvenile retinoschisis.

X-linked juvenile retinoschisis (XLRS) is one of the common early-onset hereditary retinal degenerative diseases in men. The common symptoms of XLRS range from mild to severe central vision loss and radial stripes created by the fovea, the division of the inner layer of the retina in the peripheral retina and the significant decrease in b-wave amplitude (ERG). Retinoschisin, the 224-amino-acid protein product of the retinoschisis 1 (RS1) gene, contains a discoid domain as the primary structural unit, an N-terminal cleavable signal sequence, and an oligomerization-area component. Retinoschisin is a homo-octamer complex with disulfide links that are released by retinal cells. It helps preserve the retina's integrity by binding to the surface of photoreceptors and bipolar cells. As a recessive genetic disease, XLRS was usually treated by prescribing low vision aids in most clinical cases. A gene replacement therapy based on adeno-associated virus vectors was initiated and showed a breakthrough in treating XLRS in 2014. Understanding the revolution of gene therapy for treating XLRS may accelerate its development and make this gene therapy the template for developing therapeutics against other inherited retinal diseases.

Granulocyte Colony Stimulating Factor-induced Immune Recovery Uveitis Associated with Cytomegalovirus Retinitis in the Setting of Good Syndrome.

PURPOSE: To report a case of immune recovery uveitis (IRU) secondary to cytomegalovirus (CMV) retinitis in a patient with Good syndrome treated with granulocyte colony stimulating factor (GCSF). METHODS: A case report. CASE: A 54-year-old woman with a history of Good syndrome for 2 years presented with chronic panuveitis in her right eye for 6 months. She had received multiple doses of GCSF for a pulmonary infection. Her visual acuity was hand movement in the right eye. Few anterior chamber cells, dense vitreous haze, and chorioretinal lesions were noted. Granular retinal atrophic lesions without obvious infiltration were observed during diagnostic vitrectomy. Polymerase chain reaction of the vitreous sample was positive for CMV DNA. A diagnosis of IRU secondary to CMV retinitis was made. The inflammation was controlled with topical steroids after surgery. SUMMARY: In this report, we present a patient with Good syndrome who developed IRU secondary to CMV retinitis.

Identification of Novel Genomic-Variant Patterns of OR56A5, OR52L1, and CTSD in Retinitis Pigmentosa Patients by Whole-Exome Sequencing.

Inherited retinal dystrophies (IRDs) are rare but highly heterogeneous genetic disorders that affect individuals and families worldwide. However, given its wide variability, its analysis of the driver genes for over 50% of the cases remains unexplored. The present study aims to identify novel driver genes, disease-causing variants, and retinitis pigmentosa (RP)-associated pathways. Using family-based whole-exome sequencing (WES) to identify putative RP-causing rare variants, we identified a total of five potentially pathogenic variants located in genes OR56A5, OR52L1, CTSD, PRF1, KBTBD13, and ATP2B4. Of the variants present in all affected individuals, genes OR56A5, OR52L1, CTSD, KBTBD13, and ATP2B4 present as missense mutations, while PRF1 and CTSD present as frameshift variants. Sanger sequencing confirmed the presence of the novel pathogenic variant PRF1 (c.124_128del) that has not been reported previously. More causal-effect or evidence-based studies will be required to elucidate the precise roles of these SNPs in the RP pathogenesis. Taken together, our findings may allow us to explore the risk variants based on the sequencing data and upgrade the existing variant annotation database in Taiwan. It may help detect specific eye diseases such as retinitis pigmentosa in East Asia.

Application of artificial intelligence-driven endoscopic screening and diagnosis of gastric cancer.

The landscape of gastrointestinal endoscopy continues to evolve as new technologies and techniques become available. The advent of image-enhanced and magnifying endoscopies has highlighted the step toward perfecting endoscopic screening and diagnosis of gastric lesions. Simultaneously, with the development of convolutional neural network, artificial intelligence (AI) has made unprecedented breakthroughs in medical imaging, including the ongoing trials of computer-aided detection of colorectal polyps and gastrointestinal bleeding. In the past demi-decade, applications of AI systems in gastric cancer have also emerged. With AI's efficient computational power and learning capacities, endoscopists can improve their diagnostic accuracies and avoid the missing or mischaracterization of gastric neoplastic changes. So far, several AI systems that incorporated both traditional and novel endoscopy technologies have been developed for various purposes, with most systems achieving an accuracy of more than 80%. However, their feasibility, effectiveness, and safety in clinical practice remain to be seen as there have been no clinical trials yet. Nonetheless, AI-assisted endoscopies shed light on more accurate and sensitive ways for early detection, treatment guidance and prognosis prediction of gastric lesions. This review summarizes the current status of various AI applications in gastric cancer and pinpoints directions for future research and clinical practice implementation from a clinical perspective.

An Update on Gene Therapy for Inherited Retinal Dystrophy: Experience in Leber Congenital Amaurosis Clinical Trials.

Inherited retinal dystrophies (IRDs) are a group of rare eye diseases caused by gene mutations that result in the degradation of cone and rod photoreceptors or the retinal pigment epithelium. Retinal degradation progress is often irreversible, with clinical manifestations including color or night blindness, peripheral visual defects and subsequent vision loss. Thus, gene therapies that restore functional retinal proteins by either replenishing unmutated genes or truncating mutated genes are needed. Coincidentally, the eye's accessibility and immune-privileged status along with major advances in gene identification and gene delivery systems heralded gene therapies for IRDs. Among these clinical trials, voretigene neparvovec-rzyl (Luxturna), an adeno-associated virus vector-based gene therapy drug, was approved by the FDA for treating patients with confirmed biallelic RPE65 mutation-associated Leber Congenital Amaurosis (LCA) in 2017. This review includes current IRD gene therapy clinical trials and further summarizes preclinical studies and therapeutic strategies for LCA, including adeno-associated virus-based gene augmentation therapy, 11-cis-retinal replacement, RNA-based antisense oligonucleotide therapy and CRISPR-Cas9 gene-editing therapy. Understanding the gene therapy development for LCA may accelerate and predict the potential hurdles of future therapeutics translation. It may also serve as the template for the research and development of treatment for other IRDs.

Deep learning and ensemble stacking technique for differentiating polypoidal choroidal vasculopathy from neovascular age-related macular degeneration.

Polypoidal choroidal vasculopathy (PCV) and neovascular age-related macular degeneration (nAMD) share some similarity in clinical imaging manifestations. However, their disease entity and treatment strategy as well as visual outcomes are very different. To distinguish these two vision-threatening diseases is somewhat challenging but necessary. In this study, we propose a new artificial intelligence model using an ensemble stacking technique, which combines a color fundus photograph-based deep learning (DL) model and optical coherence tomography-based biomarkers, for differentiation of PCV from nAMD. Furthermore, we introduced multiple correspondence analysis, a method of transforming categorical data into principal components, to handle the dichotomous data for combining with another image DL system. This model achieved a robust performance with an accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve of 83.67%, 80.76%, 84.72%, and 88.57%, respectively, by training nearly 700 active cases with suitable imaging quality and transfer learning architecture. This work could offer an alternative method of developing a multimodal DL model, improve its efficiency for distinguishing different diseases, and facilitate the broad application of medical engineering in a DL model design.

Smartphone-based diabetic macula edema screening with an offline artificial intelligence.

BACKGROUND: Diabetic macular edema (DME) is a sight-threatening condition that needs regular examinations and remedies. Optical coherence tomography (OCT) is the most common used examination to evaluate the structure and thickness of the macula, but the software in the OCT machine does not tell the clinicians whether DME exists directly. Recently, artificial intelligence (AI) is expected to aid in diagnosis generation and therapy selection. We thus develop a smartphone-based offline AI system that provides diagnostic suggestions and medical strategies through analyzing OCT images from diabetic patients at the risk of developing DME. METHODS: DME patients receiving treatments in 2017 at Taipei Veterans General Hospital were included in this study. We retrospectively collected the OCT images of these patients from January 2008 to July 2018. We established the AI model based on MobileNet architecture to classify the OCT images conditions. The confusion matrix has been applied to present the performance of the trained AI model. RESULTS: Based on the convolutional neural network with the MobileNet model, our AI system achieved a high DME diagnostic accuracy of 90.02%, which is comparable to other AI systems such as InceptionV3 and VGG16. We further developed a mobile-application based on this AI model available at https://aicl.ddns.net/DME.apk. CONCLUSION: We successful integrated an AI model into the mobile device to provide an offline method to provide the diagnosis for quickly screening the risk of developing DME. With the offline property, our model could help those nonophthalmological healthcare providers in offshore islands or underdeveloped countries.