From the diagnosis of infectious keratitis to discriminating fungal subtypes; a deep learning-based study.

Infectious keratitis (IK) is a major cause of corneal opacity. IK can be caused by a variety of microorganisms. Typically, fungal ulcers carry the worst prognosis. Fungal cases can be subdivided into filamentous and yeasts, which shows fundamental differences. Delays in diagnosis or initiation of treatment increase the risk of ocular complications. Currently, the diagnosis of IK is mainly based on slit-lamp examination and corneal scrapings. Notably, these diagnostic methods have their drawbacks, including experience-dependency, tissue damage, and time consumption. Artificial intelligence (AI) is designed to mimic and enhance human decision-making. An increasing number of studies have utilized AI in the diagnosis of IK. In this paper, we propose to use AI to diagnose IK (model 1), differentiate between bacterial keratitis and fungal keratitis (model 2), and discriminate the filamentous type from the yeast type of fungal cases (model 3). Overall, 9329 slit-lamp photographs gathered from 977 patients were enrolled in the study. The models exhibited remarkable accuracy, with model 1 achieving 99.3%, model 2 at 84%, and model 3 reaching 77.5%. In conclusion, our study offers valuable support in the early identification of potential fungal and bacterial keratitis cases and helps enable timely management.

A novel technique for small-incision levator resection with a double mattress suture for ptosis correction.

PURPOSE: To introduce a novel technique for small-incision levator resection in ptosis surgery and evaluate its efficacy in a pilot study among patients affected by congenital or aponeurotic ptosis. METHODS: We prospectively enrolled congenital and aponeurotic ptosis patients if their levator function was not poor (≥5 mm) from June 2021 through October 2022. Surgical technique involved a 1-cm lid crease incision, minimal dissection, and creating a loop passing through the tarsus and levator aponeurosis. Success was defined as postoperative MRD-1 ≥3 mm and inter-eyelid MRD-1 difference ≤1 mm. Eyelid contour quality was scored excellent, good, fair, and poor according to its curvature and symmetry. RESULTS: Sixty-seven eyes (35 congenital and 32 aponeurotic) were included in the study. Mean age was 34±19 years (range, 5-79 years). Mean preoperative levator function and levator resection amount were 9.53 mm and 8.39 mm in the congenital group and 12.34 mm and 4.15 mm in the aponeurotic group, respectively. Mean pre- and postoperative MRD-1 was 1.61 mm and 3.27 mm respectively (P<0.001). The overall success rate was 82.1% (95% C.I: 71.7-89.8%); the result was failure in 12 cases, of which 11 had under-correction. Preoperative MRD-1 was correlated with a success rate (P=0.017). CONCLUSION: The described technique shows non-inferior results to the previously described surgical methods and also it shows very good lid contour outcome and minimal lag. The findings suggest that the double mattress single suture technique can be used in both congenital and aponeurotic ptosis.

Microbiological study on foreign body and vitreous samples of patients with intraocular foreign body.

OBJECTIVE: To evaluate the relationship between the microbiological results of the vitreous humor and those of foreign body specimens in patients with intraocular foreign body (IOFB). METHODS: Seventy-one patients with an IOFB were included in this descriptive prospective case series. All patients underwent immediate IOFB removal. Vitreous sampling was performed during vitrectomy. Foreign bodies were placed directly into culture media for microbiological study. RESULTS: Thirteen (18.3%) patients developed endophthalmitis. The results of microbiological analysis of IOFB and vitreous humor specimens were negative in nine patients and positive in four. Fifty-eight (81.6%) patients with an IOFB had no evidence of endophthalmitis. Among them, seven patients showed positive microbiological results of foreign bodies with no manifestations of endophthalmitis. In five patients, a Staphylococcus epidermidis strain was observed in the culture of the IOFB specimen. Two patients had only positive smear test results of their vitreous humor specimen. CONCLUSION: A correlation appears to be present between the microbiological results of the vitreous humor and IOFB specimens in patients with clinical findings of endophthalmitis but not in patients with a pure IOFB without clinical features of endophthalmitis. This may justify early use of intravitreal and intravenous antibiotics before the development of endophthalmitis.