Contour Symmetry of the Upper Eyelid Following Bilateral Conjunctival-Müller's Muscle Resection

Automatic Measurement and Comparison of Normal Eyelid Contour by Age and Gender Using Image-Based Deep Learning

Purpose

This study aimed to propose a fully automatic eyelid measurement system and compare the contours of both the upper and lower eyelids of normal individuals according to age and gender.

Design

Prospective study.

Participants

Five hundred and forty healthy Chinese aged 0 to 79 years in a tertiary hospital were included.

Methods

Facial images in the primary gazing position were used to train and test the proposed automatic system for eye recognition and eye segmentation. According to the 10-millimeter diameter circular marker, measurements were transformed from pixel sizes into factual distances.

Main Outcome Measures

Midpupil lid distances (MPLDs) every 15° of all participants were automatically measured in both genders (30 males and 30 females in each age group) by the proposed deep learning (DL)-based system. Intraclass correlation coefficients (ICCs) were performed to assess the agreement between the automatic and manual margin reflex distances (MRDs). The eyelid contour, eyelid asymmetry, and palpebral fissure obliquity were analyzed using MPLD, temporal-versus-nasal MPLD ratio, and the angle between the inner and outer canthi, respectively.

Results

The measurement of MRDs by the automatic system excellently agreed with that of the expert, with ICCs ranging from 0.863 to 0.886. As the age of the participants increased, the values of MPLDs reached a peak in those in their 20s or 30s and then gradually decreased at all angles. The temporal sector showed greater changes in MPLDs than the nasal sector, and the changes were more significant in females than in males. The maximum value of palpebral fissure obliquity appeared before 10 years in both genders and remained relatively stable after the 20s (P > 0.05).

Conclusions

The proposed DL-based eyelid analysis system allowed automatic, accurate, and comprehensive measurement of the eyelid contour. The refinement of eyelid shape quantification could be beneficial for future objective assessment preocular and postocular plastic surgery.

Financial Disclosures

The authors have no proprietary or commercial interest in any materials discussed in this article.

Chasing the objective upper eyelid symmetry formula; R2, RMSE, POC, MAE, and MSE

PURPOSE

Investigate the most appropriate mathematical formula to objectively express upper eyelid contour symmetry.

METHODS

62 eyes of 31 patients were included in the study. The upper eyelid contour symmetry of the patients was classified subjectively (independent of MRD1) as poor, acceptable, and good by three oculoplastic specialists (senior, expert, and junior surgeon). Bézier curves of the upper lid contour were drawn with ImageJ software (NIH, Bethesda, MA, USA). Using the algorithms created by Author SKC in Spyder (Python 3.7.9.), the symmetry of the Bézier curves of the left eyelids were obtained according to the y-axis, and the mid-pupils of both eyes were superimposed. The lower curve moved vertically to the equal height of the other curve to equalize MRD1's. R2 (Coefficient of determination), RMSE (Root-mean-square error), MSE (Mean squared error), POC (Percentage of co-efficiency), and MAE (Mean absolute error) were calculated. We evaluated the correlation between these objective formulas and the subjective grading of three surgeons using Spearman's rho (ρ).

RESULTS

The correlation coefficient of RMSE and MSE were the same for all surgeons grading. There was a strong correlation between the senior surgeon's subjective scoring (N; poor = 8, acceptable = 16, good = 8) and R2, RMSE, POC, MAE (ρ = 0.643, p < 0.001, ρ = -0.607, p < 0.001, ρ = 0.562, p < 0.001, ρ = -0.517, p < 0.001, respectively). We found a strong relationship between the expert surgeon's subjective scoring (N; poor = 9, acceptable = 13, good:10) and R2 (ρ = 0.611, p < 0.001), RMSE (ρ = -0.549, p < 0.001), POC (ρ = 0.511, p < 0.001), and MAE (ρ = -0.450, p < 0.05). We found a strong correlation between junior surgeon's subjective scoring (N; poor = 6, acceptable = 18, good = 8) and R2, RMSE, and POC (ρ: -0.517, p < 0.001; ρ: -0.470, p < 0.001; ρ: 0.521, p < 0.001; respectively) and moderate correlation between MAE (ρ:-0.394, p < 0.05). The highest correlation is observed with R2.

CONCLUSIONS

RMSE, MSE, POC, MAE, and especially R2, may quantitatively express upper eyelid contour symmetry, comparable with the oculoplastic surgeon. The highest correlation was observed between the senior surgeon and R2, and decreases with the experience of the surgeon.

Development of a neural network-based automated eyelid measurement system

The purpose of this study was to assess the clinical utility and reliability of an automated eyelid measurement system utilizing neural network (NN) technology. Digital images of the eyelids were taken from a total of 300 subjects, comprising 100 patients with Graves' orbitopathy (GO), 100 patients with ptosis, and 100 controls. An automated measurement system based on NNs was developed to measure margin-reflex distance 1 and 2 (MRD1 and MRD2), as well as the lengths of the upper and lower eyelids. The results were then compared with values measured using the manual technique. Automated measurements of MRD1, MRD2, upper eyelid length, and lower eyelid length yielded values of 3.2 ± 1.7 mm, 6.0 ± 1.4 mm, 32.9 ± 6.1 mm, and 29.0 ± 5.6 mm, respectively, showing a high level of agreement with manual measurements. To evaluate the morphometry of curved eyelids, the distance from the midpoint of the intercanthal line to the eyelid margin was measured. The minimum number of divisions for detecting eyelid abnormalities was determined to be 24 partitions (15-degree intervals). In conclusion, an automated NN-based measurement system could provide a straightforward and precise method for measuring MRD1 and MRD2, as well as detecting morphological abnormalities in the eyelids.

Outcomes of conjunctival-Müller's muscle resection surgery with and without epinephrine in local anesthetic

Purpose: To determine the effect of epinephrine as an anesthetic adjunct on outcomes of conjunctival-Müller's muscle resection (CMMR) ptosis surgery.Methods: A retrospective cohort study of patients having undergone CMMR with plain local anesthetic (LA) and local anesthetic combined with epinephrine (LA+Epi). Two measures of success were investigated: margin to reflex distance 1 (MRD1) success and overall success. MRD1 success was defined as a postoperative MRD1 between 2-4 mm. Overall success was defined as all of i) MRD1 success, ii) a ≤ 1 mm difference between the eyelid height following the preoperative phenylephrine test and post-operative MRD1 (PE-MRD1 Δ), and iii) symmetrical postoperative contour between both upper eyelids. Study inclusion criteria included blepharoptosis from levator aponeurotic dehiscence and satisfactory response to the phenylephrine test. Exclusion criteria included congenital ptosis, ptosis secondary to another cause, previous ipsilateral eyelid surgery, or a medical condition that may have impacted surgery.Results: There were 26 eyelids in the LA+Epi group, and 19 eyelids in the LA group. There was no difference in the two groups in age (P =0.28), pre-operative MRD1 (P =0.37), levator function (P =0.27), intraoperative tissue resection amount (P =0.27), number of weeks postoperatively at final MRD1 measurement (P =0.99), and PE-MRD1 Δ (P =0.08). All patients achieved a symmetrical post-operative eyelid contour. The LA+Epi group had a higher attainment of MRD1 success (P =0.04) and overall success (P =0.045).Conclusions: Epinephrine as an anesthetic adjunct improves CMMR outcome. This suggests its use can be considered the standard of care.