Cataract Grading Research Articles

Protective Effects of Piceatannol against Selenite-Induced Cataract and Oxidative Damage in Rats

Purpose This study aimed to investigate the protective effects of piceatannol (PIC) on selenite-induced cataracts in Sprague-Dawley rats and explore its therapeutic effects as an antioxidant. Methods Thirty-two eight-day-old rat pups were randomly divided into four groups, with eight pups in each of them. Group 1, as the control group, was injected with the same amount of saline, while Groups 2–4 were administered with sodium selenite (3.46 mg/kg) subcutaneously into the neck on postpartum day 10 for cataract induction. Without further treatment, Group 2 served as the control model, while Groups 3 and 4 (low- and high-dose PIC-treated) had intraperitoneal piceatannol from day 8 to day 17 at doses of 10 mg/kg and 20 mg/kg, respectively. On postpartum day 17, after the last injection, the rat pups were examined for cataract grade by slit lamp, and the lenses of every group were isolated for oxidative damage indicators and further analysis. SRA01/04 cells were exposed to 600 μM H2O2 for 24 hours with or without pretreatment with 10μМ piceatannol. Cell viability was tested by CCK-8 assay and cell apoptosis was evaluated by AnnexinV-PE/7AAD assay. Results This study determined that compared with the model group, the degree of lens opacity was significantly reduced in PIC-treated groups. The histopathological damage of the lenses in the PIC-treated groups improved compared to the model group. There were fewer signs of lesions, such as vacuoles and atrophy. The biochemical results indicated that malondialdehyde (MDA) content of the PIC-treated groups were downregulated and the antioxidant enzyme activities (GSH and catalase) and antioxidant status (SOD) were upregulated compared with the model group. In vitro, piceatannol significantly restored cell viability and cell apoptosis under H2O2 injury. Conclusion Pretreatment with piceatannol may achieve a protective effect on cataract development through upregulating antioxidant enzyme activity.

Morphological variations influencing the outcomes in posterior polar cataract.

Purpose:To study the intraoperative complications and postoperative clinical outcomes in different types of posterior polar cataract (PPC) following phacoemulsification, based on morphological classification.Methods: All consecutive patients with PPC who underwent phacoemulsification during the study period from 2016 to 2019 were included and sub-grouped based on the morphological characteristics according to Daljit Singh’s classification. Intraoperative complications such as posterior capsular rupture (PCR), vitreous loss, nucleus drop, and Postoperative best-corrected visual acuity (BCVA) at day 1 and day 30 were documented.Results: A total of 388 eyes of 380 patients were included. Eighty nine (22.9%) eyes belonged to type 1, 135 (34.8%) belonged to type 2, 8 (2.1%) belonged to type 3, and 156 (40.2%) belonged to type 4. Thirty-five (9.3%) eyes had intraoperative PCR, with vitreous loss in 21 (60%) eyes, and nucleus/cortex drop in 5 (1.3%) eyes. Six (75%) eyes of type 3, 14 (10.04%) eyes of type 2, 12 (17.7%) eyes of type 4, and 3 (3.4%) eyes of type 1 PPC had PCR. PCR occurred more during the emulsification of the nucleus (18 cases, 51.4%). A significant correlation was seen between intraoperative PCR and type of PPC with a higher incidence in type 3 (P < 0.001). BCVA was found to be significantly worse on day 1 among patients with PCR compared to those who did not and improved well by day 30.Conclusion: PPC morphology is significantly co-related with the occurrence of PCR, emphasizing the need for careful grading of posterior polar cataracts in predicting the risk of intraoperative complications.

POST-OPERATIVE VISUAL PROGNOSIS IN SENILE CATARACT IN TOBACCO CONSUMERS: COMMUNITY BASED STUDY IN LUCKNOW, UTTAR PRADESH

Tobacco use is a leading cause of chronic diseases in India. It kills almost 1.3 million people every year. The country is the second largest producer and consumer of cigarettes. The use of tobacco is very easy to start and is available at very low prices. One of the biggest threats to public health is tobacco use. It leads to the deaths of thousands of people and has a heavy social and economic cost. There are around 267 million tobacco users in India. The most common type of tobacco used by Indians is smokeless tobacco. Khaini, which is a tobacco mixture used by almost every ninth adult, is followed by bidi smoking and gutkha tobacco. According to the Global Adult tobacco Survey, around 11% of Indian adults smoke cigarettes. This is a community-based study involving 626 patients having Immature cataracts with H/O chronic tobacco use from rural population of central Uttar Pradesh in North India coming from low Socio-economic strata with no major Ocular pathology who underwent Cataract surgery (Manual Small incision cataract surgery/Phacoemulsification) with best input in form of surgical techniques &amp; skills, equipment’s material used and uncomplicated surgeries. Serum Vitamin B6, Folic acid and B12 levels were checked to assess nutritional status of these patients. Best corrected visual acuity (BCVA) preoperatively as well as postoperatively was disproportionate to the grade of cataract and best surgical input. The visual outcome in these patients was not very good. BCVA (Best corrected visual acuity) is 70% poor and only 30% is good. There was color vision deficiency and Visual field defects in most of the patients.

Multiple Bilobed Orbital Schwannomas: A Rare Sight.

A 60-year-old lady presented with long-standing progressive, non-axial proptosis of 8-year duration associated with superior sulcus fullness, significant upper and lower eyelid retraction, and an early grade of cataract in the OD (Fig. A and B). Visual acuity had reduced to 20/100 in the OD with choroidal folds on the posterior pole on fundus examination. The other eye showed a mild grade of upper eyelid retraction with an early grade of cataract with the normal posterior segment. CT-scan of the orbit revealed 2 well-defined heterogenous ovoid lesions in the right intraconal space indenting the globe (dotted lines, Fig. C and D). The optic nerve was made out separately in few cuts. She was planned for an excision biopsy of the orbit via the superior lid crease incision. There were 2 separate lesions an intact capsule. The lesions were removed in toto with the aid of a cryoprobe one after the other. Both the excised lesions were bilobed having different dimensions (*, Fig. E and F). Histopathology showed solid areas within the 2 well-encapsulated solid cystic lesions which were hypercellular with Antoni type A and hypocellular with Antoni type B like areas. The hypercellular areas showed spindle cells with tapering ends and elongated nuclei whereas the hypocellular areas showed numerous foamy macrophages consistent with the diagnosis of Orbital Schwannoma. The proptosis resolved with improvement in the visual acuity to 20/50 at 6 weeks. Orbital schwannomas are known to be isolated in presentation and most commonly arise from the sensory branch of the ophthalmic division of the trigeminal nerve. Bilobed schwannomas and more so, multiple in the same orbit are a rare occurrence. To the best of our knowledge, there has been no report of multiple orbital intraconal bilobed schwannomas in literature.FIG.: Multiple bilobed orbital schwannomas.

RONC-09. The comparison of dosimetric parameters for predicting radiation-induced cataract in pediatric patients

OBJECTIVE: The lens dose constraint for pediatric patients was still unknown due to conflicting data of dosimetric parameter. The aim of this study was to compare predictive ability for radiation-induced cataract between the maximum point dose of lens (Lens Dmax) ≥7 Gy, lens mean dose (Lens Dmean) ≥7 Gy, Lens Dmax ≥10 Gy, and Lens Dmean ≥10 Gy. METHOD: Patients 3-18 years received cranial irradiation or radiation therapy at head and neck area with three-dimentional conformal radiation therapy (3DCRT), intensity modulated radiation therapy (IMRT), or volumetric modulated arc therapy (VMAT) between 2010 and 2019 at our institute were included. Patients who have no eye exam before radiation or within 6 months of radiation (baseline) and/or have no follow-up eye examination after complete radiation >6 months (follow-up) were excluded. Receiver operating characteristic (ROC) curves were used to identify the dosimetric parameter of potential predictors and to access their predictability. Univariate and multivariate analyses were performed using cox regression analysis to identify correlation between potential factors and cataract. RESULTS: Sixty-three patients (122 eyes) were analyzed. Cataracts were detected in 14 eyes (11.5%). The median follow-up time was 4 years (range 0.5-10 years). The median time to develop cataract was 2.5 years (range 0.3-7 years). Three (21.4%) patients developed cataract grade ≥3. Lens Dmean ≥10 Gy had highest predictive ability for predicting radiation-induced cataract in pediatric patients. The area under the ROC curve (AUC) were 0.591 for Dmax ≥ 7 Gy, 0.597 for Dmean ≥ 7 Gy, 0.642 for Dmax ≥ 10 Gy, and 0.698 for Dmean ≥ 10 Gy. Univariate analysis showed significant effect of age, diagnosis, and Lens Dmean on cataract formation. On multivariate analysis, cataract remained significantly predicted by diagnosis and Lens Dmean. CONCLUSION: Lens Dmean ≥10 Gy had highest predictive ability for predicting radiation-induced cataract in pediatric patients.

Reasons for delay in cataract surgery in patients with advanced cataracts during the COVID-19 pandemic.

Purpose:To analyze the reasons for delay in cataract surgery in patients with advanced cataracts during the COVID-19 pandemic.Methods:This was a prospective, cross-sectional, multicenter questionnaire study which included patients with mature cataract, nuclear sclerotic cataract grade IV, and cataracts with best corrected visual acuity (BCVA) <5/60, during the COVID-19 pandemic from December 2020 to April 2021. Reasons for delay in presentation to the hospital were analyzed.Results:One thousand four hundred seventy two patients were recruited with advanced cataracts. Absence of ophthalmic care nearby (44.2%), lack of awareness regarding elective surgeries (42.6%), lack of public transportation (37%), fear of contracting COVID-19 (23.4%), and waiting for outreach camps (20.4%) were found to be the reasons behind the delay in cataract surgery. 53.7% of the patients had worsening of defective vision and 55.3% of them had difficulty in carrying out activities of family living. 30.8% of the patients faced difficulty in commuting and 8.4% of the patients suffered a fall during this pandemic due to worsening of the visual acuity.Conclusion:The lockdown imposed during the pandemic has created a significant backlog of patients who are progressing to advanced cataracts due to lack of ophthalmic care nearby, lack of awareness regarding elective surgeries, lack of public transportation, and no outreach camps. Proactive measures to deal with this backlog are of utmost need to prevent blindness due to cataract.

Oxysterol Compounds in Mouse Mutant αA- and αB-Crystallin Lenses Can Improve the Optical Properties of the Lens.

PurposeTo investigate how cataract-linked mutations affect the gradient refractive index (GRIN) and lens opacification in mouse lenses and whether there is any effect on the optics of the lens from treatment with an oxysterol compound.MethodsA total of 35 mice including wild-type and knock-in mutants (Cryaa-R49C and Cryab-R120G) were used in these experiments: 26 mice were treated with topical VP1-001, an oxysterol, in one eye and vehicle in the other, and nine mice were untreated controls. Slit lamp biomicroscopy was used to analyze the lens in live animals and to provide apparent cataract grades. Refractive index in the lenses of 64 unfixed whole mouse eyes was calculated from measurements with X-ray phase tomography based on X-ray Talbot interferometry with a synchrotron radiation source.ResultsHeterozygous Cryaa-R49C lenses had slightly irregularly shaped contours in the center of the GRIN and distinct disturbances of the gradient index at the anterior and posterior poles. Contours near the lens surface were denser in homozygous Cryab-R120G lenses. Treatment with topical VP1-001, an oxysterol, showed an improvement in refractive index profiles in 61% of lenses and this was supported by a reduction in apparent lens opacity grade by 1.0 in 46% of live mice.ConclusionsThese results indicate that α-crystallin mutations alter the refractive index gradient of mouse lenses in distinct ways and suggest that topical treatment with VP1-001 may improve lens transparency and refractive index contours in some lenses with mutations.

Lens Opacities Classification System III-based artificial intelligence program for automatic cataract grading.

To establish and validate an artificial intelligence (AI)-assisted automatic cataract grading program based on the Lens Opacities Classification System III (LOCS III). Eye and Ear, Nose, and Throat Hospital, Fudan University, Shanghai, China. AI training. Advanced deep-learning algorithms, including Faster R-CNN and ResNet, were applied to the localization and analysis of the region of interest. An internal dataset from the EENT Hospital of Fudan University and an external dataset from the Pujiang Eye Study were used for AI training, validation, and testing. The datasets were automatically labeled on the AI platform regarding the capture mode and cataract grading based on the LOCS III. The AI program showed reliable capture mode recognition, grading, and referral capability for nuclear and cortical cataract grading. In the internal and external datasets, 99.4% and 100% of automatic nuclear grading, respectively, had an absolute prediction error of ≤1.0, with a satisfactory referral capability (area under the curve [AUC]: 0.983 for the internal dataset; 0.977 for the external dataset); 75.0% (internal dataset) and 93.5% (external dataset) of the automatic cortical grades had an absolute prediction error of ≤1.0, with AUCs of 0.855 and 0.795 for referral, respectively. Good consistency was observed between automatic and manual grading when both nuclear and cortical cataracts were evaluated. However, automatic grading of posterior subcapsular cataracts was impractical. The AI program proposed in this study showed robust grading and diagnostic performance for both nuclear and cortical cataracts, based on LOCS III.

Artificial intelligence in cataract: What’s new?

Artificial intelligence (AI) is a technological advancement that provides thinking and processing capacity to machines. It is a complex technology with multiple algorithms and formulas. AI has transformed the face of several industries, including the healthcare sector. Ophthalmology being a highly technology-driven branch of healthcare can benefit vastly from the application of AI. Newer technologies are cropping up with each passing day to enhance our diagnostic and management modalities. From huge machines, now, AI has even come down to applications on the small screen of smartphones. Through this study, we summarise the various AI-driven developments in the world of cataract that have occurred in the past 3 years. Ranging from cataract detection, cataract grading, IOL power calculation, to acting as an aid in the surgical arena, this study intends to cover all recent AI-based innovations and advancements.

Prevalence and risk factors for cataracts in the Lao People's Democratic Republic: The Vientiane Eye Study.

Purpose:To determine the prevalence and risk factors for cataracts in the Vientiane Province.Methods:We conducted a population-based study of 1264 participants aged ≥40 years of age from urban and rural areas of Vientiane Province. Data collection included demographic information, smoking history, body mass index, blood pressure, history of trauma and dilated lens examination using the World Health Organization WHO Simplified Cataract Grading System. Aphakic and pseudophakic eyes were included as operated cataracts for statistical analysis.Results:The mean age of the 1264 participants was 57.6 years. The prevalence of any cataract including operated eyes was 46.8% (95% CI: 44.1 – 49.6%): 36.9% nuclear, 21.7% cortical and 10.1% posterior subcapsular cataracts.Conclusion:The prevalence of cataract in the Vientiane Eye Study is similar compared to the prevalence reported in other studies from Asian regions; however, the median age in this study was low, reflecting the age group of the population and the rapid urbanisation occurring in the Lao People’s Democratic Republic. A significant association for any cataract was found with elevated blood pressure >148mmHg (OR2.48, 95%CI:1.55 - 3.97, P < 0.01), increasing age (OR1.19, 95%CI:1.17 - 1.22, P < 0.001) and rural inhabitants for cortical cataract (OR1.99, 95%CI:1.37 - 2.90, P < 0.001). An inverse relationship between rural inhabitants with any cataract and nuclear cataract was found (OR 0.63, 95%CI: 0.45 – 0.89, P < 0.01 and OR 0.42, 95%CI: 0.31 - 0.59, P < 0.001) respectively.Nevertheless, cataract remains a high prevalence disease in this population.

Evolution and Applications of Artificial Intelligence to Cataract Surgery.

TopicDespite significant recent advances in artificial intelligence (AI) technology within several ophthalmic subspecialties, AI seems to be underutilized in the diagnosis and management of cataracts. In this article, we review AI technology that may soon become central to the cataract surgical pathway, from diagnosis to completion of surgery.Clinical RelevanceThis review describes recent advances in AI in the preoperative, intraoperative, and postoperative phase of cataract surgery, demonstrating its impact on the pathway and the surgical team.MethodsA systematic search of PubMed was conducted to identify relevant publications on the topic of AI for cataract surgery. Articles of high quality and relevance to the topic were selected.ResultsBefore surgery, diagnosis and grading of cataracts through AI-based image analysis has been demonstrated in several research settings. Optimal intraocular lens (IOL) power to achieve the desired postoperative refraction can be calculated with a higher degree of accuracy using AI-based modeling compared with traditional IOL formulae. During surgery, innovative AI-based video analysis tools are in development, promoting a paradigm shift for documentation, storage, and cataloging libraries of surgical videos with applications for teaching and training, complication review, and surgical research. Situation-aware computer-assisted devices can be connected to surgical microscopes for automated video capture and cloud storage upload. Artificial intelligence-based software can provide workflow analysis, tool detection, and video segmentation for skill evaluation by the surgeon and the trainee. Mixed reality features, such as real-time intraoperative warnings, may have a role in improving surgical decision-making with the key aim of reducing complications by recognizing surgical risks in advance and alerting the operator to them. For the management of patient flow through the pathway, AI-based mathematical models generating patient referral patterns are in development, as are simulations to optimize operating room use. In the postoperative phase, AI has been shown to predict the posterior capsule status with reasonable accuracy, and can therefore improve the triage pathway in the treatment of posterior capsular opacification.DiscussionArtificial intelligence for cataract surgery will be as relevant as in other subspecialties of ophthalmology and will eventually constitute a future cornerstone for an enhanced cataract surgery pathway.

Prospective Comparative Study Investigating Agreement between Tele-Ophthalmology and Face-to-face Consultations in Patients Presenting with Chronic Visual Loss.

IntroductionThis study aims to investigate the diagnostic accuracy of store-and-forward tele-ophthalmology consultations for non-diabetic patients, aged 40 and above, presenting with vision impairment of 3 months or more, in terms of cataracts, glaucoma, and age-related macular degeneration.MethodsThis is a prospective comparative study. Enrolled subjects were independently assessed by both tele-ophthalmology and face-to-face assessment. Agreement level between the two modalities for diagnosis and severity were compared using kappa statistic. Diagnostic accuracy of tele-ophthalmology was determined using the face-to-face consultation serving as the gold standard. Costs were compared by calculating the downstream costs generated by each modality in terms of investigations and treatment.ResultsA total of 860 eyes of 430 patients were assessed during the study period. Tele-ophthalmology consultations had significantly high agreement with face-to-face consultations in the diagnosis and grading of all three ocular conditions; cataracts, glaucoma, and AMD. Diagnosis and grading of cataracts and AMD reached kappa values of > 0.8, while diagnosis and grading of glaucoma reached kappa values between 0.61 and 0.8. In terms of diagnostic accuracy, tele-ophthalmology consultations were highly sensitive and specific for AMD with greater than 99% sensitivity and specificity achieved by tele-ophthalmology. There was high specificity when diagnosing cataracts, but lower sensitivity at 87.8%. Conversely, there was high sensitivity for diagnosing glaucoma, but lower specificity at 76.5%. Downstream costs were similar between groups.ConclusionsStore-and-forward tele-ophthalmology consultations are accurate and comparable to face-to-face consultations for diagnosis and grading of cataracts, glaucoma, and AMD.Supplementary InformationThe online version contains supplementary material available at 10.1007/s40123-022-00506-x.

The Effect of Cataract on Color Vision Measurement with the Low-Vision Cambridge Colour Test: Providing an Adjustment Factor for Clinical Trials.

PurposeTo quantify the effect of cataract on color vision as measured by the low-vision Cambridge Colour Test (lvCCT; Cambridge Research Systems) and to understand whether different types and severities of cataract have different effects on color vision.DesignCohort study.ParticipantsPatients aged 18 to 95 undergoing routine cataract surgery at the Oxford Eye Hospital.MethodsThe lvCCT was performed to measure color sensitivity in both eyes both before and after surgery. The crystalline lens was examined and graded according to the Lens Opacities Classification System III to determine the type and severity of cataract. Measures of repeatability were performed for the data to explore test–retest bias using Bland–Altman analysis. The Wilcoxon signed-rank test was performed to assess the effect of cataract on color vision by comparing control and surgical test measurements. Three multiple linear regressions were performed to relate cataract grading or severity to color vision measurements.Main Outcome MeasuresColor discrimination along each of the protan, deutan, and tritan confusion lines.ResultsThe Wilcoxon signed-rank test showed a statistically significant difference in both the protan (P = 0.024) and tritan (P = 0.020) axes on comparison of control and surgical test measurements. As severity of cataract increased, color vision sensitivity was affected more greatly, and nuclear sclerotic cataract showed the most profound effect on color vision sensitivity in the lvCCT; however, the linear regression models showed that these observations did not reach statistical significance.ConclusionsCataract surgery has a statistically significant effect on color vision in both the protan and tritan axes. The effects of specific subtypes of cataract and different severities could not be elucidated because of the high prevalence of patients with mixed cataract. The lvCCT color sensitivity measurements are used regularly as outcome measures in clinical gene therapy trials involving vitreoretinal surgery, and vitrectomy accelerates cataract formation. Therefore, it is important to quantify the effect of cataract on color vision measurements so that it may be taken into account when used as an outcome measure in clinical trials. We were unable to derive a precise correction factor for cataract on color vision measurements.

Computer‐aided diagnosis of cataract severity using retinal fundus images and deep learning

AbstractCataracts are lenticular opacities that can appear in different parts of the lens in the eye and are a leading cause of blindness globally. Accurate detection and early‐stage diagnosis can prevent the cataract and improve the quality of life for cataract patients. However, clinical cataract detection and grading require the expertise of trained eye specialists, which may impede everyone's early intervention due to the underlying expenses. This article proposed a computer aid diagnosis method for cataract detection, which also grades the severity of cataracts from fundus retinal images such as normal, mild, moderate, and severe. The proposed method uses a hybrid approach in which various pre‐trained convolutional neural networks (AlexNet, VGGNet, ResNet) with transfer learning are used to extract features. These feature vectors of each network individually and in the fused form are applied on the support vector machine classifiers for 4‐stage cataract classification. This architecture also takes advantage of ensemble learning by applying a majority voting scheme on the predictions of these SVM classifiers. The fundus cataract images are obtained from several open‐access datasets and arranged into 4‐classes with the assistance of an eye specialist. Since all the collected images are not suitable for diagnosis, an image quality selection module is included with this method to determine the quality of fundus images. The proposed method achieved 96.25% 4‐class classification accuracy. According to the experimental results, the proposed method is effective for cataract classification and outperforms conventional methods.

Age-related decline in function of ON and OFF visual pathways.

PurposeA simple psychophysical paradigm is available as a digital application in iOS devices such as iPad to measure the function of ON and OFF visual pathways. However, an age-matched normative database is not readily available. The purpose of the study is to evaluate the response of ON and OFF visual pathways as a function of age.Methods158 normal healthy adults (84 males and 74 females) whose age ranged 18–80 years participated in the study. None of them had any ocular disease (except cataract of grade II or less) and visual acuity of ≤ 20/25. Monocular testing (only one eye) was performed on the ‘EyeSpeed’ application on an iPad at 40cm distance. The targets ranged between 1 to 3 light or dark squares presented randomly in a noise background and participants responded by indicating the number of squares by touching the screen as fast as possible. The main outcome variables are reaction time, accuracy and performance index (1 / speed * accuracy).ResultsThe median reaction time was shorter (Median (IQR): 1.53s (0.49) [dark] Vs 1.76s (0.58) [light], p < 0.001) and accuracy was higher (97.21% (3.30) [dark] Vs 95.15% (5.10) [light], p < 0.001) for dark targets than the light targets. Performance index and reaction time for both target types significantly correlated with age (ρ = -0.41 to -0.43; p < 0.001).ConclusionsThis normative database will be useful to quantify disease-specific defects. More importantly, the ON pathway function can potentially serve as a surrogate for rod photoreceptor function.

Development of portable and robust cataract detection and grading system by analyzing multiple texture features for Tele-Ophthalmology.

This paper presents a low cost, robust, portable and automated cataract detection system which can detect the presence of cataract from the colored digital eye images and grade their severity. Ophthalmologists detect cataract through visual screening using ophthalmoscope and slit lamps. Conventionally a patient has to visit an ophthalmologist for eye screening and treatment follows the course. Developing countries lack the proper health infrastructure and face huge scarcity of trained medical professionals as well as technicians. The condition is not very satisfactory with the rural and remote areas of developed nations. To bridge this barrier between the patient and the availability of resources, current work focuses on the development of portable low-cost, robust cataract screening and grading system. Similar works use fundus and retinal images which use costly imaging modules and image based detection algorithms which use much complex neural network models. Current work derives its benefit from the advancements in digital image processing techniques. A set of preprocessing has been done on the colored eye image and later texture information in form of mean intensity, uniformity, standard deviation and randomness has been calculated and mapped with the diagnostic opinion of doctor for cataract screening of over 200 patients. For different grades of cataract severity edge pixel count was calculated as per doctor’s opinion and later these data are used for calculating the thresholds using hybrid k-means algorithm, for giving a decision on the presence of cataract and grade its severity. Low value of uniformity and high value of other texture parameters confirm the presence of cataract as clouding in eye lens causes the uniformity function to take lower value due to presence of coarse texture. Higher the edge pixel count value, this confirms the presence of starting of cataract as solidified regions in lens are nonuniform. Lower value corresponds to fully solidified region or matured cataract. Proposed algorithm was initially developed on MATLAB, and tested on over 300 patients in an eye camp. The system has shown more than 98% accuracy in detection and grading of cataract. Later a cloud based system was developed with 3D printed image acquisition module to manifest an automated, portable and efficient cataract detection system for Tele-Ophthalmology. The proposed system uses a very simple and efficient technique by mapping the diagnostic opinion of the doctor as well, giving very promising results which suggest its potential use in teleophthalmology applications to reduce the cost of delivering eye care services and increasing its reach effectively. Developed system is simple in design and easy to operate and suitable for mass screening of cataracts. Due to non-invasive and non-mydriatic and mountable nature of device, in person screening is not required. Hence, social distancing norms are easy to follow and device is very useful in COVID-19 like situation.

Deep Learning-Based Cataract Detection and Grading from Slit-Lamp and Retro-Illumination Photographs: Model Development and Validation Study.

PurposeTo develop and validate an automated deep learning (DL)-based artificial intelligence (AI) platform for diagnosing and grading cataracts using slit-lamp and retroillumination lens photographs based on the Lens Opacities Classification System (LOCS) III.DesignCross-sectional study in which a convolutional neural network was trained and tested using photographs of slit-lamp and retroillumination lens photographs.ParticipantsOne thousand three hundred thirty-five slit-lamp images and 637 retroillumination lens images from 596 patients.MethodsSlit-lamp and retroillumination lens photographs were graded by 2 trained graders using LOCS III. Image datasets were labeled and divided into training, validation, and test datasets. We trained and validated AI platforms with 4 key strategies in the AI domain: (1) region detection network for redundant information inside data, (2) data augmentation and transfer learning for the small dataset size problem, (3) generalized cross-entropy loss for dataset bias, and (4) class balanced loss for class imbalance problems. The performance of the AI platform was reinforced with an ensemble of 3 AI algorithms: ResNet18, WideResNet50-2, and ResNext50.Main Outcome MeasuresDiagnostic and LOCS III-based grading prediction performance of AI platforms.ResultsThe AI platform showed robust diagnostic performance (area under the receiver operating characteristic curve [AUC], 0.9992 [95% confidence interval (CI), 0.9986–0.9998] and 0.9994 [95% CI, 0.9989–0.9998]; accuracy, 98.82% [95% CI, 97.7%–99.9%] and 98.51% [95% CI, 97.4%–99.6%]) and LOCS III-based grading prediction performance (AUC, 0.9567 [95% CI, 0.9501–0.9633] and 0.9650 [95% CI, 0.9509–0.9792]; accuracy, 91.22% [95% CI, 89.4%–93.0%] and 90.26% [95% CI, 88.6%–91.9%]) for nuclear opalescence (NO) and nuclear color (NC) using slit-lamp photographs, respectively. For cortical opacity (CO) and posterior subcapsular opacity (PSC), the system achieved high diagnostic performance (AUC, 0.9680 [95% CI, 0.9579–0.9781] and 0.9465 [95% CI, 0.9348–0.9582]; accuracy, 96.21% [95% CI, 94.4%–98.0%] and 92.17% [95% CI, 88.6%–95.8%]) and good LOCS III-based grading prediction performance (AUC, 0.9044 [95% CI, 0.8958–0.9129] and 0.9174 [95% CI, 0.9055–0.9295]; accuracy, 91.33% [95% CI, 89.7%–93.0%] and 87.89% [95% CI, 85.6%–90.2%]) using retroillumination images.ConclusionsOur DL-based AI platform successfully yielded accurate and precise detection and grading of NO and NC in 7-level classification and CO and PSC in 6-level classification, overcoming the limitations of medical databases such as few training data or biased label distribution.

Cataract grading method based on deep convolutional neural networks and stacking ensemble learning

AbstractThe cataract is the most common cause of severe vision impairment or blindness worldwide. A periodical diagnosis is recommended in order to prevent cataract severity, where screening might be feasibly ensured through fundus images. In this paper, we propose a CAD system to efficiently grade the cataract from fundus images. For such a need, an ensemble learning framework is put forward where the knowledge of three convolutional deep neural networks is stacked in order to perform an efficient cataract prediction. The main contributions of this work are given as follows: (1) Preprocessing and data augmentation of fundus images are carried out to ensure the robustness of the cataract grading; (2) The well‐known DL architectures (Inception‐V3, MobileNet‐V2 and NasNet‐Mobile) are fine‐tuned and learned as base classifiers; (3) An Extreme Learning Machine (ELM) is performed as a meta classifier to stack the predictions of base classifiers. The evaluation is conducted using a dataset of 590 fundus images selected from two public databases. The suggested framework achieves 94.07% accuracy, 94.37% sensitivity, 93.62% specificity, 95.71% precision and 95.04% F‐measure for cataract grading. The experimentation proves that the proposed framework successfully grades fundus images into cataract severity. Moreover, stacking ensemble learning allows achieving a performance that significantly surpasses the ones realized by each DL architecture, applied separately.

Pupil Dilation by Intracameral Injection of Preservative Free 1% Lidocaine and Topical Mydriatics in Phacoemulsification Cases: A Comparative Study

Purpose: To compare the results of pupil dilation by an intracameral injection of preservative free 1% lidocaine with conventional topical mydriatics during phacoemulsification cataract surgery. Comparison was also done for simultaneous anaesthetic effect between intracameral lidocaine and topical mydriatics. Methods: A randomized, comparative interventional study was conducted. The study included 50 patients who underwent phacoemulsification and intraocular lens implantation surgery and were divided in two groups. One group was given topical mydriatics (25 eyes) preoperatively and other intracameral lidocaine (25 eyes) at commencement of surgery to dilate the pupil. The topical group received 3 drops of tropicamide 0.8% and phenylephrine 5% eye drops 15 minutes apart starting 45 minutes before surgery. The intracameral group received preservative-free lidocaine 1% (0.2 to 0.3 mL) injected just before the procedure began. In both groups, the horizontal pupil diameter was measured before and after pupil dilation using the same caliper. Total surgical time, need for a supplement mydriatic agent during the surgery and subjective surgical performance were recorded. Any adverse ocular and systemic effects between two groups were also compared. Results: The mean age, sex, cataract grading, baseline horizontal pupil diameter and mean surgerical time were similar between the topical and intracameral group. The mean pupil dilation was 4.62 ± 0.96 mm in the intracameral group and 4.76 ± 0.75 mm in the topical group. There was no statistically significant difference between the two groups (P value =0.57).There was no significant difference between groups in the overall subjective surgical performance (P=0.72). No patient in any group required supplementary intracameral mydriatic injection. Conclusion: Intracameral lidocaine is a safe, effective and reliable alternative to topical mydriatic for pupil dilation with added advantages of fast postoperative recovery and is also ....

Comparison of postoperative astigmatism in small incision cataract surgery based on size and shape of the incision

Study of comparison of postoperative astigmatism in small incision cataract surgery depending on size and shape of incision A prospective study of 50 eyes of 50 patients who underwent manual SICS under local anaesthesia between December 2020 and May 2021 conducted by single surgeon and followed up on post op day 1 day 7 and 6 weeks. Patients selected were having grade 1 to 2 nuclear sclerosis the size and shape of incision was decided depending upon the grade of cataract. On follow ups thorough ocular examination was done especially looking for corrected visual acuity and correction needed for that. Keratometry was done in each follow up visits. At the end surgically induced astigmatism (SIA) was calculated. Surgically Induced Astigmatism (SIA) calculated by SIA calculator SIA was 0.5 - 1 D in 38 patients with frown incision of 4 to 5mm,1.0 - 1.5 D in 10 patients with frown incision size of 5 to 6mm 2D in patients with straight incision size of 6mm and more In all cases. The less average SIA was noted in group with smaller incision of about 4 to 5mm. Frown superior incision has got added advantage of early wound stabilization than straight incision. It is possible to reduce the amount of post-operative astigmatism significantly by choosing the incision shape and size.