Automated corneal endothelium image segmentation in the presence of cornea guttata via convolutional neural networks

Automated cell counting in in-vivo specular microscopy images is challenging, especially in situations where single-cell segmentation methods fail due to pathological conditions. This work aims to obtain reliable cell segmentation from specular microscopy images of both healthy and pathological corneas. We cast the problem of cell segmentation as a supervised multi-class segmentation problem. The goal is to learn a mapping relation between an input specular microscopy image and its labeled counterpart, indicating healthy (cells) and pathological regions (e.g., guttae). We trained a U-net model by extracting 96×96 pixel patches from corneal endothelial cell images and the corresponding manual segmentation by a physician. Encouraging results show that the proposed method can deliver reliable feature segmentation enabling more accurate cell density estimations for assessing the state of the cornea.

[1]  Lucas J. van Vliet,et al.  Fully convolutional architecture vs sliding-window CNN for corneal endothelium cell segmentation , 2019, BMC biomedical engineering.

[2]  S. Jacob.  Endothelium , 2002, Surgical Anatomy for Endothelial Keratoplasty.

[3]  R. Laing,et al.  Endothelial mosaic in Fuchs' dystrophy. A qualitative evaluation with the specular microscope. , 1981, Archives of ophthalmology.

[4]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[5]  Stanley S. Ipson,et al.  A fully automated cell segmentation and morphometric parameter system for quantifying corneal endothelial cell morphology , 2018, Comput. Methods Programs Biomed..

[6]  S. Riazuddin,et al.  Fuchs Corneal Dystrophy. , 2015, Progress in molecular biology and translational science.

[7]  A. Graham,et al.  Morphometry of Cells and Guttae in Subjects With Normal or Guttate Endothelium With a Contour Detection Algorithm , 2005, Eye & contact lens.

[8]  Alfredo Ruggeri,et al.  Development of a Reliable Automated Algorithm for the Morphometric Analysis of Human Corneal Endothelium , 2016, Cornea.

[9]  S. Feizi.  Corneal endothelial cell dysfunction: etiologies and management , 2018, Therapeutic advances in ophthalmology.

[10]  Thomas Reinhard,et al.  Automated segmentation of the corneal endothelium in a large set of ‘real-world’ specular microscopy images using the U-Net architecture , 2019, Scientific Reports.

[11]  Giovanni Volpe,et al.  Digital video microscopy enhanced by deep learning , 2018, Optica.

[12]  Andrés G. Marrugo,et al.  Generating density maps for convolutional neural network-based cell counting in specular microscopy images , 2020, Journal of Physics: Conference Series.

[13]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[14]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[15]  P. Camacho,et al.  Long-term endothelial cell loss with the iris-claw intraocular phakic lenses (Artisan®) , 2019, Graefe's Archive for Clinical and Experimental Ophthalmology.

[16]  Gregory R. Johnson,et al.  Label-free prediction of three-dimensional fluorescence images from transmitted light microscopy , 2018, Nature Methods.

[17]  Cris L. Luengo Hendriks,et al.  Fully automatic evaluation of the corneal endothelium from in vivo confocal microscopy , 2015, BMC Medical Imaging.

[18]  Karolina Nurzynska,et al.  Deep Learning as a Tool for Automatic Segmentation of Corneal Endothelium Images , 2018, Symmetry.

[19]  V. Galvis,et al.  Indications and techniques of corneal transplantation in a referral center in Colombia, South America (2012–2016) , 2018, International Ophthalmology.

[20]  V. Galvis,et al.  Human corneal endothelium regeneration: effect of ROCK inhibitor. , 2013, Investigative ophthalmology & visual science.

[21]  Matthieu Chabanas,et al.  Automatic segmentation of brain tumor resections in intraoperative ultrasound images using U-Net , 2020, Journal of medical imaging.

[22]  P. Camacho,et al.  Send Orders of Reprints at Reprints@benthamscience.net Corneal Transplantation at an Ophthalmological Referral Center in Colombia: Indications and Techniques (2004-2011) , 2022 .

[23]  Alfredo Ruggeri,et al.  Automated morphometric description of human corneal endothelium from in-vivo specular and confocal microscopy , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[24]  Thomas Brox,et al.  U-Net: deep learning for cell counting, detection, and morphometry , 2018, Nature Methods.

[25]  A. Ruggeri,et al.  A system for the automatic estimation of morphometric parameters of corneal endothelium in alizarine red-stained images , 2010, British Journal of Ophthalmology.