Convolution neural network for contour extraction of corneal endothelial cells

Katafuchi, Saya; Yoshimura, Motohide

doi:10.1117/12.2264430

Cited by 5 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, we already solved that dataset, achieving a segmentation error in only 0.28% of the cells and an average error in the clinical parameter estimates of less than 0.4% [28]. Katafuchi et al [33] also used a CNN in a sliding-window setup to segment human endothelium in vivo, although they did not specify the imaging technology. They also employed a similar network as Cireşan et al [3], and they achieved an error rate of 12%.…”

Section: Introductionmentioning

confidence: 99%

Fully convolutional architecture vs sliding-window CNN for corneal endothelium cell segmentation

et al. 2019

View full text Add to dashboard Cite

Background: Corneal endothelium (CE) images provide valuable clinical information regarding the health state of the cornea. Computation of the clinical morphometric parameters requires the segmentation of endothelial cell images. Current techniques to image the endothelium in vivo deliver low quality images, which makes automatic segmentation a complicated task. Here, we present two convolutional neural networks (CNN) to segment CE images: a global fully convolutional approach based on U-net, and a local sliding-window network (SW-net). We propose to use probabilistic labels instead of binary, we evaluate a preprocessing method to enhance the contrast of images, and we introduce a postprocessing method based on Fourier analysis and watershed to convert the CNN output images into the final cell segmentation. Both methods are applied to 50 images acquired with an SP-1P Topcon specular microscope. Estimates are compared against a manual delineation made by a trained observer. Results: U-net (AUC = 0.9938) yields slightly sharper, clearer images than SW-net (AUC = 0.9921). After postprocessing, U-net obtains a DICE = 0.981 and a MHD = 0.22 (modified Hausdorff distance), whereas SW-net yields a DICE = 0.978 and a MHD = 0.30. U-net generates a wrong cell segmentation in only 0.48% of the cells, versus 0.92% for the SW-net. U-net achieves statistically significant better precision and accuracy than both, Topcon and SW-net, for the estimates of three clinical parameters: cell density (ECD), polymegethism (CV), and pleomorphism (HEX). The mean relative error in U-net for the parameters is 0.4% in ECD, 2.8% in CV, and 1.3% in HEX. The computation time to segment an image and estimate the parameters is barely a few seconds. Conclusions: Both methods presented here provide a statistically significant improvement over the state of the art. U-net has reached the smallest error rate. We suggest a segmentation refinement based on our previous work to further improve the performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Fully convolutional architecture vs sliding-window CNN for corneal endothelium cell segmentation

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Recently, several studies have proposed supervised approaches to accurately detect the endothelial cell contours in images captured using specular microscopy. For instance, Katafuchi and Yoshimura [17] proposed a new segmentation algorithm based on Convolutional Neural Network (CNN) to detect the cell contours regardless to the scale of cells. Fabijanska [18] developed an efficient algorithm to address the problem of corneal endothelium image segmentation using Feed-Forward Neural Network (F-FNN), trained to recognize pixels whether they belong to the cell borders or not.…”

Section: Discussionmentioning

confidence: 99%

“…The proposed CEAS system is a fully-automated system which requires no user intervention to accurately detect the cell contours. Unlike, other supervised segmentation approaches [17] [18], which require a long time for training the neural network to detect the cell contours, no training procedure is required using the proposed CEAS system. It also enables the quantification of the additional morphometric features (e.g.…”

Section: The Proposed Methodologymentioning

confidence: 99%

A fully automated cell segmentation and morphometric parameter system for quantifying corneal endothelial cell morphology

Al-Fahdawi

Qahwaji

Al-Waisy

et al. 2018

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

show abstract

“…The input image resolution was set to 64×64, which size was motivated by previous research concerning this problem conducted in [33]. The network was trained through 20 epochs with the learning rate set to 0.01 and mini-batch capacity of 64.…”

Section: Cnn For Two-class Problemmentioning

confidence: 99%

“…Next, [32] developed another network which classified whether a pixel belongs to the cell body or a vertical, horizontal, or oblique boundary. [33] suggested very similar approach but used a convolutional neural network. Finally, [34] trained a feedforward network with statistical information about pixels, in order to classify whether they represent the border or cell body.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning as a Tool for Automatic Segmentation of Corneal Endothelium Images

Nurzynska

2018

Symmetry

View full text Add to dashboard Cite

Abstract:The automatic analysis of the state of the corneal endothelium is of much interest in ophthalmology. Up till now, several manual and semi-automatic methods have been introduced, but the need of fully-automatic segmentation of cells in the endothelium is still in search. This work addresses the problem of automatic delineation of cells in the corneal endothelium images and suggests to use the convolutional neural network (CNN) to classify between cell center, cell body, and cell border in order to achieve precise segmentation. Additionally, a method to automatically select and split merged cells is given. In order to skeletonize the result, the best-fit method is used. The achieved outcomes are compared to manual annotations in order to define the mutual overlapping. The Dice index, Jaccard coefficient, modified Hausdorff distance, and several other metrics for mosaic overlapping are used. As a final check-up, the visual inspection is shown. The performed experiments revealed the best architecture for CNN. The correctness and precision of the segmentation were evaluated on Endothelial Cell "Alizarine" dataset. According to the Dice index and Jaccard coefficient, the automatically achieved cell delineation overlaps the original one with 93% precision. While modified Hausdorff distance shows 0.14 pixel distance, proving very high accuracy. These findings are confirmed by other metrics and also supported by presented visual inspection of achieved segmentations. To conclude, the methodology to achieve fully-automatic delineation of cell boundaries in the corneal endothelium images was presented. The segmentation obtained as a result of pixel classification with CNN proved very high precision.

show abstract

Convolution neural network for contour extraction of corneal endothelial cells

Cited by 5 publications

References 2 publications

Fully convolutional architecture vs sliding-window CNN for corneal endothelium cell segmentation

Fully convolutional architecture vs sliding-window CNN for corneal endothelium cell segmentation

A fully automated cell segmentation and morphometric parameter system for quantifying corneal endothelial cell morphology

Deep Learning as a Tool for Automatic Segmentation of Corneal Endothelium Images

Contact Info

Product

Resources

About