RESUMEN
Purpose: This study aims to develop and assess an infrastructure using Python-based deep learning code for future diagnostic and management purposes related to dry eye disease (DED) utilizing smartphone images. Design: Cross-sectional study using data which was gathered in Vision Health Research Clinic. Participants: One thousand twenty-one eye images from 734 patients were included in this article that categorizes into 70% females and 30% males, with no sex and age limit. Methods: One specialist captured eye images using Samsung A71 (601 images) and iPhone 11 (420 images) cell phones with the flashlight on and direct gaze to the camera. These images include the area of only 1 eye (left/right). Main Outcome Measures: First, our specialist did 3 different segmentations for every eye image separately for 80% of the training data. This part contains eye, lower eyelid, and iris segmentation. In 20% of test data after automated cropping of the lower eyelid margin and upscaling by 8×, the appropriate tear meniscus height segmentation will be chosen and measured using a deep learning algorithm. Results: The model was trained on 80% of the data and 20% of the data used for validation from both phones with different resolutions. The dice coefficient of the trained model for validation data is 98.68%, and the accuracy of the overall model is 95.39%. Conclusions: It appears that this algorithm holds the potential to herald an evolution in the future of diagnosis and management of DED by homecare devices solely through smartphones. Financial Disclosures: The author(s) have no proprietary or commercial interest in any materials discussed in this article.
RESUMEN
BACKGROUND: Although the mechanism is not clear, the inability of the orbicularis oculi muscle, especially the deeper segment (Horner muscle), is thought to be responsible in epiphora. This study evaluates the effect of the anticholinergic drug pyridostigmine (Mestinon) in patients with patent but dysfunctional lacrimal drainage system. MATERIAL AND METHODS: Twenty patients with bilateral epiphora (mean age:60.78 ± 6.49 yrs) were included in this study. Patients with a patent lacrimal irrigation test based on persistent and symptomatic epiphora, wiping >10 times daily or continuous tearing and grade 4-5 epiphora according to Munk scale, showing neuropathic involvement in the orbicularis oculi muscle by the quantitative motor unit potential (MUP) analysis method were evaluated prospectively. Fluorescein dye disappearance test (a semi-quantitative assessment of delayed tear outflow) together with a Schirmer test reading were performed in order to detect dry eye. The patients were evaluated for tear meniscus measurements by anterior segment optical coherence topography (OCT) and non-invasive tear break-up time (NI-BUT) was measured by Oculus Keratograph 5 M. Those with a NI-BUT value above 10 s, without eyelid laxity, previous ocular surgery or ocular surface disease, or nasolacrimal duct obstruction, and who agreed to use the drug were included in the study. Each subject underwent OCT measurements of the lower tear meniscus of both eyes before and 15 mins after taking Mestinon (1 × 60 mg tablet). Upon measurement of the positive effect of the drug on tear meniscus height (TMH), the patients were asked to continue this regime daily for 1 month and then evaluated for relief in their epiphora complaints and any systemic drug side effects. RESULTS: A total of 20 patients (40 eyes) with bilateral epiphora were included in the study. All eyes had grade 4 Munk-score epiphora, Schirmer's test was within the normal range in all eyes (mean, 14 ± 4 mm), and patent lacrimal irrigation test. The lower mean TMH reductions 15 min after Mestinon in the right and left eyes were 135.41 ± 85.47 and 55.44 ± 61.56 mm, respectively, a statistically significant decrease in both eyes (p = 0.001, p < 0.01). The mean tear meniscus area (TMA) in the right and left eyes was 131.83 ± 68.27 mm2 and 62.72 ± 50.57 mm2, respectively; 15 mins after administration of Mestinon, the mean TMA in the right and left eyes was 77.27 ± 48.34 and 59.18 ± 44.74 mm2, respectively (p = 0.001, p < 0.01). The mean decreases of 54.56 ± 39.34 mm2 in the right eye area and 3.53 ± 42.32 mm2 in the left eye area were statistically significant (p = 0.041, p < 0.05). CONCLUSION: Symptomatic relief for epiphora cannot be achieved with known treatment options due to lacrimal pump dysfunction. We found that pyridostigmine (Mestinon) provided relief in patients' complaints of epiphora consistent with a significant reduction in TMH levels.