Deep learning-based image analysis for automated measurement of eyelid morphology before and after blepharoptosis surgery

Abstract Background and aim Eyelid position and contour abnormality could lead to various diseases, such as blepharoptosis, which is a common eyelid disease. Accurate assessment of eyelid morphology is important in the management of blepharoptosis. We aimed to proposed a novel deep learning-based image analysis to automatically measure eyelid morphological properties before and after blepharoptosis surgery. Methods This study included 135 ptotic eyes of 103 patients who underwent blepharoptosis surgery. Facial photographs were taken preoperatively and postoperatively. Margin reflex distance (MRD) 1 and 2 of the operated eyes were manually measured by a senior surgeon. Multiple eyelid morphological parameters, such as MRD1, MRD2, upper eyelid length and corneal area, were automatically measured by our deep learning-based image analysis. Agreement between manual and automated measurements, as well as two repeated automated measurements of MRDs were analysed. Preoperative and postoperative eyelid morphological parameters were compared. Postoperative eyelid contour symmetry was evaluated using multiple mid-pupil lid distances (MPLDs). Results The intraclass correlation coefficients (ICCs) between manual and automated measurements of MRDs ranged from 0.934 to 0.971 (p < .001), and the bias ranged from 0.09 mm to 0.15 mm. The ICCs between two repeated automated measurements were up to 0.999 (p < .001), and the bias was no more than 0.002 mm. After surgery, MRD1 increased significantly from 0.31 ± 1.17 mm to 2.89 ± 1.06 mm, upper eyelid length from 19.94 ± 3.61 mm to 21.40 ± 2.40 mm, and corneal area from 52.72 ± 15.97 mm2 to 76.31 ± 11.31mm2 (all p < .001). Postoperative binocular MPLDs at different angles (from 0° to 180°) showed no significant differences in the patients. Conclusion This technique had high accuracy and repeatability for automatically measuring eyelid morphology, which allows objective assessment of blepharoptosis surgical outcomes. Using only patients’ photographs, this technique has great potential in diagnosis and management of other eyelid-related diseases.

[1]  L. Heindl,et al.  A novel approach quantifying the periorbital morphology: A comparison of direct, 2-dimensional, and 3-dimensional technologies. , 2020, Journal of plastic, reconstructive & aesthetic surgery : JPRAS.

[2]  D. Garcia,et al.  Lower Eyelid Contour in Graves Orbitopathy , 2019, Current eye research.

[3]  Juan Ye,et al.  A Novel Approach for Automated Eyelid Measurements in Blepharoptosis Using Digital Image Analysis , 2019, Current eye research.

[4]  Amir Sadeghipour,et al.  Artificial intelligence in retina , 2018, Progress in Retinal and Eye Research.

[5]  Vijayan K. Asari,et al.  Nuclei Segmentation with Recurrent Residual Convolutional Neural Networks based U-Net (R2U-Net) , 2018, NAECON 2018 - IEEE National Aerospace and Electronics Conference.

[6]  R. Goldberg,et al.  A novel technique for the measurement of eyelid contour to compare outcomes following Muller’s muscle-conjunctival resection and external levator resection surgery , 2018, Eye.

[7]  Sang Joon Park,et al.  Topographic analysis of eyelid position using digital image processing software , 2017, Acta ophthalmologica.

[8]  Rao V. Chundury,et al.  Eyelid Contour Following Conjunctival Müllerectomy With or Without Tarsectomy Blepharoptosis Repair , 2016, Ophthalmic plastic and reconstructive surgery.

[9]  S. Baek,et al.  Analysis of Surgical Outcome After Levator Advancement by Assessing Changes in Eyelid Contour , 2016, The Journal of craniofacial surgery.

[10]  Zachary M. Bodnar,et al.  Automated Ptosis Measurements From Facial Photographs. , 2016, JAMA ophthalmology.

[11]  A. Nemet.  Accuracy of Marginal Reflex Distance Measurements in Eyelid Surgery , 2015, The Journal of craniofacial surgery.

[12]  Youness Aliyari Ghassabeh,et al.  A sufficient condition for the convergence of the mean shift algorithm with Gaussian kernel , 2015, J. Multivar. Anal..

[13]  S. Baek,et al.  Analysis of Lid Contour Change with Aging in Asians by Measuring Midpupil Lid Distance , 2014, Plastic and reconstructive surgery.

[14]  Josephine Sullivan,et al.  One millisecond face alignment with an ensemble of regression trees , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  E. Karabulut,et al.  The Expression and Comparison of Healthy and Ptotic Upper Eyelid Contours Using a Polynomial Mathematical Function , 2014, Current eye research.

[16]  Tomokazu Nishihira,et al.  A New Digital Image Analysis System for Measuring Blepharoptosis Patients’ Upper Eyelid and Eyebrow Positions , 2014, Annals of plastic surgery.

[17]  S. Kim.  Effects in the Upper Face of Far East Asians After Oriental Blepharoplasty: A Scientific Perspective on Why Oriental Blepharoplasty is Essential , 2013, Aesthetic Plastic Surgery.

[18]  Francisco G. Bravo,et al.  Incidence of lower eyelid asymmetry: an anthropometric analysis of 204 patients. , 2013, Aesthetic surgery journal.

[19]  Chia-Cheng Chen,et al.  Assessing agreement with intraclass correlation coefficient and concordance correlation coefficient for data with repeated measures , 2013, Comput. Stat. Data Anal..

[20]  A. Rocha-Sousa,et al.  Lateral and Medial Upper Eyelid Contour Abnormalities in Graves Orbitopathy: The Influence of the Degree of Retraction , 2013, Ophthalmic plastic and reconstructive surgery.

[21]  D. Garcia,et al.  Pre- and Postoperative Quantitative Analysis of Contour Abnormalities in Graves Upper Eyelid Retraction , 2012, Ophthalmic plastic and reconstructive surgery.

[22]  A. Putterman.  Margin reflex distance (MRD) 1, 2, and 3. , 2012, Ophthalmic plastic and reconstructive surgery.

[23]  D. Garcia,et al.  Multiple radial midpupil lid distances: a simple method for lid contour analysis. , 2012, Ophthalmology.

[24]  Seyed Benyamin Dalirsefat,et al.  Comparison of Similarity Coefficients used for Cluster Analysis with Amplified Fragment Length Polymorphism Markers in the Silkworm, Bombyx mori , 2009, Journal of insect science.

[25]  Catey Bunce,et al.  Correlation, agreement, and Bland-Altman analysis: statistical analysis of method comparison studies. , 2009, American journal of ophthalmology.

[26]  C Bunce,et al.  Repeatability and reproducibility of upper eyelid measurements , 2001, The British journal of ophthalmology.

[27]  A. V. Cruz,et al.  The Geometrical Basis of the Eyelid Contour , 2000, Ophthalmic plastic and reconstructive surgery.

[28]  J. Nerad.  Eyelid Reconstruction , 2021, Techniques in Ophthalmic Plastic Surgery.

[29]  Priyanka Chhadva,et al.  Blepharoptosis repair , 2018, Current opinion in otolaryngology & head and neck surgery.

[30]  Liu Guo-xiang,et al.  Fast algorithm for circle detection using randomized Hough transform , 2008 .