Artificial Intelligence in Cataract Surgery: A Systematic Review.

Purpose: The purpose of this study was to assess the current use and reliability of artificial intelligence (AI)-based algorithms for analyzing cataract surgery videos. Methods: A systematic review of the literature about intra-operative analysis of cataract surgery videos with machine learning techniques was performed. Cataract diagnosis and detection algorithms were excluded. Resulting algorithms were compared, descriptively analyzed, and metrics summarized or visually reported. The reproducibility and reliability of the methods and results were assessed using a modified version of the Medical Image Computing and Computer-Assisted (MICCAI) checklist. Results: Thirty-eight of the 550 screened studies were included, 20 addressed the challenge of instrument detection or tracking, 9 focused on phase discrimination, and 8 predicted skill and complications. Instrument detection achieves an area under the receiver operator characteristic curve (ROC AUC) between 0.976 and 0.998, instrument tracking an mAP between 0.685 and 0.929, phase recognition an ROC AUC between 0.773 and 0.990, and complications or surgical skill performs with an ROC AUC between 0.570 and 0.970. Conclusions: The studies showed a wide variation in quality and pose a challenge regarding replication due to a small number of public datasets (none for manual small incision cataract surgery) and seldom published source code. There is no standard for reported outcome metrics and validation of the models on external datasets is rare making comparisons difficult. The data suggests that tracking of instruments and phase detection work well but surgical skill and complication recognition remains a challenge for deep learning. Translational Relevance: This overview of cataract surgery analysis with AI models provides translational value for improving training of the clinician by identifying successes and challenges.

Couching of cataractous lens in microphthalmic eyes with irido-fundal coloboma: revisiting the historical technique.

PURPOSE: Cataract surgery in microphthalmic eyes is challenging due to anatomical restraints, hard bulky nucleus. This series aims to evaluate the safety and efficacy of couching of intraocular lens in irido-fundal coloboma with microphthalmos. SETTING: Tertiary care centre in South India. DESIGN: Retrospective non-comparative study in eyes with irido-fundal coloboma, corneal diameter < 7 mm and brown cataract. Visual acuity less than 6/60 in other eye. METHODS: Anterior chamber entry made, zonules broken and lens dislocated into the vitreous cavity in a controlled manner. Baseline Clinico-demographic details, corrected distance visual acuity (CDVA), Intra-ocular pressure (IOP), corneal diameter, axial length, lens status and post-surgery CDVA, IOP and complications recorded and followed up for atleast 6 months. RESULTS: Fifteen eyes of 15 subjects were evaluated with a mean age 49.4 ± 10.9 years. At baseline, mean IOP 14.5 ± 3.8 mmHg, mean axial length 19.3 ± 0.5 mm, mean corneal diameter was 6.5 ± 0.34 mm and CDVA 2 logMAR which improved to 1.5 logMAR at 3 months (p value 0.002). Transient spike in IOP in 33.3% subjects was medically managed with no significant difference in IOP (p > 0.05) at baseline (14.5 ± 3.8 mmHg), 3 months post-surgery (16 ± 2.8 mmHg) and 6 months post-surgery (14.9 ± 2.5 mmHg). One patient underwent re-couching. No other major complications were noted. CONCLUSION: Couching of cataractous lens is an effective and safe method in microphthalmic eyes with irido-fundal coloboma as last resort procedure, where no other surgical procedure may work. It provides an ambulatory gain of visual acuity in previously non-ambulatory subjects. Corneal measurements help in determining the subset of patients where couching offers viable option.

The surgical management of a patient with Fuchs endothelial dystrophy and cataracts.

Objective: To report the two different surgical approaches in the case of a patient with Fuchs endothelial dystrophy with low endothelial cell count and advanced cataracts. Methods: The chosen surgical approach differed between eyes, with the right eye undergoing a combined approach consisting of cataract surgery, intraocular lens implantation, and penetrating keratoplasty in 2022. One year later, for the left eye, a different approach was decided: cataract surgery followed by Descemet membrane endothelial keratoplasty (DMEK). The Descemet membrane graft was prepared by the surgeon using the liquid bubble technique. AS-OCT was used to monitor the patient before and after surgery. Results: Visual recovery was excellent for both eyes, however, visual acuity improved quickly in the left eye (DMEK), while, in the right eye (PK), the best corrected visual acuity was reached after several months post-surgery. Conclusion: Advanced stages of Fuchs dystrophy patients will most likely need corneal transplantation. Each type of corneal transplantation procedure comes with unique challenges, both intraoperative and postoperative. DMEK is a very good treatment option for patients with Fuchs endothelial dystrophy, with excellent visual recovery and good graft survival at the 10-year mark. Abbreviations: DMEK = Descemet membrane endothelial keratoplasty, PK = penetrating keratoplasty, AS-OCT = anterior segment optical coherence tomography, FECD = Fuchs endothelial corneal dystrophy, BCVA = best corrected visual acuity, US = ultrasound, CDE = cumulative dissipated energy, IOL = intraocular lens.

[Outcomes of hemi-Descemet membrane endothelial keratoplasty and phacoemulsification for the treatment of primary Fuchs' endothelial corneal dystrophy combined with cataract]. / Rezul'taty transplantatsii destsemetovoi membrany s endoteliem i fakoemul'sifikatsii pri pervichnoi endotelial'noi distrofii rogovitsy Fuksa, sochetannoi s kataraktoi.

PURPOSE: This study evaluates the long-term results of surgical treatment of patients with Fuchs' endothelial corneal dystrophy and cataract. MATERIAL AND METHODS: The study included 24 patients (24 eyes) with primary Fuchs' endothelial corneal dystrophy and cataract, who underwent cataract phacoemulsification with IOL implantation and of Descemet's membrane endothelial keratoplasty with a semicircular graft (hemi-DMEK). The effect of treatment was assessed by best corrected visual acuity (BCVA), central corneal thickness (CCT) and endothelial cell density (ECD). RESULTS: In total, surgical treatment involved 14 donor corneas that were divided in half during the preparation and isolation of the Descemet's membrane (DM). By month 12 after the surgery an increase in visual functions and graft transparency were observed in 23 patients (23 eyes) out of 24. Repeated keratoplasty was required in one case due to fibrosis of the posterior layers of recipient's corneal stroma. At 12 months postoperatively, the study group showed an increase in BCVA from 0.16±0.1 to 0.75±20, a decrease in CCT from 650.9±4.5 µm to 519.6±43.9, and a decreased in ECD from 2850.5±84.7 cells/mm2 up to 1285.5±277.2 cells/mm2. Thus, the loss of endothelial cells at one year after surgery amounted to 54.9%. CONCLUSIONS: The developed method for transplantation of a semicircular DM fragment provides a tissue-saving approach to endothelial keratoplasty, and considering the high percentage of transparent engraftment of grafts and complete visual rehabilitation, it can be recommended in the treatment of patients with cataract and Fuchs' endothelial corneal dystrophy.

The comparison of corneal densitometry in cases with glaucoma following childhood cataract surgery and juvenile glaucoma.

PURPOSE: To compare the corneal densitometry (CD) in pediatric cases with glaucoma following childhood cataract surgery and juvenile open-angle glaucoma (JOAG). METHODS: This prospective comparative study involved 13 eyes with JOAG, 12 eyes with pseudophakic glaucoma, 13 eyes with aphakic glaucoma, and 15 control subjects. Pentacam HR Scheimpflug corneal topography was employed to evaluate corneal thickness (CCT) and CD values. RESULTS: The mean intraocular pressure (IOP) and CCT were significantly higher in aphakic glaucoma cases than the other groups (p = 0.001). In aphakic eyes, the mean CD values were higher in most of the anterior, center, and posterior layers of 0-2 mm, 2-6 mm, 6-10 mm, and total zones (p < 0.001 for all). In pseudophakic eyes, the mean CD values were statistically similar with that of aphakic eyes and higher than that of JOAG and control eyes in all layers of 0-2 mm zone and in anterior layer of 10-12 mm and anterior and total layers of 2-6 mm zones (p < 0.05 for all). The CD values demonstrated significant correlations with CCT values in both aphakic and pseudophakic eyes. However, a significant correlation of CD values with IOP was only demonstrated in aphakic eyes (p = 0.01 for all). CONCLUSION: The probable effects of childhood cataract surgery especially aphakia might cause corneal backscatter of light and increased CD in all layers in all zones of the cornea. Increased CD values and its correlation with CCT and IOP in aphakic glaucoma eyes may be of importance in clinical management.

Association of refractive outcome with postoperative anterior chamber depth measured with 3 optical biometers.

PURPOSE: This study evaluated the relationship between refractive outcomes and postoperative anterior chamber depth (ACD, measured from corneal epithelium to lens) measured by swept-source optical coherence tomography (SS-OCT), optical low-coherence reflectometry (OLCR), and Scheimpflug devices under the undilated pupil. METHODS: Patients undergoing cataract phacoemulsification with intraocular lens (IOL) implantation in a hospital setting were enrolled. Postoperative ACD (postACD) was performed with an SS-OCT device, an OLCR device, and a Scheimpflug device at least 1 month after cataract surgery. After adjusting the mean predicted error to 0, differences in refractive outcomes were calculated with the Olsen formula using actual postACD measured from 3 devices and predicted value. RESULTS: Overall, this comparative case study included 69 eyes of 69 patients, and postACD measurements were successfully taken using all 3 devices. The postACD measured with the SS-OCT, OLCR, and Scheimpflug devices was 4.59 ± 0.30, 4.50 ± 0.30, and 4.54 ± 0.32 mm, respectively. Statistically significant differences in postACD were found among 3 devices (P < 0.001), with intraclass correlation coefficients (ICCs) and Bland-Altman showing good agreement. No significant difference in median absolute error was found with the Olsen formula using actual postACD obtained with 3 devices. Percentage prediction errors were within ± 0.50 D in 65% (OLCR), 70% (Scheimpflug), and 67% (SS-OCT) calculated by actual postACD versus 64% by predicted value. CONCLUSION: Substantial agreement was found in postACD measurements obtained from the SS-OCT, OLCR, and Scheimpflug devices, with a trend toward comparable refractive outcomes in the Olsen formula. Meanwhile, postACD measurements may be potentially superior for the additional enhancement of refractive outcomes.

Central anterior chamber depth correlated with white-to-white distance in normal, long, and short eyes.

PURPOSE: To explore the associations between central anterior chamber depth (CACD) and other anterior segment biometric parameters and to determine the possible determinants of CACD in short, normal, and long eyes. METHODS: The biometric data of pre-operation patients aged 50-80 years with coexisting cataract and primary angle-closure disease or senile cataract were reviewed. Axial length (AL), CACD, lens thickness (LT), central corneal thickness (CCT), and white-to-white distance (WTW) were measured by Lenstar optical biometry (Lenstar 900). The data of 100 normal eyes (AL = 22 to 26 mm), 100 short eyes (AL ≤ 22 mm), and 100 long eyes (AL ≥ 26 mm) were consecutively collected for subsequent analyses. RESULTS: The mean age of the subjects was 66.60 ± 7.85 years, with 25.7% of the sample being men. Both CACD and WTW were found to be smallest in short eyes and were smaller in normal eyes than in long eyes (F = 126.524, P < 0.001; F = 28.458, P < 0.001). The mean LT was significantly thicker in short eyes than in normal and long eyes (4.66 mm versus 4.49 mm versus 4.40 mm; F = 18.099, P < 0.001). No significant differences were observed in CCT between the three AL groups (F = 2.135, P = 0.120). Stepwise regression analysis highlighted AL, LT, and WTW as three independent factors associated with CACD in the normal AL group. In the short AL group and long AL group, LT and WTW were independent factors associated with CACD. CONCLUSIONS: CACD increases as AL elongates and reaches a peak when AL exceeds 26 mm. Furthermore, CACD showed inverse correlation with LT and positive correlation with WTW. A relatively small WTW results in an anteriorly positioned lens, and thus, a decrease in CACD.

A case report of iridoschisis and cataract: a challenging diagnosis.

PURPOSE: To report the cataract surgery of a 79-year-old female patient with iridoschisis and senile nuclear cataracts. OBSERVATIONS: Ophthalmologic examination of the 79-year-old female patient who came to our clinic with complaints of decreased vision in the right eye was observed to have a grade-3 senile nuclear cataract and iridoschisis in quadrants 2-3, 4-7, and 10-11 of the iris in the right eye and a grade-2 senile nuclear cataract and iridoschisis in quadrants 5-7 in the left eye to a lesser extent compared to the right eye. The iris fibrils were not connected to the corneal endothelium. A safe surgical area was created by administering the viscoelastic material several times during cataract surgery. CONCLUSIONS AND IMPORTANCE: Although iridoschisis has a low incidence rate, it is important to also consider comorbid ocular pathologies when treating iridoschisis patients. Since cataract surgery for these patients is more specialized than for uncomplicated cases, the necessary surgical planning must be paid due diligence.

Comparison of keratometric values and anterior segment parameters measured using Scheimpflug Sirius topography and Lenstar biometry.

PURPOSE: This study aimed to evaluate the consistency of preoperative keratometric values, anterior segment, and intraocular lens (IOL) power measurements in patients with cataract and no comorbidities using the Sirius topography device (CSO, Italy) and Lenstar LS 900 (Haag-Streit AG, Köeniz, Switzerland). METHODS: Patients with grade 2 and 3 cataracts who applied to Ophthalmology Clinic of Diskapi Yildirim Beyazit Education and Research Hospital, University of Health Sciences and planned for cataract surgery were included the study. Forty eyes with cataract from 40 patients were taken in the study. All patients underwent preoperative assessment using a combined Scheimpflug-Placido disc-based tomography device (Sirius) and Lenstar before cataract surgery. Keratometric measurements, such as flat keratometry (K1), steep keratometry (K2), and maximum keratometry (Kmax), and anterior segment parameters, white-to-white (WTW) distance, IOL power, astigmatism (AST), anterior chamber depth (ACD), aqueous depth (AD), and central cornea thickness (CCT), were recorded. RESULTS: There were significant differences between K1Lenstar and K1Sirius, K2Lenstar and K2Sirius, KmaxLenstar and KmaxSirius, WTWLenstar and WTWSirius, and IOL powerLenstar versus IOL powerSirius. However, there were insignificant differences between ASTLenstar and ASTSirius, ACDLenstar versus ACDSirius, ADLenstar and ADSirius, and CCTLenstar and CCTSirius variables. Furthermore, it was found that Sirius measured significantly higher than Lenstar, especially in terms of IOL power. CONCLUSION: Significant differences were observed between Lenstar and Sirius in terms of keratometric values, WTW distance, and IOL power. The IOL power value measured with Sirius was found to be higher than the IOL power value measured with Lenstar.

Susceptibility to eye diseases in relation to age and kidney failure among Taiwanese adults.

BACKGROUND: The kidney and eyes share common pathways and are thought to be closely connected. Chronic kidney disease and major eye diseases, such as cataract and glaucoma, are strongly associated with age. However, further investigation is needed to understand the joint impact of age and kidney diseases on eye diseases. In this study, we assessed the risk of eye diseases in relation to age and kidney failure in Taiwanese adults. METHODS: Our study included 127,561 cancer-free volunteers aged 30 to 70 years who participated in the Taiwan Biobank (TWB) project from 2008 to 2020. Information on the main exposures (kidney failure and age) and the outcome (eye diseases, including glaucoma, cataract, xerophthalmia, and retinal detachment) was collected through questionnaires. RESULTS: In general, kidney failure and older age were independently associated with a higher risk of eye, particularly cataract and retinal detachment: prevalence odds ratio (POR); 95% confidence interval (CI) = 2.480; 1.635-3.761 for cataract and 3.885; 1.968-7.666 for retinal detachment. A significant interaction between kidney failure and age on cataract was observed (p-value = 0.0002). Age-stratified analysis revealed a higher risk of cataract among patients with kidney failure aged below 50 (POR = 6.534; 95% CI = 2.493-17.124) and between 50 and 60 years (POR = 3.957; 95%CI = 1.986-7.881). Combining kidney failure and age (reference: no kidney failure and age < 50 years), kidney failure in all age groups was associated with a higher risk of cataract. The PORs; 95% CIs were 10.725; 4.227-27.211 for patients below 50 years, 28.487; 14.270-56.866 for those aged 50-60 years, and 43.183; 24.434-72.824 for those > 60 years. Combining cataract and age (reference: no cataract and age < 50 years), patients below 50 years had the highest risk of kidney failure (POR; 95% CI = 9.510; 3.722-24.297). CONCLUSIONS: Our study suggests that age and kidney failure may jointly contribute to eye diseases, particularly cataract. The association between cataract and kidney failure could be bidirectional, especially in individuals below 50 years. This significant bidirectional relationship underscores the need for screening patients with cataract for kidney failure and vice versa, particularly in younger adults.

Fundus examination using a wide-angle viewing system and intraocular illumination through the corneal incision during cataract surgery: a case series.

PURPOSE: To report a new technique for fundus examination using a wide-angle viewing system combined with intraocular illumination without accessing the vitreous cavity. STUDY DESIGN: Retrospective case series METHODS: Consecutive patients with atopic dermatitis-related cataracts who underwent standard cataract surgery and the novel fundus examination technique were included. After phacoemulsification, the anterior and posterior chambers were filled with ocular viscoelastic devices. A 27-gauge endo-illumination probe was inserted into the anterior chamber through a corneal incision made for cataract surgery. The fundus examination was performed with a wide-angle viewing system and scleral indentation. If any retinal breaks/detachments were detected, they were treated simultaneously. Finally, an intraocular lens was implanted. RESULTS: Ten patients (13 eyes) were included (mean age 26.8 years; 9 men). Retinal breaks were detected in 5 eyes (38%); 2 of the 5 had rhegmatogenous retinal detachment (RRD) (15%). Intraoperative cryopexy was performed for 3 eyes with retinal breaks, while 2 eyes with RRD underwent a scleral buckling procedure (SBP) during the same surgery. There were no intra- or postoperative complications, including posterior capsule damage. The average surgical time was 22 minutes for cases requiring only fundus examination and about 28 and for eyes with cryopexy and 80 minutes for SBP. CONCLUSION: The described technique may reduce the disadvantages of creating scleral incisions and provide comparable visibility to inserting the illuminator into the vitreous cavity.

PHARC syndrome which an ultra-rare syndrome with retinitis pigmentosa and cataracts: case report and review of the literature.

BACKGROUND: PHARC syndrome (MIM:612674) is a rare neurodegenerative disorder characterized by demyelinating polyneuropathy, hearing loss, ataxia, retinitis pigmentosa, and cataracts (PHARC). The syndrome is caused by mutations in the ABHD12 gene, which encodes αß-hydrolase domain-containing protein 12 related to endocannabinoid metabolism. PHARC syndrome is one of the rare diseases; so far, only 51 patients have been reported in the literature. METHODS: We evaluated the 25-year-old male patient referred to us due to vision loss, cataracts, and hearing loss. Ophthalmological examinations and genetic analyses were performed using targeted next-generation sequencing. RESULTS: In the genetic analysis, the patient was diagnosed with PHARC syndrome by detecting homozygous (NM_001042472.3): c.871del (p.Tyr291IlefsTer28) novel pathogenic variation in the ABHD12 gene. Following the molecular diagnosis, he was referred to the neurology department for reverse phenotyping and sensorimotor demyelinating polyneuropathy was detected in the neurological evaluation. CONCLUSIONS: In this study, we report a novel variation in ABHD12 gene in the first Turkish-origin PHARC patient. We present this study to contribute genotype-phenotype correlation of PHARC syndrome and emphasize the importance of molecular genetic diagnosis in order to determine the appropriate clinical approach. This report is essential for expanding the phenotypic spectrum in different populations and understanding the genotype-phenotype correlation of PHARC syndrome via novel pathogenic variation in the ABHD12 gene.

Capabilities and Limitations of Student-Led Free Vision Screening Programs in the United States.

Purpose: The Consortium of Student-Led Eye Clinics (CSLEC), founded in 2021, administered a comprehensive survey to document the types of services, most common diagnoses, and follow-up care protocols offered by student-led free vision screening programs (SLFVSP) in the United States. Methods: An 81-question institutional review board (IRB)-approved survey was administered to student-led vision screening eye clinics from October 1, 2022 to February 24, 2023. Results: Sixteen SLFVSPs were included in the final analysis, of which 81% (n = 13) conducted variations of fundoscopic examinations and 75% (n = 12) measured intraocular pressure. Cataracts and diabetic retinopathy were reported as the most frequent diagnoses by the majority of SLFVSPs (n = 9, 56%); non-mobile SLFVSPs more commonly reported cataract as a frequent diagnosis (P < 0.05). Most patients screened at participating programs were uninsured or met federal poverty guidelines. Prescription glasses were offered by 56% of the programs (n = 9). SLFVSPs that directly scheduled follow-up appointments reported higher attendance rates (66.5%) than those that only sent referrals (20%). Transportation was the most cited barrier for follow-up appointment attendance. Conclusions: SLFVSPs, one community vision screening initiative subtype, vary significantly in scope and capabilities of identifying vision threatening disease. The follow-up infrastructure is not uniformly robust and represents a key target for improving care delivery to at-risk populations. Translational Relevance: The CSLEC aims to develop a consensus-based standardization for the scope of screening services, offer guidelines for diagnostic criteria, promote real-time data stewardship, and identify means to improve follow-up care mechanisms in member communities.

Identification of pathogenic genetic variants in patients with acquired early-onset bilateral cataracts using next-generation sequencing.

BACKGROUND: Acquired early-onset bilateral cataracts can result from systemic etiologies or genetic disorders. METHODS: In this observational study, we analyzed individuals 18 months to 35 years of age with acquired bilateral cataracts via a next-generation sequencing panel of 66 genes to identify disease-causing genetic variants. RESULTS: Of 347 patients enrolled, 313 (90.2%) were <19 years (median, 8 years). We identified 74 pathogenic or likely pathogenic variants in 69 patients. Of the variants, we observed 64 single nucleotide variants (SNV) in 24 genes and 10 copy number variants (CNV) of varying size and genomic location. SNVs in crystallin genes were most common, accounting for 27.0% of all variants (20 of 74). Of those, recurrent variants included known cataract-causing variants CRYBA1 c.215+1G>A, observed in 3 patients, and CRYBA1 c.272_274delGAG, CRYBB2 c.463C>T and c.562C>T, and CRYAA c.62G>A, each observed in 2 patients. In 5 patients, we identified CNV deletions ranging from 1.32-2.41 Mb in size associated with 1q21.1 microdeletion syndrome. Biallelic variants in CYP27A1 were identified in two siblings, one as part of targeted follow-up family testing, who were subsequently diagnosed with cerebrotendinous xanthomatosis, a rare but treatable autosomal recessive disease that often presents with acquired early-onset bilateral cataracts. CONCLUSIONS: This study demonstrates the utility of genetic testing in individuals with acquired early-onset bilateral cataracts to help clarify etiology. Identification of causative genetic variants can inform patient management and facilitate genetic counseling by identifying genetic conditions with risk of recurrence in families.

The Slitscope.

Slit lamp biomicroscope is the right hand of an Ophthalmologist. Even though precise, its bulky design and complex working process are limiting constraints, making it difficult for screening at outreach camps, which are an integral part of this field for the purpose of eliminating needless blindness. The torchlight is the main tool used for screening. Recently, the integration of smartphones with instruments and the digitization of slit lamp has been explored, to provide simple and easy hacks. By bringing the slit of the slit lamp to traditional torchlight, we have created "The Slitscope". It combines the best of both worlds as a simple innovative do-it-yourself novel technique for precise cataract screening. It is especially useful in peripheral centers, vision centers, and outreach camps. We present two prototypes which can also be 3D printed.