Mark Christopher

Validation of tablet-based evaluation of color fundus images

Purpose: To compare diabetic retinopathy (DR) referral recommendations made by viewing fundus images using a tablet computer with those made using a standard desktop display. Methods: A tablet computer (iPad) and a desktop computer with a high-definition color display were compared. For each platform, 2 retinal specialists independently rated 1,200 color fundus images from patients at risk for DR using an annotation program Truthseeker. The specialists determined whether each image had referable DR and also how urgently each patient should be referred for medical examination. Graders viewed and rated the randomly presented images independently and were masked to their ratings on the alternative platform. Tablet-based and desktop display–based referral ratings were compared using cross-platform intraobserver kappa as the primary outcome measure. Additionally, interobserver kappa, sensitivity, specificity, and area under the receiver operating characteristic were determined. Results: A high level of cross-platform intraobserver agreement was found for the DR referral ratings between the platforms (&kgr; = 0.778) and for the 2 graders (&kgr; = 0.812). Interobserver agreement was similar for the 2 platforms (&kgr; = 0.544 and &kgr; = 0.625 for tablet and desktop, respectively). The tablet-based ratings achieved a sensitivity of 0.848, a specificity of 0.987, and an area under the receiver operating characteristic of 0.950 compared with desktop display-based ratings. Conclusion: In this pilot study, tablet-based rating of color fundus images for subjects at risk for DR was consistent with desktop display–based rating. These results indicate that tablet computers can be reliably used for clinical evaluation of fundus images for DR.

Automated Axon Counting in Rodent Optic Nerve Sections with AxonJ

We have developed a publicly available tool, AxonJ, which quantifies the axons in optic nerve sections of rodents stained with paraphenylenediamine (PPD). In this study, we compare AxonJ’s performance to human experts on 100x and 40x images of optic nerve sections obtained from multiple strains of mice, including mice with defects relevant to glaucoma. AxonJ produced reliable axon counts with high sensitivity of 0.959 and high precision of 0.907, high repeatability of 0.95 when compared to a gold-standard of manual assessments and high correlation of 0.882 to the glaucoma damage staging of a previously published dataset. AxonJ allows analyses that are quantitative, consistent, fully-automated, parameter-free, and rapid on whole optic nerve sections at 40x. As a freely available ImageJ plugin that requires no highly specialized equipment to utilize, AxonJ represents a powerful new community resource augmenting studies of the optic nerve using mice.

RetFM-J, an ImageJ-based module for automated counting and quantifying features of nuclei in retinal whole-mounts.

The present article introduces RetFM-J, a semi-automated ImageJ-based module that detects, counts, and collects quantitative data on nuclei of the inner retina from H&E-stained whole-mounted retinas. To illustrate performance, computer-derived outputs were analyzed in inbred C57BL/6J mice. Automated characterization yielded computer-derived outputs that closely matched manual counts. As a method using open-source software that is freely available, inexpensive staining reagents that are robust, and imaging equipment that is routine to most laboratories, RetFM-J could be utilized in a wide variety of experiments benefiting from high-throughput, quantitative, uniform analyses of total cellularity in the inner retina.

Automated discovery of structural features of the optic nerve head on the basis of image and genetic data

Evaluation of optic nerve head (ONH) structure is a commonly used clinical technique for both diagnosis and monitoring of glaucoma. Glaucoma is associated with characteristic changes in the structure of the ONH. We present a method for computationally identifying ONH structural features using both imaging and genetic data from a large cohort of participants at risk for primary open angle glaucoma (POAG). Using 1054 participants from the Ocular Hypertension Treatment Study, ONH structure was measured by application of a stereo correspondence algorithm to stereo fundus images. In addition, the genotypes of several known POAG genetic risk factors were considered for each participant. ONH structural features were discovered using both a principal component analysis approach to identify the major modes of variance within structural measurements and a linear discriminant analysis approach to capture the relationship between genetic risk factors and ONH structure. The identified ONH structural features were evaluated based on the strength of their associations with genotype and development of POAG by the end of the OHTS study. ONH structural features with strong associations with genotype were identified for each of the genetic loci considered. Several identified ONH structural features were significantly associated (p < 0.05) with the development of POAG after Bonferroni correction. Further, incorporation of genetic risk status was found to substantially increase performance of early POAG prediction. These results suggest incorporating both imaging and genetic data into ONH structural modeling significantly improves the ability to explain POAG-related changes to ONH structure.

Changes in quantitative 3D shape features of the optic nerve head associated with age

Optic nerve head (ONH) structure is an important biological feature of the eye used by clinicians to diagnose and monitor progression of diseases such as glaucoma. ONH structure is commonly examined using stereo fundus imaging or optical coherence tomography. Stereo fundus imaging provides stereo views of the ONH that retain 3D information useful for characterizing structure. In order to quantify 3D ONH structure, we applied a stereo correspondence algorithm to a set of stereo fundus images. Using these quantitative 3D ONH structure measurements, eigen structures were derived using principal component analysis from stereo images of 565 subjects from the Ocular Hypertension Treatment Study (OHTS). To evaluate the usefulness of the eigen structures, we explored associations with the demographic variables age, gender, and race. Using regression analysis, the eigen structures were found to have significant (p < 0.05) associations with both age and race after Bonferroni correction. In addition, classifiers were constructed to predict the demographic variables based solely on the eigen structures. These classifiers achieved an area under receiver operating characteristic curve of 0.62 in predicting a binary age variable, 0.52 in predicting gender, and 0.67 in predicting race. The use of objective, quantitative features or eigen structures can reveal hidden relationships between ONH structure and demographics. The use of these features could similarly allow specific aspects of ONH structure to be isolated and associated with the diagnosis of glaucoma, disease progression and outcomes, and genetic factors.

Retinal Nerve Fiber Layer Features Identified by Unsupervised Machine Learning on Optical Coherence Tomography Scans Predict Glaucoma Progression

Purpose To apply computational techniques to wide-angle swept-source optical coherence tomography (SS-OCT) images to identify novel, glaucoma-related structural features and improve detection of glaucoma and prediction of future glaucomatous progression. Methods Wide-angle SS-OCT, OCT circumpapillary retinal nerve fiber layer (cpRNFL) circle scans spectral-domain (SD)-OCT, standard automated perimetry (SAP), and frequency doubling technology (FDT) visual field tests were completed every 3 months for 2 years from a cohort of 28 healthy participants (56 eyes) and 93 glaucoma participants (179 eyes). RNFL thickness maps were extracted from segmented SS-OCT images and an unsupervised machine learning approach based on principal component analysis (PCA) was used to identify novel structural features. Area under the receiver operating characteristic curve (AUC) was used to assess diagnostic accuracy of RNFL PCA for detecting glaucoma and progression compared to SAP, FDT, and cpRNFL measures. Results The RNFL PCA features were significantly associated with mean deviation (MD) in both SAP (R2 = 0.49, P < 0.0001) and FDT visual field testing (R2 = 0.48, P < 0.0001), and with mean circumpapillary RNFL thickness (cpRNFLt) from SD-OCT (R2 = 0.58, P < 0.0001). The identified features outperformed each of these measures in detecting glaucoma with an AUC of 0.95 for RNFL PCA compared to an 0.90 for mean cpRNFLt (P = 0.09), 0.86 for SAP MD (P = 0.034), and 0.83 for FDT MD (P = 0.021). Accuracy in predicting progression was also significantly higher for RNFL PCA compared to SAP MD, FDT MD, and mean cpRNFLt (P = 0.046, P = 0.007, and P = 0.044, respectively). Conclusions A computational approach can identify structural features that improve glaucoma detection and progression prediction.

Stereo photo measured ONH shape predicts development of POAG in subjects with ocular hypertension

PURPOSE To identify objective, quantitative optic nerve head (ONH) structural features and model the contributions of glaucoma. METHODS Baseline stereoscopic optic disc images of 1635 glaucoma-free participants at risk for developing primary open-angle glaucoma (POAG) were collected as part of the Ocular Hypertension Treatment Study. A stereo correspondence algorithm designed for fundus images was applied to extract the three-dimensional (3D) information about the ONH. Principal component analysis was used to identify ONH 3D structural features and the contributions of demographic features, clinical variables, and disease were modeled using linear regression and linear component analysis. The computationally identified features were evaluated based on associations with glaucoma and ability to predict which participants would develop POAG. RESULTS The computationally identified features were significantly associated with future POAG, POAG-related demographics (age, ethnicity), and clinical measurements (horizontal and vertical cup-to-disc ratio, central corneal thickness, and refraction). Models predicting future POAG development using the OHTS baseline data and STEP features achieved an AUC of 0.722 in cross-validation testing. This was a significant improvement over using only demographics (age, sex, and ethnicity), which had an AUC of 0.599. CONCLUSIONS Methods for identifying objective, quantitative measurements of 3D ONH structure were developed using a large dataset. The identified features were significantly associated with POAG and POAG-related variables. Further, these features increased predictive model accuracy in predicting future POAG. The results indicate that the computationally identified features might be useful in POAG early screening programs or as endophenotypes to investigate POAG genetics.

Selection of Phototransduction Genes in Homo sapiens

PURPOSE We investigated the evidence of recent positive selection in the human phototransduction system at single nucleotide polymorphism (SNP) and gene level. METHODS SNP genotyping data from the International HapMap Project for European, Eastern Asian, and African populations was used to discover differences in haplotype length and allele frequency between these populations. Numeric selection metrics were computed for each SNP and aggregated into gene-level metrics to measure evidence of recent positive selection. The level of recent positive selection in phototransduction genes was evaluated and compared to a set of genes shown previously to be under recent selection, and a set of highly conserved genes as positive and negative controls, respectively. RESULTS Six of 20 phototransduction genes evaluated had gene-level selection metrics above the 90th percentile: RGS9, GNB1, RHO, PDE6G, GNAT1, and SLC24A1. The selection signal across these genes was found to be of similar magnitude to the positive control genes and much greater than the negative control genes. CONCLUSIONS There is evidence for selective pressure in the genes involved in retinal phototransduction, and traces of this selective pressure can be demonstrated using SNP-level and gene-level metrics of allelic variation. We hypothesize that the selective pressure on these genes was related to their role in low light vision and retinal adaptation to ambient light changes. Uncovering the underlying genetics of evolutionary adaptations in phototransduction not only allows greater understanding of vision and visual diseases, but also the development of patient-specific diagnostic and intervention strategies.

Corrigendum: Automated Axon Counting in Rodent Optic Nerve Sections with AxonJ

Scientific Reports 6: Article number: 26559; published online: 26 May 2016; updated: 19 October 2016 In the Supplementary Information file originally published with this Article, Supplemental Figure 1 was omitted. In addition, “Supplemental Software” was incorrectly given as “Software Legend” These errors have now been corrected in the Supplementary Information that now accompanies the Article.

Optimal filter approach for the detection of vessel bifurcations in color fundus images

Bifurcations of retinal vessels in fundus images are important structures clinically and their detection is also an important component in image processing algorithms such as registration, segmentation and change detection. In this paper, we develop a method for direct bifurcation detection based on the optimal filter framework. This approach first generates a set of filters to represent all cases of bifurcations, and then uses them to generate a feature space for a classifier to distinguish bifurcations and non-bifurcations. This approach is different from previous methods as it uses a minimal number of assumptions, essentially only requiring training images and expert annotations of bifurcations. The method is trained on 60 fundus images and tested on 20 fundus images, resulting in an AUC of 0.883, which compares well to a human expert.