Customized Reconstruction of Lower Eyelid Defects.

BACKGROUND: A lower eyelid defect is a loss of skin, muscle, and underlying structures that can occur due to trauma, malignant or benign tumors, burns, or other causes. The conventional surgical treatment of lower lid defects has several limitations, including visible scarring, narrowing of the eye, and ectropion. Here, we combined the use of a customized mid-face lift with a free mucochondral graft to overcome the disadvantages of existing methods. METHODS: Forty patients underwent reconstructive surgery using a customized mid-face lift with or without a free mucochondral graft for a lower lid defect between April 2013 and October 2020. Patients were discharged shortly after surgery and were expected to visit the outpatient clinic periodically for 12 months. RESULTS: The causes of lower eyelid defects were malignancy, trauma, foreign body granuloma, and other causes. Four patients reported complications, including 2 cases of chemosis, 1 case of a hematoma, and 1 case of corneal abrasion, who reportedly performed well after 2 weeks of conservative therapy. No patient required revision during the average follow-up period. CONCLUSIONS: Customized reconstruction demonstrated a better aesthetic reconstruction of the lower eyelid. This method represents a good option for reconstructing lower lid defects.

Introduction of Deep Learning-Based Infrared Image Analysis to Marginal Reflex Distance1 Measurement Method to Simultaneously Capture Images and Compute Results: Clinical Validation Study.

Marginal reflex distance1 (MRD1) is a crucial clinical tool used to evaluate the position of the eyelid margin in relation to the cornea. Traditionally, this assessment has been conducted manually by plastic surgeons, ophthalmologists, or trained technicians. However, with the advancements in artificial intelligence (AI) technology, there is a growing interest in the development of automated systems capable of accurately measuring MRD1. In this context, we introduce novel MRD1 measurement methods based on deep learning algorithms that can simultaneously capture images and compute the results. This prospective observational study involved 154 eyes of 77 patients aged over 18 years who visited Chungnam National University Hospital between 1 January 2023 and 29 July 2023. We collected four different MRD1 datasets from patients using three distinct measurement methods, each tailored to the individual patient. The mean MRD1 values, measured through the manual method using a penlight, the deep learning method, ImageJ analysis from RGB eye images, and ImageJ analysis from IR eye images in 56 eyes of 28 patients, were 2.64 ± 1.04 mm, 2.85 ± 1.07 mm, 2.78 ± 1.08 mm, and 3.07 ± 0.95 mm, respectively. Notably, the strongest agreement was observed between MRD1_deep learning (DL) and MRD1_IR (0.822, p < 0.01). In a Bland-Altman plot, the smallest difference was observed between MRD1_DL and MRD1_IR ImageJ, with a mean difference of 0.0611 and ΔLOA (limits of agreement) of 2.5162, which was the smallest among all of the groups. In conclusion, this novel MRD1 measurement method, based on an IR camera and deep learning, demonstrates statistical significance and can be readily applied in clinical settings.

Smartphone-Based LiDAR Application for Easy and Accurate Wound Size Measurement.

The accurate assessment of wound size is a critical step in advanced wound care management. This study aims to introduce and validate a Light Detection and Ranging (LiDAR) technique for measuring wound size. Twenty-eight wounds treated from December 2022 to April 2023 at the Chungnam National University Hospital were analyzed. All the wounds were measured using three techniques: conventional ruler methods, the LiDAR technique, and ImageJ analysis. Correlation analysis, linear regression, and Bland-Altman plot analysis were performed to validate the accuracy of the novel method. The measurement results (mean ± standard deviation) obtained using the ruler method, LiDAR technique, and ImageJ analysis were 112.99 ± 110.07 cm2, 73.59 ± 72.97 cm2, and 74.29 ± 72.15 cm2, respectively. The Pearson correlation coefficient was higher for the LiDAR application (0.995) than for the conventional ruler methods (mean difference, -5.0000 cm2), as was the degree of agreement (mean difference, 38.6933 cm2). Wound size measurement using LiDAR is a simple and reliable method that will enable practitioners to conveniently assess wounds with a flattened and irregular shape with higher accuracy. However, non-flattened wounds cannot be assessed owing to the technical limitations of LiDAR.