Automated classification of angle-closure mechanisms based on anterior segment optical coherence tomography images via deep learning.

Purpose: To develop and validate deep learning algorithms that can identify and classify angle-closure (AC) mechanisms using anterior segment optical coherence tomography (AS-OCT) images. Methods: This cross-sectional study included participants of the Handan Eye Study aged ≥35 years with AC detected via gonioscopy or on the AS-OCT images. These images were classified by human experts into the following to indicate the predominant AC mechanism (ground truth): pupillary block, plateau iris configuration, or thick peripheral iris roll. A deep learning architecture, known as comprehensive mechanism decision net (CMD-Net), was developed to simulate the identification of image-level AC mechanisms by human experts. Cross-validation was performed to optimize and evaluate the model. Human-machine comparisons were conducted using a held-out and separate test sets to establish generalizability. Results: In total, 11,035 AS-OCT images of 1455 participants (2833 eyes) were included. Among these, 8828 and 2.207 images were included in the cross-validation and held-out test sets, respectively. A separate test was formed comprising 228 images of 35 consecutive patients with AC detected via gonioscopy at our eye center. In the classification of AC mechanisms, CMD-Net achieved a mean area under the receiver operating characteristic curve (AUC) of 0.980, 0.977, and 0.988 in the cross-validation, held-out, and separate test sets, respectively. The best-performing ophthalmologist achieved an AUC of 0.903 and 0.891 in the held-out and separate test sets, respectively. And CMD-Net outperformed glaucoma specialists, achieving an accuracy of 89.9 % and 93.0 % compared to 87.0 % and 86.8 % for the best-performing ophthalmologist in the held-out and separate test sets, respectively. Conclusions: Our study suggests that CMD-Net has the potential to classify AC mechanisms using AS-OCT images, though further validation is needed.

Efficacy and safety of penetrating canaloplasty versus ab externo canaloplasty for primary open-angle glaucoma: A randomized controlled trial.

PURPOSE: To report the 2-year efficacy and safety of penetrating canaloplasty versus ab externo canaloplasty for the treatment of primary open-angle glaucoma (POAG). SETTING: A single surgical site in China. DESIGN: This was a prospective, randomized controlled trial. POAG patients were randomly assigned to the penetrating canaloplasty or ab externo canaloplasty group. METHODS: This study enrolled POAG patients who underwent penetrating canaloplasty or ab externo canaloplasty randomly. Surgical success, intraocular pressure (IOP), number of glaucoma medications, and surgical complications were evaluated until 24 months post-operatively. Surgical success was defined as 6 mmHg ≤ IOP ≤21 mmHg with an IOP reduction ≥20%, which included qualified success (with or without medications) and complete success (without medications). RESULTS: A total of 52 eyes (45 patients) were randomly assigned to one of two groups: the penetrating canaloplasty group (PCP, n = 26) or the ab externo canaloplasty group (CP, n = 26). The probabilities of qualified success and complete success were 92.3% and 76.9%, respectively, in the PCP group and 64.1% and 52.1%, respectively, in the CP group at 24 months (p = 0.013, p = 0.042, log-rank test). The mean IOP decreased from 30.8 ± 10.7 and 28.6 ± 11.8 mmHg to 14.1 ± 3.3 mmHg in the PCP group and 22.1 ± 13.6 mmHg in the CP group at year two (p = 0.007). The PCP group also received fewer medications (0.2 ± 0.5) than did the CP group (0.7 ± 1.2) at year two (p = 0.038). Post-operative complications were similar, and the most common complications were transient IOP elevation and hyphema in the PCP group (42.3%, 46.2%) and the CP group (38.5%, 23.1%) (p > 0.05). CONCLUSIONS: Compared to ab externo canaloplasty, penetrating canaloplasty had a greater surgical success rate and better IOP reduction with a comparable rate of complications.

Mendelian randomization supports causal effects of inflammatory biomarkers on myopic refractive errors.

AIMS: To determine whether inflammatory biomarkers are causal risk factors for more myopic refractive errors. METHODS: Northern Sweden Population Health Study (NSPHS), providing inflammatory biomarkers data; UK Biobank, providing refractive errors data. 95,619 European men and women aged 40 to 69 years with available information of refractive errors and inflammatory biomakers. Inflammatory biomarkers including ADA, CCL23, CCL25, CD6, CD40, CDCP-1, CST5, CXCL-5, CXCL-6, CXCL-10, IL-10RB, IL-12B, IL-15RA, IL-18R1, MCP-2, MMP-1, TGF-ß1, TNF-ß, TWEAK and VEGF-A were exposures, and spherical equivalent (SE) using the formula SE = sphere + (cylinder/2) was outcome. RESULTS: Mendelian randomization analyses showed that each unit increase in VEGF-A, CD6, MCP-2 were causally related to a more myopic refractive errors of 0.040 D/pg.mL-1 (95% confidence interval 0.019 to 0.062; P = 2.031 × 10-4), 0.042 D/pg.mL-1 (0.027 to 0.057; P = 7.361 × 10-8) and 0.016 D/pg.mL-1 (0.004 to 0.028; P = 0.009), and each unit increase in TWEAK was causally related to a less myopic refractive errors of 0.104 D/pg.mL-1 (-0.152 to -0.055; P = 2.878 × 10-5). Tested by the MR-Egger, weighted median, MR-PRESSO, Leave-one-out methods, our results were robust to horizontal pleiotropy and heterogeneity in VEGF-A, MCP-2, CD6, but not in TWEAK. CONCLUSIONS: Our Mendelian Randomization analysis supported the causal effects of VEGF-A, MCP-2, CD6 and TWEAK on myopic refractive errors. These findings are important for providing new indicators for early intervention of myopia to make myopic eyesight threatening consequences less inevitable.

Separation of astragaloside IV from Astragalus membranaceus based on high-speed countercurrent chromatography in continuous injection mode.

INTRODUCTION: Astragaloside IV (AS-IV) is an index for the quality evaluation of the traditional Chinese medicine Astragalus and an important material basis for Astragalus to exert its medicinal effects, and it is difficult to obtain a single AS-IV by ordinary separation methods. OBJECTIVE: To find a new isolation method that can prepare AS-IV quickly and efficiently. METHODOLOGY: AS-IV was isolated from Astragalus membranaceus extract by high-speed countercurrent chromatography using a two-phase solvent system consisting of ethyl acetate/n-butanol/water (4.2:0.8:5, v/v) at a speed of 950 rpm at a flow rate of 2 mL/min using one of the high-speed countercurrent chromatographic sequential injection models developed during the previous study. RESULTS: Compared with the common countercurrent chromatographic separation, this separation method increased the injection volume and yield by 4-fold and 4.47-fold, respectively, with only about 1.2-fold increase in solvent consumption and separation time, and the purity was basically not reduced, and 55.9 mg of AS-IV, with a purity of 96.95%, was finally prepared from 400 mg of the crude extract in 240 min. CONCLUSION: The continuous injection mode of high-speed countercurrent chromatography was able to successfully prepare a large amount of AS-IV with high purity at one time.

Phacoemulsification combined with Kahook Dual Blade Goniotomy versus with Trabectome in the treatment of open angle glaucoma.

PURPOSE: To compare the surgical effectiveness and safety of phacoemulsification combined with KDB (Phaco-KDB) and with Trabectome (Phaco-Trabectome) at 6 months follow-up in patients with open-angle glaucoma (OAG) METHODS: This comparative case series was conducted at Beijing Tongren Hospital, including patients diagnosed with OAG who underwent Phaco-KDB from November 2021 to April 2022 and Phaco-Trabectome from April 2017 to December 2017. Surgical success was defined as an IOP reduction ≥ 20% or a postoperative IOP ≤ 21 mmHg. Kaplan-Meier methods were used to calculate cumulative rates of success among groups RESULTS: A total of 35 eyes from 29 patients were included in the analysis. At 6-month, Both groups exhibited a significant reduction in IOP and the number of IOP-lowering medications compared to preoperative (P=0.01 and P<0.01, respectively). There were no significant differences among groups in terms of reducing IOP and the number of IOP-lowering medications (all P values<0.05). In the Phaco-KDB and Phaco-Trabectome groups, 53.8% and 45.0% of patients achieved an IOP reduction of ≥ 20%, while 92.3% and 85% achieved a mean IOP ≤ 21 mmHg 6 months after surgery. The incidence of IOP spike was 20%, and 3 eyes (8.6%) needed further surgery to control the IOP CONCLUSIONS: Both Phaco-KDB and Phaco-Trabectome demonstrate a significant reduction in IOP and the number of IOP-lowering medications. Phaco-Trabectome appears to provide a more predictable postoperative course in the early postoperative period compared to Phaco-KDB, and the postoperative mean IOP is lower in Phaco-KDB compared to Phaco-Trabectome, despite not being statistically significant.

Deep learning for predicting circular retinal nerve fiber layer thickness from fundus photographs and diagnosing glaucoma.

Purpose: This study aimed to propose a new deep learning (DL) approach to automatically predict the retinal nerve fiber layer thickness (RNFLT) around optic disc regions in fundus photography trained by optical coherence tomography (OCT) and diagnose glaucoma based on the predicted comprehensive information about RNFLT. Methods: A total of 1403 pairs of fundus photographs and OCT RNFLT scans from 1403 eyes of 1196 participants were included. A residual deep neural network was trained to predict the RNFLT for each local image in a fundus photograph, and then a RNFLT report was generated based on the local images. Two indicators were designed based on the generated report. The support vector machines (SVM) algorithm was used to diagnose glaucoma based on the two indicators. Results: A strong correlation was found between the predicted and actual RNFLT values on local images. On three testing datasets, we found the Pearson r to be 0.893, 0.850, and 0.831, respectively, and the mean absolute error of the prediction to be 14.345, 17.780, and 19.250 µm, respectively. The area under the receiver operating characteristic curves for discriminating glaucomatous from healthy eyes was 0.860 (95 % confidence interval, 0.799-0.921). Conclusions: We established a novel local image-based DL approach to provide comprehensive quantitative information on RNFLT in fundus photographs, which was used to diagnose glaucoma. In addition, training a deep neural network based on local images to predict objective detail information in fundus photographs provided a new paradigm for the diagnosis of ophthalmic diseases.

Fundus Tessellation and Parapapillary Atrophy, as Ocular Characteristics of Spontaneously High Myopia in Macaques: The Non-Human Primates Eye Study.

Purpose: This study aimed to evaluate the ocular characteristics associated with spontaneously high myopia in adult nonhuman primates (NHPs). Methods: A total of 537 eyes of 277 macaques with an average age of 18.53 ± 3.01 years (range = 5-26 years), raised in a controlled environment, were included. We measured ocular parameters, including spherical equivalent (SE), axial length (AXL), and intraocular pressure. The 45-degree fundus images centered on the macula and the disc assessed the fundus tessellation and parapapillary atrophy (PPA). Additionally, optical coherence tomography (OCT) was used to measure the thickness of the retinal nerve fiber layer (RNFL). Results: The mean SE was -1.58 ± 3.71 diopters (D). The mean AXL was 18.76 ± 0.86 mm. The prevalence rate of high myopia was 17.7%. As myopia aggravated, the AXL increased (r = -0.498, P < 0.001). Compared with non-high myopia, highly myopic eyes had a greater AXL (P < 0.001), less RNFL thickness (P = 0.004), a higher incidence of PPA (P < 0.001), and elevated grades of fundus tessellation (P < 0.001). The binary logistic regression was performed, which showed PPA (odds ratio [OR] = 4.924, 95% confidence interval [CI] = 2.375-10.207, P < 0.001) and higher grades of fundus tessellation (OR = 1.865, 95% CI = 1.474-2.361, P < 0.001) were independent risk characteristics for high myopia. Conclusions: In NHPs, a higher grade of fundus tessellation and PPA were significant biomarkers of high myopia. Translational Relevance: The study demonstrates adult NHPs raised in conditioned rooms have a similar prevalence and highly consistent fundus changes with human beings, which strengthens the foundation for utilizing macaques as an animal model in high myopic studies.

Efficacy and Safety of Surgical Peripheral Iridectomy, Goniosynechialysis, and Goniotomy for Advanced Primary Angle-closure Glaucoma without Cataract: One-year Results of a Multicenter Study.

PRCIS: The combination of surgical peripheral iridectomy, goniosynechialysis, and goniotomy is a safe and effective surgical approach for advanced primary angle-closure glaucoma without cataract. PURPOSE: To evaluate the efficacy and safety of surgical peripheral iridectomy (SPI), goniosynechialysis (GSL), and goniotomy (GT) in advanced primary angle-closure glaucoma (PACG) eyes without cataract. PATIENTS AND METHODS: A prospective multicenter observational study was performed for patients who underwent combined SPI, GSL, and GT for advanced PACG without cataract. Patients were assessed before and after the operation. Complete success was defined as achieving intraocular pressure (IOP) between 6-18 mm Hg with at least a 20% reduction compared to baseline, without the use of ocular hypotensive medications or reoperation. Qualified success adopted the same criteria but allowed medication use. Factors associated with surgical success were analyzed using logistic regression. RESULTS: A total of 61 eyes of 50 advanced PACG were included. All participants completed 12 months of follow-up. Thirty-six eyes (59.0%) achieved complete success, and 56 eyes (91.8%) achieved qualified success. Preoperative and postsurgical at 12 months mean IOPs were 29.7±7.7 and 16.1±4.8 mm Hg, respectively. The average number of ocular hypotensive medications decreased from 1.9 to 0.9 over 12 months. The primary complications included IOP spike (n=9), hyphema (n=7), and shallow anterior chamber (n=3). Regression analysis indicated that older age (odds ratio [OR]=1.09; P=0.043) was positively associated with complete success, while a mixed angle closure mechanism (OR=0.17; P=0.036) reduced success rate. CONCLUSIONS: The combination of SPI, GSL, and GT is a safe and effective surgical approach for advanced PACG without cataract. It has great potential as a first-line treatment option for these patients.

Impact of Peripheral Anterior Synechiae on the Outcome of Combined Phacoemulsification, Goniosynechialysis, and Goniotomy for Primary Angle Closure Glaucoma and Cataract: A Multicenter Observational Study.

PRCIS: The combination of phacoemulsification, goniosynechialysis and goniotomy is an effective treatment for primary angle closure glaucoma patients with cataract, and this is not linked to the extent of preoperative peripheral anterior synechiae. PURPOSE: To evaluate the impact of the extent of peripheral anterior synechiae (PAS) on the effectiveness and safety of combined phacoemulsification (PEI), goniosynechialysis (GSL), and goniotomy (GT) in eyes with primary angle closure glaucoma (PACG) and cataract. PATIENTS AND METHODS: This study included patients diagnosed with PACG and cataracts who underwent combined PEI and 120 degrees GSL plus GT (PEI+GSL+GT) between April 2020 and October 2022 at 10 ophthalmic institutes. Eligible patients were divided into 3 groups based on the extent of PAS: 180°≤PAS<270°, 270°≤PAS<360°, and PAS=360°. Data on intraocular pressure (IOP), the number of ocular hypotensive medications, and complications were collected and compared. The study defined complete success as postoperative IOP within the 6-18 mm Hg range and a 20% reduction from baseline without the use of topical medications. Qualified success was defined in the same way as complete success, but it allowed for the use of ocular hypotensive medications. RESULTS: Three hundred four eyes of 283 patients were included. The mean follow-up was 12.50±1.24 months. All groups experienced a significant reduction in IOP after the surgery ( P <0.05). There were no significant differences in final IOP, number of medications, and cumulative complete and qualified success rates among the 3 groups ( P >0.05). The groups with 270°≤PAS<360°had a higher frequency of hyphema compared with 180°≤PAS<270° ( P = 0.044). CONCLUSIONS: PEI+GSL+GT has proven to be an effective treatment for PACG with cataracts over a 1 year period. However, the outcome was not correlated with the preoperative extent of PAS.

Lhx2 promotes axon regeneration of adult retinal ganglion cells and rescues neurodegeneration in mouse models of glaucoma.

The axons of retinal ganglion cells (RGCs) form the optic nerve, transmitting visual information from the eye to the brain. Damage or loss of RGCs and their axons is the leading cause of visual functional defects in traumatic injury and degenerative diseases such as glaucoma. However, there are no effective clinical treatments for nerve damage in these neurodegenerative diseases. Here, we report that LIM homeodomain transcription factor Lhx2 promotes RGC survival and axon regeneration in multiple animal models mimicking glaucoma disease. Furthermore, following N-methyl-D-aspartate (NMDA)-induced excitotoxicity damage of RGCs, Lhx2 mitigates the loss of visual signal transduction. Mechanistic analysis revealed that overexpression of Lhx2 supports axon regeneration by systematically regulating the transcription of regeneration-related genes and inhibiting transcription of Semaphorin 3C (Sema3C). Collectively, our studies identify a critical role of Lhx2 in promoting RGC survival and axon regeneration, providing a promising neural repair strategy for glaucomatous neurodegeneration.

Proportion and risk factors of zonulopathy in patients with age-related cataract.

Purpose: To investigate the proportion of zonulopathy in patients with age-related cataract, and further explore demographics and ocular characteristics, as well as potential risk factors. Methods: Hospital-based, observational, cross-sectional study. We enrolled consecutive patients who were 45 years or older and diagnosed with age-related cataract and underwent surgery between October 2022 and April 2023 at the Division of Cataract, Beijing Tongren Hospital. Zonulopathy was diagnosed based on intraoperative signs. We calculated the total proportion, age, and gender specific proportions of zonulopathy. We compared the demographic and ocular characteristics between the cases with and without zonulopathy. Univariate and multivariate logistic regression analyses were employed to determine the risk factors associated with the presence of zonulopathy in patients with age-related cataract. Results: A total of 640 age-related cataract patients with a median age of 70.0 (64.0-77.0) were enrolled. Zonulopathy was diagnosed intraoperatively in 70 patients (10.9%). Compared with the patients having no zonulopathy, those with zonulopathy were likely to be older (P < 0.001), have a shallower central ACD (P < 0.001), a thicker lens (P < 0.001) and a shorter AL (P = 0.010). Logistic regression analyses showed that the risk predictors associated with the presence of zonulopathy in patients with age-related cataract were older age (OR, 1.042; P = 0.035) and shallower central ACD (OR, 0.834; P < 0.001). Conclusion: Zonulopathy in age-related cataract patients is not an uncommon finding. Clinicians should be mindful of zonulopathy in patient population with advanced age and shallower ACD.

Performance of anterior segment OCT-based algorithms in the opportunistic screening for primary angle-closure disease.

Purpose: This study aimed to investigate the performance of deep learning algorithms in the opportunistic screening for primary angle-closure disease (PACD) using combined anterior segment parameters. Methods: This was an observational, cross-sectional hospital-based study. Patients with PACD and healthy controls who underwent comprehensive eye examinations, including gonioscopy and anterior segment optical coherence tomography (ASOCT) examinations under both light and dark conditions, were consecutively enrolled from the Department of Ophthalmology at the Beijing Tongren Hospital between November 2020 and June 2022. The anterior chamber, anterior chamber angle, iris, and lens parameters were assessed using ASOCT. To build the prediction models, backward logistic regression was utilized to select the variables to discriminate patients with PACD from normal participants, and the area under the receiver operating characteristic curve was used to evaluate the efficacy of the opportunistic screening. Results: The data from 199 patients (199 eyes) were included in the final analysis and divided into two groups: PACD (109 eyes) and controls (90 eyes). Angle opening distance at 500 µm, anterior chamber area, and iris curvature measured in the light condition were included in the final prediction models. The area under the receiver operating characteristic curve was 0.968, with a sensitivity of 91.74 % and a specificity of 91.11 %. Conclusion: ASOCT-based algorithms showed excellent diagnostic performance in the opportunistic screening for PACD. These results provide a promising basis for future research on the development of an angle-closure probability scoring system for PACD screening.

Zonular instability-associated morphologic features in eyes with primary angle closure disease using the swept-source anterior segment - optical coherence tomography system.

BACKGROUND: This study aims to investigate the morphologic features of the crystalline lens in Primary Angle Closure Disease (PACD) patients with zonular instability during cataract surgery using the swept-source CASIA 2 Anterior Segment-Optical Coherence Tomography (AS-OCT) system. METHODS: A total of 398 eyes (125 PACD eyes with zonular instability, 133 PACD eyes with zonular stability, and 140 cataract patient controls) of 398 patients who underwent cataract surgery combined or not glaucoma surgery between January 2021 and January 2023 were enrolled. The crystalline lens parameters were measured by CASIA2 AS-OCT. Then, logistic regression was performed to evaluate the risk factors associated with zonular instability. RESULTS: The results revealed that PACD eyes had a more anterior lens equator position, a steeper anterior curvature of lens, shorter Axial Length (AL), shallower Anterior Chamber Distance (ACD), higher Lens Vault (LV) and thicker Lens Thickness (LT), when compared to eyes in the cataract control group. Furthermore, PACD eyes in the zonular instability group had steeper front R, front Rs and Front Rf, flatter back Rf, thicker lens anterior part thickness, higher lens anterior-to-posterior part thickness ratios, shallower ACD, and greater LV, when compared to PACD eyes with zonular stability. The logistic regression analysis, which was adjusted for age and gender, revealed that zonular instability was positively correlated with anterior part thickness, lens anterior-to-posterior part thickness ratio, and LV, but was negatively correlated with lens anterior radius and ACD. CONCLUSION: Steeper anterior curvature, increased lens anterior part thickness, higher anterior-to-posterior part thickness ratio, shallower ACD, and greater LV are the anatomic features of PACD eyes associated with zonular instability.

Association of Gene Polymorphisms with Normal Tension Glaucoma: A Systematic Review and Meta-Analysis.

BACKGROUND: Normal tension glaucoma (NTG) is becoming a more and more serious problem, especially in Asia. But the pathological mechanisms are still not illustrated clearly. We carried out this research to uncover the gene polymorphisms with NTG. METHODS: We searched in Web of Science, Embase, Pubmed and Cochrane databases for qualified case-control studies investigating the association between single nucleotide polymorphisms (SNPs) and NTG risk. Odds ratios (ORs) and 95% confidence intervals (CIs) for each SNP were estimated by fixed- or random-effect models. Sensitivity analysis was also performed to strengthen the reliability of the results. RESULTS: Fifty-six studies involving 33 candidate SNPs in 14 genetic loci were verified to be eligible for our meta-analysis. Significant associations were found between 16 SNPs (rs166850 of OPA1; rs10451941 of OPA1; rs735860 of ELOVL5; rs678350 of HK2; c.603T>A/Met98Lys of OPTN; c.412G>A/Thr34Thr of OPTN; rs10759930 of TLR4; rs1927914 of TLR4; rs1927911 of TLR4; c.*70C>G of EDNRA; rs1042522/-Arg72Pro of P53; rs10483727 of SIX1-SIX6; rs33912345 of SIX1-SIX6; rs2033008 of NCK2; rs3213787 of SRBD1 and c.231G>A of EDNRA) with increased or decreased risk of NTG. CONCLUSIONS: In this study, we confirmed 16 genetic polymorphisms in 10 genes (OPA1, ELOVL5, HK2, OPTN, TLR4, EDNRA, P53, NCK2, SRBD1 and SIX1-SIX6) were associated with NTG.

Natural History and Risk Factors for Glaucoma Progression in Chinese Patients With Normal-Tension Glaucoma.

Purpose: To characterize the natural history of normal-tension glaucoma (NTG) in Chinese patients. Methods: The prospective observational cohort study included patients with untreated NTG with a minimum follow-up of 2 years. Functional progression was defined by visual field (VF) deterioration, while structural progression was characterized by thinning of the retinal nerve fiber layer (RNFL) or ganglion cell inner plexiform layer (GCIPL). Results: Among 84 participants (mean age, 60.5 years; mean deviation, -5.01 decibels [dB]) with newly diagnosed NTG followed for an average of 69.7 months, 63.1% progressed during the observation period. Specifically, 29.8% progressed by VF, and 48.8% progressed by either RNFL or GCIPL. In Cox proportional hazards analysis, disc hemorrhage (hazard ratio [HR], 2.82; 95% confidence interval [CI], 1.48-5.35), female gender (HR, 1.98; 95% CI, 1.08-3.62), and mean IOP during the follow-up period (HR, 1.14 per mm Hg; 95% CI, 1.00-1.31) were significant predictors of glaucomatous progression. Additionally, longer axial length (AL; HR, 0.57 per millimeter; 95% CI, 0.35-0.94) was protective against VF progression faster than -0.50 dB/y, and higher minimum diastolic blood pressure (DBP; HR, 0.96 per mm Hg; 95% CI, 0.92-1.00) was protective against structural progression. Conclusions: Nearly two-thirds of untreated Chinese patients with NTG progressed over an average follow-up of 70 months by VF, RNFL, or GCIPL. Disc hemorrhage, female gender, higher mean IOP, shorter AL, and lower minimum DBP were significant predictors for disease progression.

Efficacy of far infrared functional glasses in the treatment of meibomian gland dysfunction-related dry eye.

Meibomian gland dysfunction (MGD)-related dry eye disease (DED) is a significant subtype of DED. In this research, we investigate the effectiveness of far infrared (FIR) functional glasses in the treatment of MGD-related DED. According to the TFO DEWS II diagnostic criteria, 61 eyes with MGD-related DED were included. All participants wore functional FIR glasses throughout the day for a period of 4 weeks and were followed up three times during the treatment. All subjects were followed up thoroughly in accordance with the DED clinical examination procedure. Ultimately, the treatment's impact was assessed. We found the Visual Analogue Scale and Ocular Surface Disease Index scores after FIR treatment were significantly lower than the baseline values (p < 0.05). Compared with the baseline, fluorescein tear breakup time and corneal fluorescein staining score after FIR treatment were significantly improved (p < 0.05). The eyelid margin signs, meibum quality, and meibomian gland expressibility after the 4-week treatment were significantly better than those at baseline (p < 0.05). We can see that wearing the FIR functional glasses significantly relieves the symptoms and signs of patients. We believe FIR therapy could be considered as a new method of MGD-related DED.

Anomaly Detection for Medical Images Using Heterogeneous Auto-Encoder.

Anomaly detection is an important task for medical image analysis, which can alleviate the reliance of supervised methods on large labelled datasets. Most existing methods use a pixel-wise self-reconstruction framework for anomaly detection. However, there are two challenges of these studies: 1) they tend to overfit learning an identity mapping between the input and output, which leads to failure in detecting abnormal samples; 2) the reconstruction considers the pixel-wise differences which may lead to an undesirable result. To mitigate the above problems, we propose a novel heterogeneous Auto-Encoder (Hetero-AE) for medical anomaly detection. Our model utilizes a convolutional neural network (CNN) as the encoder and a hybrid CNN-Transformer network as the decoder. The heterogeneous structure enables the model to learn the intrinsic information of normal data and enlarge the difference on abnormal samples. To fully exploit the effectiveness of Transformer in the hybrid network, a multi-scale sparse Transformer block is proposed to trade off modelling long-range feature dependencies and high computational costs. Moreover, the multi-stage feature comparison is introduced to reduce the noise of pixel-wise comparison. Extensive experiments on four public datasets (i.e., retinal OCT, chest X-ray, brain MRI, and COVID-19) verify the effectiveness of our method on different imaging modalities for anomaly detection. Additionally, our method can accurately detect tumors in brain MRI and lesions in retinal OCT with interpretable heatmaps to locate lesion areas, assisting clinicians in diagnosing abnormalities efficiently.

Long-term outcomes of anti-vascular endothelial growth factor therapy with and without posterior scleral reinforcement on myopic maculopathy in myopic choroidal neovascularization eyes.

BACKGROUND: Anti-vascular endothelial growth factor (anti-VEGF) therapy is used for myopic choroidal neovascularization (mCNV). Patchy chorioretinal atrophy (pCRA) enlargement has been reported in mCNV cases associated with vision loss. Our aim was to compare the long-term effectiveness of anti-VEGF therapy alone versus anti-VEGF followed by posterior scleral reinforcement (PSR) in controlling myopic maculopathy in mCNV eyes. METHODS: We performed a retrospective review of the medical records of 95 high myopia patients (refractive error ≥ 6.00 diopters, axial length ≥ 26.0 mm) with mCNV. Patients were treated with anti-VEGF alone (group A) or anti-VEGF followed by PSR (group B). The following data were collected: refractive error, best corrected visual acuity (BCVA), ophthalmic fundus examination, ocular coherence tomography and ocular biometry at 12 and 24 months pre- and postoperatively. The primary outcomes were changes in pCRA and BCVA. RESULTS: In 26 eyes of 24 patients, the mean pCRA size significantly increased from baseline (0.88 ± 1.69 mm2) to 12 months (1.57 ± 2.32 mm2, t = 3.249, P = 0.003) and 24 months (2.17 ± 2.79 mm2, t = 3.965, P = 0.001) postoperatively. The increase in perilesional pCRA in group B (n = 12) was 98.2% and 94.2% smaller than that in group A (n = 14) at 12 and 24 months (Beta 0.57 [95% CI 0.01, 191 1.13], P = 0.048). In group B, 7 eyes (58.3%) gained more than 2 lines of BCVA compared with only 4 eyes (28.6%) in group A at 24 months. CONCLUSION: Anti-VEGF therapy followed by PSR achieved better outcomes than anti-VEGF therapy alone in controlling the development of myopic maculopathy in mCNV and may constitute a better treatment option by securing a better long-term VA outcome.

PatchCL-AE: Anomaly detection for medical images using patch-wise contrastive learning-based auto-encoder.

Anomaly detection is an important yet challenging task in medical image analysis. Most anomaly detection methods are based on reconstruction, but the performance of reconstruction-based methods is limited due to over-reliance on pixel-level losses. To address the limitation, we propose a patch-wise contrastive learning-based auto-encoder for medical anomaly detection. The key contribution is the patch-wise contrastive learning loss that provides supervision on local semantics to enforce semantic consistency between corresponding input-output patches. Contrastive learning pulls corresponding patch pairs closer while pushing non-corresponding ones apart between input and output, enabling the model to learn local normal features better and improve discriminability on anomalous regions. Additionally, we design an anomaly score based on local semantic discrepancies to pinpoint abnormalities by comparing feature difference rather than pixel variations. Extensive experiments on three public datasets (i.e., brain MRI, retinal OCT, and chest X-ray) achieve state-of-the-art performance, with our method achieving over 99% AUC on retinal and brain images. Both the contrastive patch-wise supervision and patch-discrepancy score provide targeted advancements to overcome the weaknesses in existing approaches.