Automated Ocular Surface Image Analysis and Health-Related Quality of Life Utility Tool to Measure Blepharokeratoconjunctivitis Activity in Children

Definition and Diagnostic Criteria for Pediatric Blepharokeratoconjunctivitis

Importance

Pediatric blepharokeratoconjunctivitis (PBKC) is a chronic, sight-threatening inflammatory ocular surface disease. Due to the lack of unified terminology and diagnostic criteria, nonspecific symptoms and signs, and the challenge of differentiation from similar ocular surface disorders, PBKC may be frequently unrecognized or diagnosed late.

Objective

To establish a consensus on the nomenclature, definition, and diagnostic criteria of PBKC.

Design, Setting, and Participants

This quality improvement study used expert panel and agreement applying the non-RAND modified Delphi method and open discussions to identify unified nomenclature, definition, and definitive diagnostic criteria for PBKC. The study was conducted between September 1, 2021, and August 14, 2022. Consensus activities were carried out through electronic surveys via email and online virtual meetings.

Results

Of 16 expert international panelists (pediatric ophthalmologists or cornea and external diseases specialists) chosen by specific inclusion criteria, including their contribution to scientific leadership and research in PBKC, 14 (87.5%) participated in the consensus. The name proposed was "pediatric blepharokeratoconjunctivitis," and the agreed-on definition was "Pediatric blepharokeratoconjunctivitis is a frequently underdiagnosed, sight-threatening, chronic, and recurrent inflammatory eyelid margin disease associated with ocular surface involvement affecting children and adolescents. Its clinical spectrum includes chronic blepharitis, meibomitis, conjunctivitis, and corneal involvement ranging from superficial punctate keratitis to corneal infiltrates with vascularization and scarring." The diagnostic criteria included 1 or more suggestive symptoms accompanied by clinical signs from 3 anatomical regions: the eyelid margin, conjunctiva, and cornea. For PBKC suspect, the same criteria were included except for corneal involvement.

Conclusions and Relevance

The agreements on the name, definition, and proposed diagnostic criteria of PBKC may help ophthalmologists avoid diagnostic confusion and recognize the disease early to establish adequate therapy and avoid sight-threatening complications. The diagnostic criteria rely on published evidence, analysis of simulated clinical cases, and the expert panel's clinical experience, requiring further validation with real patient data analysis.

A comparison of subjective and objective conjunctival hyperaemia grading with AOS® Anterior software

Clinical relevance: This study evaluates a commercially available conjunctival hyperaemia grading system, providing validation of an important tool for ocular surface research and clinical trials.Background: Bulbar conjunctival hyperaemia is a sign of ocular surface inflammation, and proper measurement is essential to clinical care and trials. The aim of this study was to assess the validity and repeatability of an objective grading system in comparison with subjective grading.Methods: This study was a retrospective, randomised analysis of 300 bulbar conjunctival images that were collected at an academic institution. The images used were de-identified and collected from the Keratograph K5 and Haag-Streit slitlamp. Six investigators graded the images with either a 0.1 or 0.5 unit scaling using a 0-4 Efron grading scale. Three of the investigators also imported the images into the AOS ® Anterior software and graded them objectively. All measurement techniques were assessed for repeatability and comparability to each other.Results: Mean hyperaemia with the objective system (1.1 ± 0.7) was significantly less than the subjective grading (2.0 ± 0.8) (P < 0.001). Both inter- and intra-subject repeatability of the objective system (0.15) was better than the subjective methods (1.70).Conclusion: The results showed excellent repeatability of the AOS ® Anterior objective conjunctival hyperaemia grading software, although they were not found to be interchangeable with subjective scores. This system has value in monitoring levels of hyperaemia in contact lens wearers and patients in clinical care and research trials.

Adopting low-shot deep learning for the detection of conjunctival melanoma using ocular surface images

BACKGROUND AND OBJECTIVE

The purpose of the present study was to investigate low-shot deep learning models applied to conjunctival melanoma detection using a small dataset with ocular surface images.

METHODS

A dataset was composed of anonymized images of four classes; conjunctival melanoma (136), nevus or melanosis (93), pterygium (75), and normal conjunctiva (94). Before training involving conventional deep learning models, two generative adversarial networks (GANs) were constructed to augment the training dataset for low-shot learning. The collected data were randomly divided into training (70%), validation (10%), and test (20%) datasets. Moreover, 3D melanoma phantoms were designed to build an external validation set using a smartphone. The GoogleNet, InceptionV3, NASNet, ResNet50, and MobileNetV2 architectures were trained through transfer learning and validated using the test and external validation datasets.

RESULTS

The deep learning model demonstrated a significant improvement in the classification accuracy of conjunctival lesions using synthetic images generated by the GAN models. MobileNetV2 with GAN-based augmentation displayed the highest accuracy of 87.5% in the four-class classification and 97.2% in the binary classification for the detection of conjunctival melanoma. It showed an accuracy of 94.0% using 3D melanoma phantom images captured using a smartphone camera.

CONCLUSIONS

The present study described a low-shot deep learning model that can detect conjunctival melanomas using ocular surface images. To the best of our knowledge, this study is the first to develop a deep learning model to detect conjunctival melanoma using a digital imaging device such as smartphone camera.

Evaluation of dry eye disease in children with blepharokeratoconjunctivitis

OBJECTIVE

To evaluate the symptoms and signs of dry eye disease (DED) in children diagnosed with blepharokeratoconjunctivitis (BKC).

DESIGN

Prospective case-controlled study PARTICIPANTS: Consecutive patients with BKC and normal controls.

METHODS

All participants underwent a comprehensive dry eye assessment including the Canadian Dry Eye Assessment (CDEA) questionnaire, tear film osmolarity test, Schirmer's test without anesthesia, slit lamp examination, tear film break-up time, corneal fluorescein staining (CFS), and lissamine green conjunctival staining (LGCS), according to the Sjögren's International Collaborative Clinical Alliance ocular staining score. For each test the result of the more severe eye was included in the statistical analysis.

RESULTS

Twenty-five patients were recruited-11 with BKC and 14 healthy controls. No difference in symptoms was found between children with BKC (CDEA score 6.1 ± 5.5) and normal controls (CDEA score 3.6 ± 3.2; p = 0.16). Children with BKC had significantly higher mean CFS (1.1 ± 1.6 vs 0.1 ± 0.4; p = 0.04) but similar mean LGCS (1.4 ± 1.8 vs 1.5 ± 2.1; p = 0.81) than normal controls. No statistically significant differences were observed in other tests between the 2 groups. CDEA scores were significantly correlated to CFS in normal controls (r = 0.59, p = 0.03), and approached significance in children with BKC (r = 0.56, p = 0.07).

CONCLUSIONS

The only test that can distinguish DED in patients with BKC from children without BKC is the CFS score. This should guide management and monitoring of this unique patient population with DED symptoms and signs.