Machine learning for segmenting cells in corneal endothelium images

Potential applications of artificial intelligence in image analysis in cornea diseases: a review

Artificial intelligence (AI) is an emerging field which could make an intelligent healthcare model a reality and has been garnering traction in the field of medicine, with promising results. There have been recent developments in machine learning and/or deep learning algorithms for applications in ophthalmology-primarily for diabetic retinopathy, and age-related macular degeneration. However, AI research in the field of cornea diseases is relatively new. Algorithms have been described to assist clinicians in diagnosis or detection of cornea conditions such as keratoconus, infectious keratitis and dry eye disease. AI may also be used for segmentation and analysis of cornea imaging or tomography as an adjunctive tool. Despite the potential advantages that these new technologies offer, there are challenges that need to be addressed before they can be integrated into clinical practice. In this review, we aim to summarize current literature and provide an update regarding recent advances in AI technologies pertaining to corneal diseases, and its potential future application, in particular pertaining to image analysis.

Unbiased image segmentation assessment toolkit for quantitative differentiation of state-of-the-art algorithms and pipelines

BACKGROUND

Image segmentation pipelines are commonly used in microscopy to identify cellular compartments like nucleus and cytoplasm, but there are few standards for comparing segmentation accuracy across pipelines. The process of selecting a segmentation assessment pipeline can seem daunting to researchers due to the number and variety of metrics available for evaluating segmentation quality.

RESULTS

Here we present automated pipelines to obtain a comprehensive set of 69 metrics to evaluate segmented data and propose a selection methodology for models based on quantitative analysis, dimension reduction or unsupervised classification techniques and informed selection criteria.

CONCLUSION

We show that the metrics used here can often be reduced to a small number of metrics that give a more complete understanding of segmentation accuracy, with different groups of metrics providing sensitivity to different types of segmentation error. These tools are delivered as easy to use python libraries, command line tools, Common Workflow Language Tools, and as Web Image Processing Pipeline interactive plugins to ensure a wide range of users can access and use them. We also present how our evaluation methods can be used to observe the changes in segmentations across modern machine learning/deep learning workflows and use cases.

Artificial intelligence in cornea and ocular surface diseases

In modern ophthalmology, the advent of artificial intelligence (AI) is gradually showing promising results. The application of complex algorithms to machine and deep learning has the potential to improve the diagnosis of various corneal and ocular surface diseases, customize the treatment, and enhance patient outcomes. Moreover, the use of AI can ameliorate the efficiency of the health-care system by providing more accurate results, reducing the workload of ophthalmologists, allowing the analysis of a big amount of data, and reducing the time and resources required for manual image acquisition and analysis. In this article, we reviewed the most important and recently published applications of AI in the field of cornea and ocular surface diseases, with a particular focus on keratoconus, infectious keratitis, corneal transplants, and the use of in vivo confocal microscopy.

DenseUNets with feedback non-local attention for the segmentation of specular microscopy images of the corneal endothelium with guttae

Corneal guttae, which are the abnormal growth of extracellular matrix in the corneal endothelium, are observed in specular images as black droplets that occlude the endothelial cells. To estimate the corneal parameters (endothelial cell density [ECD], coefficient of variation [CV], and hexagonality [HEX]), we propose a new deep learning method that includes a novel attention mechanism (named fNLA), which helps to infer the cell edges in the occluded areas. The approach first derives the cell edges, then infers the well-detected cells, and finally employs a postprocessing method to fix mistakes. This results in a binary segmentation from which the corneal parameters are estimated. We analyzed 1203 images (500 contained guttae) obtained with a Topcon SP-1P microscope. To generate the ground truth, we performed manual segmentation in all images. Several networks were evaluated (UNet, ResUNeXt, DenseUNets, UNet++, etc.) and we found that DenseUNets with fNLA provided the lowest error: a mean absolute error of 23.16 [cells/mm[Formula: see text]] in ECD, 1.28 [%] in CV, and 3.13 [%] in HEX. Compared with Topcon's built-in software, our error was 3-6 times smaller. Overall, our approach handled notably well the cells affected by guttae, detecting cell edges partially occluded by small guttae and discarding large areas covered by extensive guttae.

Overestimation of corneal endothelial cell density by automated method in glaucomatous eyes with impaired corneal endothelial cells

PURPOSE

To determine between-method differences in corneal endothelial cell parameters using center and automated methods of non-contact specular microscopy (CellCheck software of Konan, Inc.) in glaucomatous eyes.

METHODS

We analyzed the central corneal endothelial cell density (ECD) of 245 glaucomatous eyes using center (ECD-Ce) and automated methods (ECD-Au). Based on the ECD-Ce, we allocated subjects to Groups 1 to 10 (at 250 cells/mm2 intervals) and evaluated the ECD, coefficient of variation in cell area (CV), and percentage of hexagonal cells (HEX).

RESULTS

There was a close correlation (r = 0.91) between the ECD values measured using both methods. However, ECD-Au were significantly higher than those measured by the center method when ECD-Ce was less than 2500 (in Groups 1 to 8; P < 0.001 to P = 0.006). The regression equation of (ECD-Au-ECD-Ce) = 1028-0.397*ECD-Ce shows greater deviation in eyes with lower ECD, and this difference became 0 when ECD -Ce was 2593 cells/mm2. None of the 44 subjects with an ECD-Ce of < 1000 cells/mm2 recorded an ECD-Au < 1000 cells/mm2. Compared with the center method, the automated method had higher and lower median CV and HEX values, respectively (P < 0.001). The between-method differences in both CV and HEX were negatively correlated with ECD-Ce (r = -0.49, P < 0.001 and r = -0.25, P < 0.001, respectively).

CONCLUSION

The automated method of the CellCheck software overestimates ECD in eyes with lower ECD values and may overlook risk of corneal decompensation.

Segmentation of wood cell in cross-section using deep convolutional neural networks

Fiber and vessel structures located in the cross-section are anatomical features that play an important role in identifying tree species. In order to determine the microscopic anatomical structure of these cell types, each cell must be accurately segmented. In this study, a segmentation method is proposed for wood cell images based on deep convolutional neural networks. The network, which was developed by combining two-stage CNN structures, was trained using the Adam optimization algorithm. For evaluation, the method was compared with SegNet and U-Net architectures, trained with the same dataset. The losses in these models trained were compared using IoU (Intersection over Union), accuracy, and BF-score measurements on the test data. The automatic identification of the cells in the wood images obtained using a microscope will provide a fast, inexpensive, and reliable tool for those working in this field.

An automatic approach for cell detection and segmentation of corneal endothelium in specular microscope

PURPOSE

Specular microscopy is an indispensable tool for clinicians seeking to monitor the corneal endothelium. Automated methods of determining endothelial cell density (ECD) are limited in their ability to analyze images of poor quality. We describe and assess an image processing algorithm to analyze corneal endothelial images.

METHODS

A set of corneal endothelial images acquired with a Konan CellChek specular microscope was analyzed using three methods: flex-center, Konan Auto Tracer, and the proposed method. In this technique, the algorithm determines the region of interest, filters the image to differentiate cell boundaries from their interiors, and utilizes stochastic watershed segmentation to draw cell boundaries and assess ECD based on the masked region. We compared ECD measured by the algorithm with manual and automated results from the specular microscope.

RESULTS

We analyzed a total of 303 images manually, using the Auto Tracer, and with the proposed image processing method. Relative to manual analysis across all images, the mean error was 0.04% in the proposed method (p = 0.23 for difference) whereas Auto Tracer demonstrated a bias towards overestimation, with a mean error of 5.7% (p = 2.06× 10^-8). The relative mean absolute errors were 6.9% and 7.9%, respectively, for the proposed and Auto Tracer. The average time for analysis of each image using the proposed method was 2.5 s.

CONCLUSION

We demonstrate a computationally efficient algorithm to analyze corneal endothelial cell density that can be implemented on devices for clinical and research use.

Automated Image Segmentation of the Corneal Endothelium in Patients With Fuchs Dystrophy

Purpose

To perform segmentation of specular microscopy (SM) images of the corneal endothelium for comparing average perimeter length (APL) between Fuchs endothelial corneal dystrophy (FECD) patients and healthy subjects.

Methods

A retrospective review of clinical records of FECD patients and those with healthy endothelium was carried out to collect images of the endothelium. The images were segmented by modified U-Net, a deep learning architecture, followed by the Watershed algorithm to resolve merged cell borders (<5%). The segmented images were analyzed for endothelial cell density (ECDUW) and APL.

Results

The combination of the U-Net and Watershed algorithm, referred to as the UW approach, enabled a complete segmentation of the endothelium. In healthy, ECDUW was close to estimates by SM and manual segmentation (31 subjects; P > 0.1). However, in FECD, ECDUW was closer to estimates by manual segmentation but not by SM (27 patients; P < 0.001). ECDUW in FECD (2547 ± 499 cells/mm2; 60 patients) was smaller compared to that in the healthy (2713 ± 401 cells/mm2; 70 subjects) (P < 0.001). APL in the healthy was 66.87 ± 7.68 µm/cell (70 subjects), but it increased with %Guttae in FECD (56.60-195.30 µm/cell; 60 patients) (P < 0.0001).

Conclusions

The UW approach is precise for the segmentation of SM images from the healthy and FECD. Our analysis has revealed that APL increases with %Guttae.

Translational Relevance

The average perimeter length of the corneal endothelium, which represents the length of the paracellular pathway for fluid flux into the stroma, is increased in Fuchs dystrophy.

Digital Image Processing and Development of Machine Learning Models for the Discrimination of Corneal Pathology: An Experimental Model

Machine learning (ML) has an impressive capacity to learn and analyze a large volume of data. This study aimed to train different algorithms to discriminate between healthy and pathologic corneal images by evaluating digitally processed spectral-domain optical coherence tomography (SD-OCT) corneal images. A set of 22 SD-OCT images belonging to a random set of corneal pathologies was compared to 71 healthy corneas (control group). A binary classification method was applied where three approaches of ML were explored. Once all images were analyzed, representative areas from every digital image were also extracted, processed and analyzed for a statistical feature comparison between healthy and pathologic corneas. The best performance was obtained from transfer learning—support vector machine (TL-SVM) (AUC = 0.94, SPE 88%, SEN 100%) and transfer learning—random forest (TL- RF) method (AUC = 0.92, SPE 84%, SEN 100%), followed by convolutional neural network (CNN) (AUC = 0.84, SPE 77%, SEN 91%) and random forest (AUC = 0.77, SPE 60%, SEN 95%). The highest diagnostic accuracy in classifying corneal images was achieved with the TL-SVM and the TL-RF models. In image classification, CNN was a strong predictor. This pilot experimental study developed a systematic mechanized system to discern pathologic from healthy corneas using a small sample.

Advances in Imaging Technology of Anterior Segment of the Eye

Advances in imaging technology and computer science have allowed the development of newer assessment of the anterior segment, including Corvis ST, Brillouin microscopy, ultrahigh-resolution optical coherence tomography, and artificial intelligence. They enable accurate and precise assessment of structural and biomechanical alterations associated with anterior segment disorders. This review will focus on these 4 new techniques, and a brief overview of these modalities will be introduced. The authors will also discuss the recent advances in research regarding these techniques and potential application of these techniques in clinical practice. Many studies on these modalities have reported promising results, indicating the potential for more detailed comprehensive understanding of the anterior segment tissues.

Deep Learning for Assessing the Corneal Endothelium from Specular Microscopy Images up to 1 Year after Ultrathin-DSAEK Surgery

Purpose

To present a fully automatic method to estimate the corneal endothelium parameters from specular microscopy images and to use it to study a one-year follow-up after ultrathin Descemet stripping automated endothelial keratoplasty.

Methods

We analyzed 383 post ultrathin Descemet stripping automated endothelial keratoplasty images from 41 eyes acquired with a Topcon SP-1P specular microscope at 1, 3, 6, and 12 months after surgery. The estimated parameters were endothelial cell density (ECD), coefficient of variation (CV), and hexagonality (HEX). Manual segmentation was performed in all images.

Results

Our method provided an estimate for ECD, CV, and HEX in 98.4% of the images, whereas Topcon's software had a success rate of 71.5% for ECD/CV and 30.5% for HEX. For the images with estimates, the percentage error in our method was 2.5% for ECD, 5.7% for CV, and 5.7% for HEX, whereas Topcon's software provided an error of 7.5% for ECD, 17.5% for CV, and 18.3% for HEX. Our method was significantly better than Topcon's (P < 0.0001) and was not statistically significantly different from the manual assessments (P > 0.05). At month 12, the subjects presented an average ECD = 1377 ± 483 [cells/mm2], CV = 26.1 ± 5.7 [%], and HEX = 58.1 ± 7.1 [%].

Conclusions

The proposed method obtains reliable and accurate estimations even in challenging specular images of pathologic corneas.

Translational Relevance

CV and HEX, not currently used in the clinic owing to a lack of reliability in automatic methods, are useful biomarkers to analyze the postoperative healing process. Our accurate estimations allow now for their clinical use.