Differentiation of Active Corneal Infections from Healed Scars Using Deep Learning.

PURPOSE: To develop and evaluate an automated, portable algorithm to differentiate active corneal ulcers from healed scars using only external photographs. DESIGN: A convolutional neural network was trained and tested using photographs of corneal ulcers and scars. PARTICIPANTS: De-identified photographs of corneal ulcers were obtained from the Steroids for Corneal Ulcers Trial (SCUT), Mycotic Ulcer Treatment Trial (MUTT), and Byers Eye Institute at Stanford University. METHODS: Photographs of corneal ulcers (n = 1313) and scars (n = 1132) from the SCUT and MUTT were used to train a convolutional neural network (CNN). The CNN was tested on 2 different patient populations from eye clinics in India (n = 200) and the Byers Eye Institute at Stanford University (n = 101). Accuracy was evaluated against gold standard clinical classifications. Feature importances for the trained model were visualized using gradient-weighted class activation mapping. MAIN OUTCOME MEASURES: Accuracy of the CNN was assessed via F1 score. The area under the receiver operating characteristic (ROC) curve (AUC) was used to measure the precision-recall trade-off. RESULTS: The CNN correctly classified 115 of 123 active ulcers and 65 of 77 scars in patients with corneal ulcer from India (F1 score, 92.0% [95% confidence interval (CI), 88.2%-95.8%]; sensitivity, 93.5% [95% CI, 89.1%-97.9%]; specificity, 84.42% [95% CI, 79.42%-89.42%]; ROC: AUC, 0.9731). The CNN correctly classified 43 of 55 active ulcers and 42 of 46 scars in patients with corneal ulcers from Northern California (F1 score, 84.3% [95% CI, 77.2%-91.4%]; sensitivity, 78.2% [95% CI, 67.3%-89.1%]; specificity, 91.3% [95% CI, 85.8%-96.8%]; ROC: AUC, 0.9474). The CNN visualizations correlated with clinically relevant features such as corneal infiltrate, hypopyon, and conjunctival injection. CONCLUSIONS: The CNN classified corneal ulcers and scars with high accuracy and generalized to patient populations outside of its training data. The CNN focused on clinically relevant features when it made a diagnosis. The CNN demonstrated potential as an inexpensive diagnostic approach that may aid triage in communities with limited access to eye care.

Abscesos de córnea bilaterales en una paciente con SIDA. Presentación de un caso y revisión de la literatura / Corneal Abscess in a patient with aids: case report and literature review

El epitelio corneal es una importante barrera de defensa que impide el ingreso de una gran variedad de microorganismos. Cualquier alteración de la superficie ocular facilita la invasión bacteriana de la córnea. El germen más frecuentemente identificado es Staphylococcus aureus. Se presenta una paciente con enfermedad debida al virus de la inmunodeficiencia humana (VIH) con diagnóstico de sida, absceso corneal bilateral y lesiones cutáneas. S.aureus meticilino resistente se aisló en hemocultivos y en material obtenido por raspado de la córnea. El absceso corneal es una entidad poco frecuente en pacientes con infección por VIH y síndrome de inmunodeficiencia adquirida.

The corneal epithelium is an important defense barrier that prevents the entry of great variety of microorganisms. Any alteration of the ocular surface facilitates bacterial invasion of the cornea. The most frequently reported germ is Staphylococcus aureus. Here, we present a patient with a diagnosis of HIV/ AIDS disease, who developed bilateral corneal abscess and skin lesions. Methicillin-resistant Staphylococcus aureus was isolated from blood cultures and corneal scrapings. Corneal abscess is a rare entity in patients with HIV and acquired immunodeficiency syndrome

Úlcera neurotrófica secundaria a aplasia de nervio trigémino en paciente con síndrome de Goldenhar / Neurotrophic keratopathy secondary to trigeminal nerve aplasia in patient with Goldenhar syndrome

CASO CLÍNICO: Varón de 4 años de edad diagnosticado de síndrome de Goldenhar, sin antecedentes oftalmológicos relevantes, desarrolla una úlcera neurotrófica secundaria a aplasia de nervio trigémino que es tratada con trasplante de membrana amniótica multilaminar. DISCUSIÓN: En el síndrome de Goldenhar no suele estar descrita la aplasia de nervio trigémino como manifestación oftalmológica típica. Por tanto, parece necesario realizar controles oftalmológicos rutinarios y desde una edad temprana, para evitar la aparición de complicaciones graves asociadas a la anestesia corneal

CASE REPORT: A 4-year-old male diagnosed with Goldenhar syndrome, with an unremarkable ophthalmic history, develops a neurotrophic ulcer secondary to trigeminal nerve aplasia. It was treated with multilaminar amniotic membrane transplantation. DISCUSSION: Trigeminal nerve aplasia is not usually reported in Goldenhar syndrome. Therefore, it seems necessary to perform routine eye examinations, from an early age, to prevent serious complications associated with corneal anaesthesia

[Purulent corneal ulcers: etiology, pathogenesis, classification].

Advanced purulent corneal ulcer, as well as abscess, is a serious vision-threatening condition notable for its fulminant course and possible loss of the eye due to endophthalmitis. Its leading causes, pathogenesis, and classifications are described and analyzed in this paper.

Corneal topographic analysis of patients with Mooren ulcer using 3-dimensional anterior segment optical coherence tomography.

PURPOSE: To investigate the corneal topography and visual function of patients with Mooren ulcer using 3-dimensional anterior segment optical coherence tomography (3-D AS-OCT). METHODS: Fourteen eyes of 9 patients with Mooren ulcer were studied. Pachymetric and axial power maps were obtained by 3-D AS-OCT. The axial power maps were classified into 3 patterns by visual inspection. The distribution of the corneal dioptric power was analyzed by Fourier harmonic expansion. The magnitudes of the spherical component, asymmetry, regular astigmatism, higher-order irregularity, and radial distance from the corneal vertex to the thinnest point of the lesion were determined. RESULTS: The axial power maps of 9 eyes were classified into arcuate patterns, 4 into crab-claw patterns, and 1 eye into an intermediate pattern. The radial distance from the corneal vertex to the thinnest point of the lesion was significantly shorter in the crab-claw pattern group than in the arcuate pattern group (P = 0.007). The magnitudes of asymmetry, regular astigmatism, and higher-order irregularity of the crab-claw pattern group were significantly greater than those of the arcuate pattern group (P = 0.017, P = 0.011, and P = 0.030, respectively). CONCLUSIONS: Three-dimensional AS-OCT is able to evaluate the corneal topography of opacified peripheral lesions in eyes with Mooren ulcer, and the results showed that irregular astigmatism is higher when the lesion is closer to the center of the cornea.

Corneal collagen cross-linking (CXL) for the treatment of melting keratitis in cats and dogs: a pilot study.

OBJECTIVE: UV-A/riboflavin cross-linking (CXL) of corneal collagen fibers is an established, highly promising therapy for corneal melting in physician-based ophthalmology. A prospective pilot study was conducted to demonstrate proof of principle of this novel method for the treatment of melting corneal ulcers in dogs and cats. PROCEDURES: After obtaining owner consent, CXL was performed in three cats and three dogs with corneal melting, which either affected the entire corneal surface or was resistant to conventional antibiotic and anticollagenolytic therapy, and affected parts or all of the corneal surface. Medical therapy was continued in all patients. The available follow-up ranged from 2 to 22.5 months and involved slit-lamp examination, fluorescein staining, and photographic documentation during all rechecks. RESULTS: Surgical stabilization of the cornea was not necessary in any case, because progression of corneal melting was arrested in all cases within 1-20 days of CXL treatment. Corneal re-epithelization occurred within 7-40 days in all eyes. At 40 days after CXL, all eyes presented a quiescent corneal state without signs of active inflammation and with beginning scar formation. The complications observed in three of the six animals included a corneal sequestrum, superficial corneal stromal pigmentation, and bullous keratopathy. CONCLUSIONS: This study shows the feasibility of CXL to treat progressive corneal melting in veterinary patients. CXL may represent a cost-efficient and safe alternative therapy in the treatment for corneal melting in veterinary ophthalmology. More investigations comparing the effectivity and complication rate of CXL to those of standard medical treatment are necessary.

Management, clinical outcomes, and complications of shield ulcers in vernal keratoconjunctivitis.

PURPOSE: To assess the clinical outcomes and complications of shield ulcers by various treatment methods. DESIGN: Retrospective, interventional case series. METHODS: setting: Cornea and anterior segment service of L.V. Prasad Eye Institute, India. study population: One hundred ninety-three eyes of 163 patients clinically diagnosed with vernal keratoconjunctivitis and shield ulcers. intervention: The treatment algorithm was based on the Cameron clinical grading of shield ulcers. Grade 1 ulcers received medical therapy alone. Grade 2 and grade 3 ulcers received either medical therapy alone or medical therapy combined with debridement, amniotic membrane transplantation (AMT), or both. main outcome measures: Re-epithelialization time and best-corrected visual acuity. RESULTS: Grade 1 ulcers were seen in 71 (37%) eyes, grade 2 ulcers were seen in 79 (41%) eyes, and grade 3 ulcers were seen in 43 (22%) eyes. In the grade 1 group, re-epithelialization was seen in 67 (94%) eyes. In the grade 2 group, re-epithelialization was seen in 36 (88%) eyes that received medical treatment, in 20 (95%) eyes that underwent debridement, and in 17 (100%) eyes that underwent AMT. In the grade 3 group, re-epithelialization was seen in only 1 (1.7%) eye that received medical treatment, whereas it was seen in all eyes that underwent debridement and AMT. The mean best-corrected visual acuity after re-epithelialization of the shield ulcer was 20/30, 20/30, and 20/40 in the grade 1, grade 2, and grade 3 groups, respectively. Recurrence and secondary bacterial keratitis were seen in 28 (14.5%) and 20 (10%) eyes, respectively. CONCLUSIONS: Grade 1 shield ulcers respond well to medical therapy alone, whereas grade 2 ulcers occasionally may require additional debridement or AMT. Grade 3 ulcers, however, largely are refractory to medical therapy and require debridement and AMT for rapid re-epithelialization.

Association of single nucleotide polymorphisms of interleukins-1ß, -6, and -12B with contact lens keratitis susceptibility and severity.

PURPOSE: To investigate whether single nucleotide polymorphisms (SNPs) in interleukin (IL)-1ß, IL-6, and IL-12ß are associated with the susceptibility and severity of contact lens-related keratitis. DESIGN: Retrospective, case control study. PARTICIPANTS: One hundred twelve cases of keratitis and 225 controls were recruited from studies conducted at Moorfields Eye Hospital and in Australia during 2003 through 2005. METHODS: Buccal swab samples were collected on Whatman FTA cards and were mailed by post for analysis. IL-1ß (-31), IL-6 (-174, -572, -597), and IL-12B (3'+1158) genotypes were analyzed with pyrosequencing and analyzed using a regression model for susceptibility (sterile, microbial keratitis, controls) and severity. Statistical significance was set at 0.05. MAIN OUTCOME MEASURES: The relative risk of developing contact lens-related keratitis and more severe forms of the disease based on allele, genotype, and haplotype associations. RESULTS: Carriers of IL-6 SNPs were more likely to experience moderate and severe events compared with those with nonmutated genotypes (-174 heterozygous: odds ratio [OR], 3.1; 95% confidence interval [CI], 1.1-8.3; homozygous: OR, 6.4; 95% CI, 1.4-28.4; -174/-597: OR, 4.1; 95% CI, 1.6-11.0). More severe keratitis and microbial keratitis were less likely to occur in wearers with the nonmutated IL-6 haplotype (severity OR, 0.4 [95% CI, 0.2-0.7]; microbial OR, 0.6 [95% CI, 0.4-0.9]). Wearers carrying an IL-12B SNP had an increased risk of sterile keratitis (OR, 9.7; 95% CI, 1.2-76.9) compared with controls. CONCLUSIONS: The IL-6 SNPs are known to reduce protein expression of this cytokine and thus ocular immune defense, and carriers of these SNPs were more likely to experience more severe and microbial keratitis, suggesting that IL-6 decreases the severity and susceptibility of contact lens-related keratitis. Carriers of a functional SNP of IL-12B that is known to increase IL-12 expression and stability are more likely to experience sterile keratitis, suggesting that this is associated with the intense inflammatory reaction that occurs in this condition.

Rituximab en queratitis ulcerativa periférica asociada a artritis reumatoide / Rituximab in rheumatoid arthritis-associated peripheral ulcerative keratitis

Caso clínico: : Se presentan dos pacientes diagnosticadas de artritis reumatoide de largaevolución que desarrollaron una queratitis ulcerativa periférica (QUP) grave. Habían sidotratadas previamente con fármacos modificadores de la enfermedad (FAME) y terapia biológica(TB) sin alcanzar un control clínico-biológico óptimo de su enfermedad. Se trataroninicialmente con corticoides sistémicos a dosis altas sin éxito. Rituximab indujo la regresiónde las lesiones corneales y el control de su artritis reumatoidea.Discusión: Rituximab puede ser una alternativa para detener la progresión de la QUP asociadaa artritis reumatoide refractaria a otros fármacos(AU)

Clinical case: We report two cases of patients affected by longstanding rheumatoid arthritiswho developed a severe form of peripheral ulcerative keratitis (PUK). Neither of them hadan optimal biological and clinical control of their systemic illness despite being treated withseveral disease-modifying antirheumatic drugs (DMARDs) and biologic therapy. High-dosesystemic corticosteroidswere given to treat the PUK without any success. Rituximab resultedin a favourable response with resolution of the corneal lesions and optimal control of theirsystemic illness.Discussion: Rituximab may be an additional tool to arrest progressive rheumatoid arthritisassociatedPUK that is refractory to other drug(AU)

Classifying the severity of corneal ulcers by using the "1, 2, 3" rule.

PURPOSE: To propose and define the "1, 2, 3" rule as a system of categorizing the severity of bacterial keratitis and to determine its value in predicting the likelihood of visual loss after healing of bacterial corneal infection. METHODS: Seventy patients were evaluated for infectious corneal ulcers by 2 cornea subspecialists (J.D.L., M.C.V.) at a tertiary facility between October 30, 2001, and November 1, 2004. Forty-one patients met the inclusion criteria. Visual acuities, ulcer characteristics, culture results, and treatment data were collected. RESULTS: The sensitivity of the "1, 2, 3" rule for detecting potentially sight-threatening (PST) ulcers that would result in 0.20 logMAR (2 Snellen lines) or greater loss in best spectacle-corrected visual acuity (BSCVA) was 100%. The specificity of the "1, 2, 3" rule in correctly labeling an ulcer that did not cause vision loss as rarely sight threatening (RST) was 57.14%. The positive predictive value of the "1, 2, 3" rule was 28.57%. The negative predictive value of the "1, 2, 3" rule was 100%. CONCLUSIONS: Corneal ulcers classified as PST are at significantly higher risk for sustaining loss of BCSVA compared with RST corneal ulcers. The "1, 2, 3" rule is sensitive and specific enough to be clinically useful in predicting which ulcers are more likely to have vision loss and which ulcers are not.

Can subtypes of contact lens-associated corneal infiltrative events be clinically differentiated?

PURPOSE: A schema has recently been described for clinical differentiation among 4 symptomatic subtypes of contact lens-associated corneal infiltrative events (CIEs): microbial keratitis (MK), contact lens-induced peripheral ulcer (CLPU), contact lens-induced acute red eye (CLARE), and infiltrative keratitis (IK). The clinical utility of this schema has been challenged in the literature. The aim of this study is to determine whether it is possible to clinically differentiate among these conditions. METHODS: Criteria for MK, CLPU, CLARE, and IK were applied to a data set of 111 contact lens-associated CIEs, spanning a wide range of clinical severities, presenting consecutively to a hospital clinic. A Venn diagram analysis was used to determine the extent to which these conditions can be clinically differentiated. RESULTS: Of the 111 CIEs, 20% could be classified unambiguously as MK, CLPU, CLARE, or IK, 56% could be classified as 1 of 2 conditions, 13% could be classified as 1 of 3 conditions, and 0% could be classified as 1 of 4 conditions. Eleven percent of CIEs could not be classified as any of the 4 conditions. CONCLUSIONS: Although the etiology of CIEs is multifactorial, the considerable overlap between the clinical presentation of MK, CLPU, CLARE, and IK is such that it is not possible to clinically differentiate between them with any degree of certainty. A preferred approach might be to consider CIEs as part of a disease continuum whereby these events can manifest in various degrees of severity, depending as well on the point at which the condition is observed in the course of the natural history of the disease.

Neural network approach to classify infective keratitis.

PURPOSE: Infective keratitis is a major sight-threatening condition in developing countries like India. An early diagnosis of infective keratitis is critical to its treatment. Epidemiological trends, morphological features of corneal ulceration and presence of other risk factors often dictate choice of initial treatment. This work assesses the usefulness of classification of infective keratitis by artificial neural network (ANN). METHODS: Forty input variables from each of the sixty-three known bacterial or fungal ulcers provided the basis for training a three layer feed-forward neural network. The trained neural network classified another set of forty-three corneal ulcers. RESULTS: Trained artificial neural network could classify correctly all sixty-three cornea ulcers in the training set. In the test set, the artificial neural network correctly classified 39 out of 43 cornea ulcers. Specificity for bacterial and fungal categories was 76.47% and 100% respectively. Accuracy of classification by neural network was 90.7% and compared significantly better than clinicians' prediction of 62.8% (p < 0.01). CONCLUSION: ANN has the potential to help clinicians classify corneal ulcers more accurately.

Management of Mooren's ulceration.

Although the diagnosis may be difficult when a patient first presents with Mooren's ulceration, the clinical appearances are characteristic and should not be confused with other conditions which cause corneal ulceration. Based on the clinical presentation and the low-dose anterior segment fluorescein angiographic findings, there seem to be three distinct varieties of Mooren's ulceration: (1) Unilateral Mooren's ulceration (UM), characterised by an excessively painful progressive corneal ulceration in one eye in elderly patients, associated with non-perfusion of the superficial vascular plexus of the anterior segment. (2) Bilateral aggressive Mooren's ulceration (BAM), which occurs in young patients, progresses circumferentially and, only later, centrally in the cornea. Angiography shows vascular leakage and new vessel formation which extends into the base of the ulcer. (3) Bilateral indolent Mooren's ulceration (BIM), which usually occurs in middle-aged patients presenting with progressive peripheral corneal guttering in both eyes, with little inflammatory response. There is no change from the normal vascular architecture on angiography except an extension of new vessels into the ulcer. The management differs in each of these varieties.

Management of human keratomycosis with miconazole.

A prospective clinical study was undertaken to evaluate the efficacy of 1% miconazole in 85 cases of smear-positive fungal corneal ulcers. Miconazole therapy healed 44 ulcers, thereby achieving a success rate of 64.7%. The most common organism encountered was Aspergillus followed by Fusarium, Philophora and Candida. The average healing time was found to be 22 days. The drug was well tolerated by the eye and no symptoms of ocular toxicity were observed. The findings of this study suggest that miconazole is an effective agent for the management of human keratomycosis.