Automated segmentation of the optic disc from stereo color photographs using physiologically plausible features

Modeling complex age-related eye disease

Modeling complex eye diseases like age-related macular degeneration (AMD) and glaucoma poses significant challenges, since these conditions depend highly on age-related changes that occur over several decades, with many contributing factors remaining unknown. Although both diseases exhibit a relatively high heritability of >50%, a large proportion of individuals carrying AMD- or glaucoma-associated genetic risk variants will never develop these diseases. Furthermore, several environmental and lifestyle factors contribute to and modulate the pathogenesis and progression of AMD and glaucoma. Several strategies replicate the impact of genetic risk variants, pathobiological pathways and environmental and lifestyle factors in AMD and glaucoma in mice and other species. In this review we will primarily discuss the most commonly available mouse models, which have and will likely continue to improve our understanding of the pathobiology of age-related eye diseases. Uncertainties persist whether small animal models can truly recapitulate disease progression and vision loss in patients, raising doubts regarding their usefulness when testing novel gene or drug therapies. We will elaborate on concerns that relate to shorter lifespan, body size and allometries, lack of macula and a true lamina cribrosa, as well as absence and sequence disparities of certain genes and differences in their chromosomal location in mice. Since biological, rather than chronological, age likely predisposes an organism for both glaucoma and AMD, more rapidly aging organisms like small rodents may open up possibilities that will make research of these diseases more timely and financially feasible. On the other hand, due to the above-mentioned anatomical and physiological features, as well as pharmacokinetic and -dynamic differences small animal models are not ideal to study the natural progression of vision loss or the efficacy and safety of novel therapies. In this context, we will also discuss the advantages and pitfalls of alternative models that include larger species, such as non-human primates and rabbits, patient-derived retinal organoids, and human organ donor eyes.

TUNet and domain adaptation based learning for joint optic disc and cup segmentation

Glaucoma is a chronic disorder that harms the optic nerves and causes irreversible blindness. The calculation of optic cup (OC) to optic disc (OD) ratio plays an important role in the primary screening and diagnosis of glaucoma. Thus, automatic and precise segmentations of OD and OC is highly preferable. Recently, deep neural networks demonstrate remarkable progress in the OD and OC segmentation, however, they are severely hindered in generalizing across different scanners and image resolution. In this work, we propose a novel domain adaptation-based framework to mitigate the performance degradation in OD and OC segmentation. We first devise an effective transformer-based segmentation network as a backbone to accurately segment the OD and OC regions. Then, to address the issue of domain shift, we introduce domain adaptation into the learning paradigm to encourage domain-invariant features. Since the segmentation-based domain adaptation loss is insufficient for capturing segmentation details, we further propose an auxiliary classifier to enable the discrimination on segmentation details. Exhaustive experiments on three public retinal fundus image datasets, i.e., REFUGE, Drishti-GS and RIM-ONE-r3, demonstrate our superior performance on the segmentation of OD and OC. These results suggest that our proposal has great potential to be an important component for an automated glaucoma screening system.

FSOU-Net: Feature supplement and optimization U-Net for 2D medical image segmentation

BACKGROUND

The results of medical image segmentation can provide reliable evidence for clinical diagnosis and treatment. The U-Net proposed previously has been widely used in the field of medical image segmentation. Its encoder extracts semantic features of different scales at different stages, but does not carry out special processing for semantic features of each scale.

OBJECTIVE

To improve the feature expression ability and segmentation performance of U-Net, we proposed a feature supplement and optimization U-Net (FSOU-Net).

METHODS

First, we put forward the view that semantic features of different scales should be treated differently. Based on this view, we classify the semantic features automatically extracted by encoders into two categories: shallow semantic features and deep semantic features. Then, we propose the shallow feature supplement module (SFSM), which obtains fine-grained semantic features through up-sampling to supplement the shallow semantic information. Finally, we propose the deep feature optimization module (DFOM), which uses the expansive convolution of different receptive fields to obtain multi-scale features and then performs multi-scale feature fusion to optimize the deep semantic information.

RESULTS

The proposed model is experimented on three medical image segmentation public datasets, and the experimental results prove the correctness of the proposed idea. The segmentation performance of the model is higher than the advanced models for medical image segmentation. Compared with baseline network U-NET, the main index of Dice index is 0.75% higher on the RITE dataset, 2.3% higher on the Kvasir-SEG dataset, and 0.24% higher on the GlaS dataset.

CONCLUSIONS

The proposed method can greatly improve the feature representation ability and segmentation performance of the model.

RSAP-Net: joint optic disc and cup segmentation with a residual spatial attention path module and MSRCR-PT pre-processing algorithm

BACKGROUND

Glaucoma can cause irreversible blindness to people's eyesight. Since there are no symptoms in its early stage, it is particularly important to accurately segment the optic disc (OD) and optic cup (OC) from fundus medical images for the screening and prevention of glaucoma. In recent years, the mainstream method of OD and OC segmentation is convolution neural network (CNN). However, most existing CNN methods segment OD and OC separately and ignore the a priori information that OC is always contained inside the OD region, which makes the segmentation accuracy of most methods not high enough.

METHODS

This paper proposes a new encoder-decoder segmentation structure, called RSAP-Net, for joint segmentation of OD and OC. We first designed an efficient U-shaped segmentation network as the backbone. Considering the spatial overlap relationship between OD and OC, a new Residual spatial attention path is proposed to connect the encoder-decoder to retain more characteristic information. In order to further improve the segmentation performance, a pre-processing method called MSRCR-PT (Multi-Scale Retinex Colour Recovery and Polar Transformation) has been devised. It incorporates a multi-scale Retinex colour recovery algorithm and a polar coordinate transformation, which can help RSAP-Net to produce more refined boundaries of the optic disc and the optic cup.

RESULTS

The experimental results show that our method achieves excellent segmentation performance on the Drishti-GS1 standard dataset. In the OD and OC segmentation effects, the F1 scores are 0.9752 and 0.9012, respectively. The BLE are 6.33 pixels and 11.97 pixels, respectively.

CONCLUSIONS

This paper presents a new framework for the joint segmentation of optic discs and optic cups, called RSAP-Net. The framework mainly consists of a U-shaped segmentation skeleton and a residual space attention path module. The design of a pre-processing method called MSRCR-PT for the OD/OC segmentation task can improve segmentation performance. The method was evaluated on the publicly available Drishti-GS1 standard dataset and proved to be effective.

Classification of Glaucoma Stages Using Image Empirical Mode Decomposition from Fundus Images

One of the most prevalent causes of visual loss and blindness is glaucoma. Conventionally, instrument-based tools are employed for glaucoma screening. However, they are inefficient, time-consuming, and manual. Hence, computerized methodologies are needed for fast and accurate diagnosis of glaucoma. Therefore, we proposed a Computer-Aided Diagnosis (CAD) method for the classification of glaucoma stages using Image Empirical Mode decomposition (IEMD). In this study, IEMD is applied to decompose the preprocessed fundus photographs into different Intrinsic Mode Functions (IMFs) to capture the pixel variations. Then, the significant texture-based descriptors have been computed from the IMFs. A dimensionality reduction approach called Principal Component Analysis (PCA) has been employed to pick the robust descriptors from the retrieved feature set. We used the Analysis of Variance (ANOVA) test for feature ranking. Finally, the LS-SVM classifier has been employed to classify glaucoma stages. The proposed CAD system achieved a classification accuracy of 94.45% for the binary classification on the RIM-ONE r12 database. Our approach demonstrated better glaucoma classification performance than the existing automated systems.

Which Color Channel Is Better for Diagnosing Retinal Diseases Automatically in Color Fundus Photographs?

Color fundus photographs are the most common type of image used for automatic diagnosis of retinal diseases and abnormalities. As all color photographs, these images contain information about three primary colors, i.e., red, green, and blue, in three separate color channels. This work aims to understand the impact of each channel in the automatic diagnosis of retinal diseases and abnormalities. To this end, the existing works are surveyed extensively to explore which color channel is used most commonly for automatically detecting four leading causes of blindness and one retinal abnormality along with segmenting three retinal landmarks. From this survey, it is clear that all channels together are typically used for neural network-based systems, whereas for non-neural network-based systems, the green channel is most commonly used. However, from the previous works, no conclusion can be drawn regarding the importance of the different channels. Therefore, systematic experiments are conducted to analyse this. A well-known U-shaped deep neural network (U-Net) is used to investigate which color channel is best for segmenting one retinal abnormality and three retinal landmarks.

ECSD-Net: A joint optic disc and cup segmentation and glaucoma classification network based on unsupervised domain adaptation

BACKGROUND AND OBJECTIVES

Glaucoma can cause irreversible vision loss and even blindness, and early diagnosis can help prevent vision loss. Analyzing the optic disc and optic cup helps diagnose glaucoma, which motivates many computer-aided diagnosis methods based on deep learning networks. However, the performance of the trained model on new datasets is seriously hindered due to the distribution gap between different datasets. Therefore, we aim to develop an unsupervised learning method to solve this problem and improve the prediction performance of the model on new datasets.

METHODS

In this paper, we propose a novel unsupervised model based on adversarial learning to perform the optic disc and cup segmentation and glaucoma screening tasks in a more generalized and efficient manner. We adopt an efficient segmentation and classification network and employ unsupervised domain adaptation technology on the output space of the segmentation network to solve the domain shift problem. We conduct glaucoma screening task by combining classification and segmentation networks to obtain more stable and efficient glaucoma screening prediction.

RESULTS

We verify the effectiveness and efficiency of our proposed method on three public datasets, the REFUGE, DRISHTI-GS and RIM-ONE-r3 datasets. The experimental results demonstrate that the proposed method can effectively alleviate the deterioration of segmentation performance caused by domain shift and improve the accuracy of glaucoma screening. Furthermore, the proposed method outperforms state-of-the-art unsupervised optic disc and cup segmentation domain adaptation methods.

CONCLUSIONS

The proposed method can assist clinicians in screening and diagnosis of glaucoma and is suitable for real-world applications.

A Precise Method to Evaluate 360 Degree Measures of Optic Cup and Disc Morphology in an African American Cohort and Its Genetic Applications

(1) Background: Vertical cup-to-disc ratio (CDR) is an important measure for evaluating damage to the optic nerve head (ONH) in glaucoma patients. However, this measure often does not fully capture the irregular cupping observed in glaucomatous nerves. We developed and evaluated a method to measure cup-to-disc ratio (CDR) at all 360 degrees of the ONH. (2) Methods: Non-physician graders from the Scheie Reading Center outlined the cup and disc on digital stereo color disc images from African American patients enrolled in the Primary Open-Angle African American Glaucoma Genetics (POAAGG) study. After converting the resultant coordinates into polar representation, the CDR at each 360-degree location of the ONH was obtained. We compared grader VCDR values with clinical VCDR values, using Spearman correlation analysis, and validated significant genetic associations with clinical VCDR, using grader VCDR values. (3) Results: Graders delineated outlines of the cup contour and disc boundaries twice in each of 1815 stereo disc images. For both cases and controls, the mean CDR was highest at the horizontal bisector, particularly in the temporal region, as compared to other degree locations. There was a good correlation between grader CDR at the vertical bisector and clinical VCDR (Spearman Correlation OD: r = 0.78 [95% CI: 0.76–0.79]). An SNP in the MPDZ gene, associated with clinical VCDR in a prior genome-wide association study, showed a significant association with grader VCDR (p = 0.01) and grader CDR area ratio (p = 0.02). (4) Conclusions: The CDR of both glaucomatous and non-glaucomatous eyes varies by degree location, with the highest measurements in the temporal region of the eye. This method can be useful for capturing innate eccentric ONH morphology, tracking disease progression, and identifying genetic associations.

NENet: Nested EfficientNet and adversarial learning for joint optic disc and cup segmentation

Glaucoma is an ocular disease threatening irreversible vision loss. Primary screening of Glaucoma involves computation of optic cup (OC) to optic disc (OD) ratio that is widely accepted metric. Recent deep learning frameworks for OD and OC segmentation have shown promising results and ways to attain remarkable performance. In this paper, we present a novel segmentation network, Nested EfficientNet (NENet) that consists of EfficientNetB4 as an encoder along with a nested network of pre-activated residual blocks, atrous spatial pyramid pooling (ASPP) block and attention gates (AGs). The combination of cross-entropy and dice coefficient (DC) loss is utilized to guide the network for accurate segmentation. Further, a modified patch-based discriminator is designed for use with the NENet to improve the local segmentation details. Three publicly available datasets, REFUGE, Drishti-GS, and RIM-ONE-r3 were utilized to evaluate the performances of the proposed network. In our experiments, NENet outperformed state-of-the-art methods for segmentation of OD and OC. Additionally, we show that NENet has excellent generalizability across camera types and image resolution. The obtained results suggest that the proposed technique has potential to be an important component for an automated Glaucoma screening system.

The SEE Study: Safety, Efficacy, and Equity of Implementing Autonomous Artificial Intelligence for Diagnosing Diabetic Retinopathy in Youth

OBJECTIVE

Diabetic retinopathy (DR) is a leading cause of vision loss worldwide. Screening for DR is recommended in children and adolescents, but adherence is poor. Recently, autonomous artificial intelligence (AI) systems have been developed for early detection of DR and have been included in the American Diabetes Association's guidelines for screening in adults. We sought to determine the diagnostic efficacy of autonomous AI for the diabetic eye exam in youth with diabetes.

RESEARCH DESIGN AND METHODS

In this prospective study, point-of-care diabetic eye exam was implemented using a nonmydriatic fundus camera with an autonomous AI system for detection of DR in a multidisciplinary pediatric diabetes center. Sensitivity, specificity, and diagnosability of AI was compared with consensus grading by retinal specialists, who were masked to AI output. Adherence to screening guidelines was measured before and after AI implementation.

RESULTS

Three hundred ten youth with diabetes aged 5-21 years were included, of whom 4.2% had DR. Diagnosability of AI was 97.5% (302 of 310). The sensitivity and specificity of AI to detect more-than-mild DR was 85.7% (95% CI 42.1-99.6%) and 79.3% (74.3-83.8%), respectively, compared with the reference standard as defined by retina specialists. Adherence improved from 49% to 95% after AI implementation.

CONCLUSIONS

Use of a nonmydriatic fundus camera with autonomous AI was safe and effective for the diabetic eye exam in youth in our study. Adherence to screening guidelines improved with AI implementation. As the prevalence of diabetes increases in youth and adherence to screening guidelines remains suboptimal, effective strategies for diabetic eye exams in this population are needed.

MSU-Net: Multi-Scale U-Net for 2D Medical Image Segmentation

Aiming at the limitation of the convolution kernel with a fixed receptive field and unknown prior to optimal network width in U-Net, multi-scale U-Net (MSU-Net) is proposed by us for medical image segmentation. First, multiple convolution sequence is used to extract more semantic features from the images. Second, the convolution kernel with different receptive fields is used to make features more diverse. The problem of unknown network width is alleviated by efficient integration of convolution kernel with different receptive fields. In addition, the multi-scale block is extended to other variants of the original U-Net to verify its universality. Five different medical image segmentation datasets are used to evaluate MSU-Net. A variety of imaging modalities are included in these datasets, such as electron microscopy, dermoscope, ultrasound, etc. Intersection over Union (IoU) of MSU-Net on each dataset are 0.771, 0.867, 0.708, 0.900, and 0.702, respectively. Experimental results show that MSU-Net achieves the best performance on different datasets. Our implementation is available at https://github.com/CN-zdy/MSU_Net.

Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image Segmentation

A common shortfall of supervised deep learning for medical imaging is the lack of labeled data, which is often expensive and time consuming to collect. This article presents a new semisupervised method for medical image segmentation, where the network is optimized by a weighted combination of a common supervised loss only for the labeled inputs and a regularization loss for both the labeled and unlabeled data. To utilize the unlabeled data, our method encourages consistent predictions of the network-in-training for the same input under different perturbations. With the semisupervised segmentation tasks, we introduce a transformation-consistent strategy in the self-ensembling model to enhance the regularization effect for pixel-level predictions. To further improve the regularization effects, we extend the transformation in a more generalized form including scaling and optimize the consistency loss with a teacher model, which is an averaging of the student model weights. We extensively validated the proposed semisupervised method on three typical yet challenging medical image segmentation tasks: 1) skin lesion segmentation from dermoscopy images in the International Skin Imaging Collaboration (ISIC) 2017 data set; 2) optic disk (OD) segmentation from fundus images in the Retinal Fundus Glaucoma Challenge (REFUGE) data set; and 3) liver segmentation from volumetric CT scans in the Liver Tumor Segmentation Challenge (LiTS) data set. Compared with state-of-the-art, our method shows superior performance on the challenging 2-D/3-D medical images, demonstrating the effectiveness of our semisupervised method for medical image segmentation.

Atlas-based score for automatic glaucoma risk stratification

Glaucoma is a disease that affects the optic nerve and can lead to blindness. The cup-to-disc ratio (CDR) measurement is one of the key clinical indicators for glaucoma assessment. However, the CDR only evaluates the relative sizes of the cup and optic disc (OD) via their diameters, and does not characterize local morphological changes that can inform clinicians on early signs of glaucoma. In this work, we propose a novel glaucoma score based on a statistical atlas framework that automatically quantifies the deformations of the OD region induced by glaucoma. A deep-learning approach is first used to segment the optic cup with a dedicated atlas-based data augmentation strategy. The segmented OD region (disc, cup and vessels) is then registered to the statistical OD atlas and the deformation is projected onto the atlas eigenvectors. The atlas glaucoma score (AGS) is then obtained by a linear combination of the principal modes of deformation of the atlas with linear discriminant analysis. The AGS performs better than the CDR on the three datasets used for evaluation, including RIM-ONE and ORIGA650. Compared to the CDR measurement, which yields an area under the ROC curve (AUC) of 91.4% using the expert segmentations, the AGS achieves an AUC of 98.2%. Our novel glaucoma score captures more complex deformations within the optic disc region than the CDR can. Such morphological changes are the first cue of glaucoma onset, before the visual field is affected. The proposed approach can thus significantly improve early detection of glaucoma.

DoFE: Domain-Oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets

Deep convolutional neural networks have significantly boosted the performance of fundus image segmentation when test datasets have the same distribution as the training datasets. However, in clinical practice, medical images often exhibit variations in appearance for various reasons, e.g., different scanner vendors and image quality. These distribution discrepancies could lead the deep networks to over-fit on the training datasets and lack generalization ability on the unseen test datasets. To alleviate this issue, we present a novel Domain-oriented Feature Embedding (DoFE) framework to improve the generalization ability of CNNs on unseen target domains by exploring the knowledge from multiple source domains. Our DoFE framework dynamically enriches the image features with additional domain prior knowledge learned from multi-source domains to make the semantic features more discriminative. Specifically, we introduce a Domain Knowledge Pool to learn and memorize the prior information extracted from multi-source domains. Then the original image features are augmented with domain-oriented aggregated features, which are induced from the knowledge pool based on the similarity between the input image and multi-source domain images. We further design a novel domain code prediction branch to infer this similarity and employ an attention-guided mechanism to dynamically combine the aggregated features with the semantic features. We comprehensively evaluate our DoFE framework on two fundus image segmentation tasks, including the optic cup and disc segmentation and vessel segmentation. Our DoFE framework generates satisfying segmentation results on unseen datasets and surpasses other domain generalization and network regularization methods.

Coronary angiography video segmentation method for assisting cardiovascular disease interventional treatment

Background

Coronary heart disease is one of the diseases with the highest mortality rate. Due to the important position of cardiovascular disease prevention and diagnosis in the medical field, the segmentation of cardiovascular images has gradually become a research hotspot. How to segment accurate blood vessels from coronary angiography videos to assist doctors in making accurate analysis has become the goal of our research.

Method

Based on the U-net architecture, we use a context-based convolutional network for capturing more information of the vessel in the video. The proposed method includes three modules: the sequence encoder module, the sequence decoder module, and the sequence filter module. The high-level information of the feature is extracted in the encoder module. Multi-kernel pooling layers suitable for the extraction of blood vessels are added before the decoder module. In the filter block, we add a simple temporal filter to reducing inter-frame flickers.

Results

The performance comparison with other method shows that our work can achieve 0.8739 in Sen, 0.9895 in Acc. From the performance of the results, the accuracy of our method is significantly improved. The performance benefit from the algorithm architecture and our enlarged dataset.

Conclusion

Compared with previous methods that only focus on single image analysis, our method can obtain more coronary information through image sequences. In future work, we will extend the network to 3D networks.

Channel and Spatial Attention Regression Network for Cup-to-Disc Ratio Estimation

Cup-to-disc ratio (CDR) is of great importance during assessing structural changes at the optic nerve head (ONH) and diagnosis of glaucoma. While most efforts have been put on acquiring the CDR number through CNN-based segmentation algorithms followed by the calculation of CDR, these methods usually only focus on the features in the convolution kernel, which is, after all, the operation of the local region, ignoring the contribution of rich global features (such as distant pixels) to the current features. In this paper, a new end-to-end channel and spatial attention regression deep learning network is proposed to deduces CDR number from the regression perspective and combine the self-attention mechanism with the regression network. Our network consists of four modules: the feature extraction module to extract deep features expressing the complicated pattern of optic disc (OD) and optic cup (OC), the attention module including the channel attention block (CAB) and the spatial attention block (SAB) to improve feature representation by aggregating long-range contextual information, the regression module to deduce CDR number directly, and the segmentation-auxiliary module to focus the model’s attention on the relevant features instead of the background region. Especially, the CAB selects relatively important feature maps in channel dimension, shifting the emphasis on the OD and OC region; meanwhile, the SAB learns the discriminative ability of feature representation at pixel level by capturing the relationship of intra-feature map. The experimental results of ORIGA dataset show that our method obtains absolute CDR error of 0.067 and the Pearson’s correlation coefficient of 0.694 in estimating CDR and our method has a great potential in predicting the CDR number.

Practice Guidelines for Ocular Telehealth-Diabetic Retinopathy, Third Edition

Contributors The following document and appendices represent the third edition of the Practice Guidelines for Ocular Telehealth-Diabetic Retinopathy. These guidelines were developed by the Diabetic Retinopathy Telehealth Practice Guidelines Working Group. This working group consisted of a large number of subject matter experts in clinical applications for telehealth in ophthalmology. The editorial committee consisted of Mark B. Horton, OD, MD, who served as working group chair and Christopher J. Brady, MD, MHS, and Jerry Cavallerano, OD, PhD, who served as cochairs. The writing committees were separated into seven different categories. They are as follows: 1.Clinical/operational: Jerry Cavallerano, OD, PhD (Chair), Gail Barker, PhD, MBA, Christopher J. Brady, MD, MHS, Yao Liu, MD, MS, Siddarth Rathi, MD, MBA, Veeral Sheth, MD, MBA, Paolo Silva, MD, and Ingrid Zimmer-Galler, MD. 2.Equipment: Veeral Sheth, MD (Chair), Mark B. Horton, OD, MD, Siddarth Rathi, MD, MBA, Paolo Silva, MD, and Kristen Stebbins, MSPH. 3.Quality assurance: Mark B. Horton, OD, MD (Chair), Seema Garg, MD, PhD, Yao Liu, MD, MS, and Ingrid Zimmer-Galler, MD. 4.Glaucoma: Yao Liu, MD, MS (Chair) and Siddarth Rathi, MD, MBA. 5.Retinopathy of prematurity: Christopher J. Brady, MD, MHS (Chair) and Ingrid Zimmer-Galler, MD. 6.Age-related macular degeneration: Christopher J. Brady, MD, MHS (Chair) and Ingrid Zimmer-Galler, MD. 7.Autonomous and computer assisted detection, classification and diagnosis of diabetic retinopathy: Michael Abramoff, MD, PhD (Chair), Michael F. Chiang, MD, and Paolo Silva, MD.

CTumorGAN: a unified framework for automatic computed tomography tumor segmentation

PURPOSE

Unlike the normal organ segmentation task, automatic tumor segmentation is a more challenging task because of the existence of similar visual characteristics between tumors and their surroundings, especially on computed tomography (CT) images with severe low contrast resolution, as well as the diversity and individual characteristics of data acquisition procedures and devices. Consequently, most of the recently proposed methods have become increasingly difficult to be applied on a different tumor dataset with good results, and moreover, some tumor segmentors usually fail to generalize beyond those datasets and modalities used in their original evaluation experiments.

METHODS

In order to alleviate some of the problems with the recently proposed methods, we propose a novel unified and end-to-end adversarial learning framework for automatic segmentation of any kinds of tumors from CT scans, called CTumorGAN, consisting of a Generator network and a Discriminator network. Specifically, the Generator attempts to generate segmentation results that are close to their corresponding golden standards, while the Discriminator aims to distinguish between generated samples and real tumor ground truths. More importantly, we deliberately design different modules to take into account the well-known obstacles, e.g., severe class imbalance, small tumor localization, and the label noise problem with poor expert annotation quality, and then use these modules to guide the CTumorGAN training process by utilizing multi-level supervision more effectively.

RESULTS

We conduct a comprehensive evaluation on diverse loss functions for tumor segmentation and find that mean square error is more suitable for the CT tumor segmentation task. Furthermore, extensive experiments with multiple evaluation criteria on three well-established datasets, including lung tumor, kidney tumor, and liver tumor databases, also demonstrate that our CTumorGAN achieves stable and competitive performance compared with the state-of-the-art approaches for CT tumor segmentation.

CONCLUSION

In order to overcome those key challenges arising from CT datasets and solve some of the main problems existing in the current deep learning-based methods, we propose a novel unified CTumorGAN framework, which can be effectively generalized to address any kinds of tumor datasets with superior performance.

Automated and Computer-Assisted Detection, Classification, and Diagnosis of Diabetic Retinopathy

Background: The introduction of artificial intelligence (AI) in medicine has raised significant ethical, economic, and scientific controversies. Introduction: Because an explicit goal of AI is to perform processes previously reserved for human clinicians and other health care personnel, there is justified concern about the impact on patient safety, efficacy, equity, and liability. Discussion: Systems for computer-assisted and fully automated detection, triage, and diagnosis of diabetic retinopathy (DR) from retinal images show great variation in design, level of autonomy, and intended use. Moreover, the degree to which these systems have been evaluated and validated is heterogeneous. We use the term DR AI system as a general term for any system that interprets retinal images with at least some degree of autonomy from a human grader. We put forth these standardized descriptors to form a means to categorize systems for computer-assisted and fully automated detection, triage, and diagnosis of DR. The components of the categorization system include level of device autonomy, intended use, level of evidence for diagnostic accuracy, and system design. Conclusion: There is currently minimal empirical basis to assert that certain combinations of autonomy, accuracy, or intended use are better or more appropriate than any other. Therefore, at the current stage of development of this document, we have been descriptive rather than prescriptive, and we treat the different categorizations as independent and organized along multiple axes.

Diagnosis of Glaucoma on Retinal Fundus Images Using Deep Learning: Detection of Nerve Fiber Layer Defect and Optic Disc Analysis

Early detection of glaucoma is important to slow down progression of the disease and to prevent total vision loss. Retinal fundus photography is frequently obtained for various eye disease diagnosis and record and is a suitable screening exam for its simplicity and low cost. However, the number of ophthalmologists who are specialized in glaucoma diagnosis is limited. We have been studying automated schemes for detection of nerve fiber layer defects and analysis of optic disc deformation, two major signs of glaucoma, in assisting ophthalmologists' accurate and efficient diagnosis. In this chapter, our recent progress in computerized methods is discussed.

Patch-Based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation

Glaucoma is a leading cause of irreversible blindness. Accurate segmentation of the optic disc (OD) and optic cup (OC) from fundus images is beneficial to glaucoma screening and diagnosis. Recently, convolutional neural networks demonstrate promising progress in the joint OD and OC segmentation. However, affected by the domain shift among different datasets, deep networks are severely hindered in generalizing across different scanners and institutions. In this paper, we present a novel patch-based output space adversarial learning framework ( p OSAL) to jointly and robustly segment the OD and OC from different fundus image datasets. We first devise a lightweight and efficient segmentation network as a backbone. Considering the specific morphology of OD and OC, a novel morphology-aware segmentation loss is proposed to guide the network to generate accurate and smooth segmentation. Our p OSAL framework then exploits unsupervised domain adaptation to address the domain shift challenge by encouraging the segmentation in the target domain to be similar to the source ones. Since the whole-segmentation-based adversarial loss is insufficient to drive the network to capture segmentation details, we further design the p OSAL in a patch-based fashion to enable fine-grained discrimination on local segmentation details. We extensively evaluate our p OSAL framework and demonstrate its effectiveness in improving the segmentation performance on three public retinal fundus image datasets, i.e., Drishti-GS, RIM-ONE-r3, and REFUGE. Furthermore, our p OSAL framework achieved the first place in the OD and OC segmentation tasks in the MICCAI 2018 Retinal Fundus Glaucoma Challenge.

Accurate Optic Disc and Cup Segmentation from Retinal Images Using a Multi-Feature Based Approach for Glaucoma Assessment

Accurate optic disc (OD) and optic cup (OC) segmentation play a critical role in automatic glaucoma diagnosis. In this paper, we present an automatic segmentation technique regarding the OD and the OC for glaucoma assessment. First, the robust adaptive approach for initializing the level set is designed to increase the performance of contour evolution. Afterwards, in order to handle the complex OD appearance affected by intensity inhomogeneity, pathological changes, and vessel occlusion, a novel model that integrates ample information of OD with the effective local intensity clustering (LIC) model together is presented. For the OC segmentation, to overcome the segmentation challenge as the OC’s complex anatomy location, a novel preprocessing method based on structure prior information between the OD and the OC is designed to guide contour evolution in an effective region. Then, a novel implicit region based on modified data term using a richer form of local image clustering information at each point of interest gathered over a multiple-channel feature image space is presented, to enhance the robustness of the variations found in and around the OC region. The presented models symmetrically integrate the information at each point in a single-channel image from a multiple-channel feature image space. Thus, these models correlate with the concept of symmetry. The proposed models are tested on the publicly available DRISHTI-GS database and the experimental results demonstrate that the models outperform state-of-the-art methods.

CE-Net: Context Encoder Network for 2D Medical Image Segmentation

Medical image segmentation is an important step in medical image analysis. With the rapid development of a convolutional neural network in image processing, deep learning has been used for medical image segmentation, such as optic disc segmentation, blood vessel detection, lung segmentation, cell segmentation, and so on. Previously, U-net based approaches have been proposed. However, the consecutive pooling and strided convolutional operations led to the loss of some spatial information. In this paper, we propose a context encoder network (CE-Net) to capture more high-level information and preserve spatial information for 2D medical image segmentation. CE-Net mainly contains three major components: a feature encoder module, a context extractor, and a feature decoder module. We use the pretrained ResNet block as the fixed feature extractor. The context extractor module is formed by a newly proposed dense atrous convolution block and a residual multi-kernel pooling block. We applied the proposed CE-Net to different 2D medical image segmentation tasks. Comprehensive results show that the proposed method outperforms the original U-Net method and other state-of-the-art methods for optic disc segmentation, vessel detection, lung segmentation, cell contour segmentation, and retinal optical coherence tomography layer segmentation.

Clinical validation of RIA-G, an automated optic nerve head analysis software

Purpose

To clinically validate a new automated glaucoma diagnosis software RIA-G.

Methods

A double-blinded study was conducted where 229 valid random fundus images were evaluated independently by RIA-G and three expert ophthalmologists. Optic nerve head parameters [vertical and horizontal cup-disc ratio (CDR) and neuroretinal rim (NRR) changes] were quantified. Disc damage likelihood scale (DDLS) staging and presence of glaucoma were noted. The software output was compared with consensus values of ophthalmologists.

Results

Mean difference between the vertical CDR output by RIA-G and the ophthalmologists was - 0.004 ± 0.1. Good agreement and strong correlation existed between the two [interclass correlation coefficient (ICC) 0.79; r = 0.77, P < 0.005]. Mean difference for horizontal CDR was - 0.07 ± 0.13 with a moderate to strong agreement and correlation (ICC 0.48; r = 0.61, P < 0.05). Experts and RIA-G found a violation of the inferior-superior NRR in 47 and 54 images, respectively (Cohen's kappa = 0.56 ± 0.07). RIA-G accurately detected DDLS in 66.2% cases, while in 93.8% cases, output was within ± 1 stage (ICC 0.51). Sensitivity and specificity of RIA-G to diagnose glaucomatous neuropathy were 82.3% and 91.8%, respectively. Overall agreement between RIA-G and experts for glaucoma diagnosis was good (Cohen's kappa = 0.62 ± 0.07). Overall accuracy of RIA-G to detect glaucomatous neuropathy was 90.3%. A detection error rate of 5% was noted.

Conclusion

RIA-G showed good agreement with the experts and proved to be a reliable software for detecting glaucomatous optic neuropathy. The ability to quantify optic nerve head parameters from simple fundus photographs will prove particularly useful in glaucoma screening, where no direct patient-doctor contact is established.

Machine Learning in the Detection of the Glaucomatous Disc and Visual Field

Glaucoma is the leading cause of irreversible blindness worldwide. Early detection is of utmost importance as there is abundant evidence that early treatment prevents disease progression, preserves vision, and improves patients' long-term quality of life. The structure and function thresholds that alert to the diagnosis of glaucoma can be obtained entirely via digital means, and as such, screening is well suited to benefit from artificial intelligence and specifically machine learning. This paper reviews the concepts and current literature on the use of machine learning for detection of the glaucomatous disc and visual field.

Diagnostic Accuracy of a Device for the Automated Detection of Diabetic Retinopathy in a Primary Care Setting

OBJECTIVE

To determine the diagnostic accuracy in a real-world primary care setting of a deep learning-enhanced device for automated detection of diabetic retinopathy (DR).

RESEARCH DESIGN AND METHODS

Retinal images of people with type 2 diabetes visiting a primary care screening program were graded by a hybrid deep learning-enhanced device (IDx-DR-EU-2.1; IDx, Amsterdam, the Netherlands), and its classification of retinopathy (vision-threatening [vt]DR, more than mild [mtm]DR, and mild or more [mom]DR) was compared with a reference standard. This reference standard consisted of grading according to the International Clinical Classification of DR by the Rotterdam Study reading center. We determined the diagnostic accuracy of the hybrid deep learning-enhanced device (IDx-DR-EU-2.1) against the reference standard.

RESULTS

A total of 1,616 people with type 2 diabetes were imaged. The hybrid deep learning-enhanced device's sensitivity/specificity against the reference standard was, respectively, for vtDR 100% (95% CI 77.1-100)/97.8% (95% CI 96.8-98.5) and for mtmDR 79.4% (95% CI 66.5-87.9)/93.8% (95% CI 92.1-94.9).

CONCLUSIONS

The hybrid deep learning-enhanced device had high diagnostic accuracy for the detection of both vtDR (although the number of vtDR cases was low) and mtmDR in a primary care setting against an independent reading center. This allows its' safe use in a primary care setting.

Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning

Glaucoma detection in color fundus images is a challenging task that requires expertise and years of practice. In this study we exploited the application of different Convolutional Neural Networks (CNN) schemes to show the influence in the performance of relevant factors like the data set size, the architecture and the use of transfer learning vs newly defined architectures. We also compared the performance of the CNN based system with respect to human evaluators and explored the influence of the integration of images and data collected from the clinical history of the patients. We accomplished the best performance using a transfer learning scheme with VGG19 achieving an AUC of 0.94 with sensitivity and specificity ratios similar to the expert evaluators of the study. The experimental results using three different data sets with 2313 images indicate that this solution can be a valuable option for the design of a computer aid system for the detection of glaucoma in large-scale screening programs.

Structure-Preserving Guided Retinal Image Filtering and Its Application for Optic Disk Analysis

Retinal fundus photographs have been used in the diagnosis of many ocular diseases such as glaucoma, pathological myopia, age-related macular degeneration, and diabetic retinopathy. With the development of computer science, computer aided diagnosis has been developed to process and analyze the retinal images automatically. One of the challenges in the analysis is that the quality of the retinal image is often degraded. For example, a cataract in human lens will attenuate the retinal image, just as a cloudy camera lens which reduces the quality of a photograph. It often obscures the details in the retinal images and posts challenges in retinal image processing and analyzing tasks. In this paper, we approximate the degradation of the retinal images as a combination of human-lens attenuation and scattering. A novel structure-preserving guided retinal image filtering (SGRIF) is then proposed to restore images based on the attenuation and scattering model. The proposed SGRIF consists of a step of global structure transferring and a step of global edge-preserving smoothing. Our results show that the proposed SGRIF method is able to improve the contrast of retinal images, measured by histogram flatness measure, histogram spread, and variability of local luminosity. In addition, we further explored the benefits of SGRIF for subsequent retinal image processing and analyzing tasks. In the two applications of deep learning-based optic cup segmentation and sparse learning-based cup-to-disk ratio (CDR) computation, our results show that we are able to achieve more accurate optic cup segmentation and CDR measurements from images processed by SGRIF.

Automated gonioscopy photography for iridocorneal angle grading

PURPOSE

The aim of this study is to assess the agreement between manual and automated gonioscopy for iridocorneal angle opening.

METHODS

The research is a cross-sectional observational study. Manual and automated gonioscopy were performed to consecutive patients in a glaucoma clinic. Iridocorneal angle opening grading was performed according to Shaffer's classification. Automated gonioscopy was performed with NGS-1 automated gonioscope (NIDEK Co., Gamagori, Japan). The automated gonio-photos were graded by two independent observers. Agreement between automated and manual gonioscopy and also among raters was ascertained by Fleiss' kappa statistic and comparison of area under curve.

RESULTS

In total, 88 eyes of 47 subjects were analysed. Mean age was 63 ± 10 years. Twenty eyes (22.7%) were excluded from grading due to poor quality images. Angle closure was detected in 23.4% with dynamic gonioscopy in comparison with 4.3% using automated image grading. The agreement for angle closure diagnosis between dynamic and automated gonioscopy was low (κ = 0.09 ± 0.10; p = 0.18). The area under curve for detecting eyes with angle closure showed poor accuracy between automated and manual methods (area under curve: 0.53 ± 0.05, 95% confidence interval: 0.44-0.62). There was modest inter-rater agreement for angle opening assessment of automated images with Fleiss' kappa of 0.17 (95% confidence interval: 0.035-0.238).

CONCLUSION

Manual and automated gonioscopy showed only slight agreement for the assessment of iridocorneal angle opening status. Further improvements of the NGS-1 automated gonioscopy and technique are desired for widespread use in a real-life setting.

Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices

Artificial Intelligence (AI) has long promised to increase healthcare affordability, quality and accessibility but FDA, until recently, had never authorized an autonomous AI diagnostic system. This pivotal trial of an AI system to detect diabetic retinopathy (DR) in people with diabetes enrolled 900 subjects, with no history of DR at primary care clinics, by comparing to Wisconsin Fundus Photograph Reading Center (FPRC) widefield stereoscopic photography and macular Optical Coherence Tomography (OCT), by FPRC certified photographers, and FPRC grading of Early Treatment Diabetic Retinopathy Study Severity Scale (ETDRS) and Diabetic Macular Edema (DME). More than mild DR (mtmDR) was defined as ETDRS level 35 or higher, and/or DME, in at least one eye. AI system operators underwent a standardized training protocol before study start. Median age was 59 years (range, 22–84 years); among participants, 47.5% of participants were male; 16.1% were Hispanic, 83.3% not Hispanic; 28.6% African American and 63.4% were not; 198 (23.8%) had mtmDR. The AI system exceeded all pre-specified superiority endpoints at sensitivity of 87.2% (95% CI, 81.8–91.2%) (>85%), specificity of 90.7% (95% CI, 88.3–92.7%) (>82.5%), and imageability rate of 96.1% (95% CI, 94.6–97.3%), demonstrating AI’s ability to bring specialty-level diagnostics to primary care settings. Based on these results, FDA authorized the system for use by health care providers to detect more than mild DR and diabetic macular edema, making it, the first FDA authorized autonomous AI diagnostic system in any field of medicine, with the potential to help prevent vision loss in thousands of people with diabetes annually. ClinicalTrials.gov NCT02963441

Joint Optic Disc and Cup Segmentation Based on Multi-Label Deep Network and Polar Transformation

Glaucoma is a chronic eye disease that leads to irreversible vision loss. The cup to disc ratio (CDR) plays an important role in the screening and diagnosis of glaucoma. Thus, the accurate and automatic segmentation of optic disc (OD) and optic cup (OC) from fundus images is a fundamental task. Most existing methods segment them separately, and rely on hand-crafted visual feature from fundus images. In this paper, we propose a deep learning architecture, named M-Net, which solves the OD and OC segmentation jointly in a one-stage multi-label system. The proposed M-Net mainly consists of multi-scale input layer, U-shape convolutional network, side-output layer, and multi-label loss function. The multi-scale input layer constructs an image pyramid to achieve multiple level receptive field sizes. The U-shape convolutional network is employed as the main body network structure to learn the rich hierarchical representation, while the side-output layer acts as an early classifier that produces a companion local prediction map for different scale layers. Finally, a multi-label loss function is proposed to generate the final segmentation map. For improving the segmentation performance further, we also introduce the polar transformation, which provides the representation of the original image in the polar coordinate system. The experiments show that our M-Net system achieves state-of-the-art OD and OC segmentation result on ORIGA data set. Simultaneously, the proposed method also obtains the satisfactory glaucoma screening performances with calculated CDR value on both ORIGA and SCES datasets.

A Unified Optic Nerve Head and Optic Cup Segmentation Using Unsupervised Neural Networks for Glaucoma Screening

Segmentation of retinal anatomical features such as optic nerve head (ONH) and optic cup, the brightest area in the center of ONH which is devoid of neural elements, is a prerequisite for computer-aided diagnosis and follow-up of glaucoma. The ONH segmentation methods, which imposed shape and intensity constraints, are unable to identify ONH and optic cup boundaries at the same time. On the other hand, recent efficient supervised learning-based methods, which provide a unified system, require combination of many informative features as their inputs, as well as ground truth for the training phase. This paper uses a saliency map including color, intensity and orientation contrasts as the input of a winner-take-all neural network, and color visual features as the input of a self-organizing map neural network to segment ONH and optic cup, simultaneously. Our method is evaluated on a database of 205 ocular fundus images provided by local eye hospitals and publicly available image databases RIMONE and DIARETDB0 comprising 60 non-glaucomtous and 145 glaucomatous images. The ground truth is provided by two expert ophthalmologists. The method attained an average overlapping error of 9.6% and 25.1% for ONH and cup segmentation, respectively. Cup-to-disc area ratio (CDR) is computed for glaucoma assessment. The mean and standard deviation of the CDR differences between our method and the ground truth in all images are 0.11 and 0.09, respectively.

Statistical atlas-based descriptor for an early detection of optic disc abnormalities

Optic disc (OD) appearance in fundus images is one of the clinical indicators considered in the assessment of retinal diseases such as glaucoma. The cup-to-disc ratio (CDR) is the most common clinical measurement used to characterize glaucoma. However, the CDR only evaluates the relative sizes of the cup and the OD via their diameters. We propose to construct an atlas-based shape descriptor (ASD) to statistically characterize the geometric deformations of the OD shape and of the blood vessels' configuration inside the OD region. A local representation of the OD region is proposed to construct a well-defined statistical atlas using nonlinear registration and statistical analysis of deformation fields. The shape descriptor is defined as being composed of several statistical measures from the atlas. Analysis of the average model and its principal modes of deformation are performed on a healthy population. The components of the ASD show a significant difference between pathological and healthy ODs. We show that the ASD is able to characterize healthy and glaucomatous OD regions. The deviation map extracted from the atlas can be used to assist clinicians in an early detection of deformation abnormalities in the OD region.

A Novel Adaptive Deformable Model for Automated Optic Disc and Cup Segmentation to Aid Glaucoma Diagnosis

This paper proposes a novel Adaptive Region-based Edge Smoothing Model (ARESM) for automatic boundary detection of optic disc and cup to aid automatic glaucoma diagnosis. The novelty of our approach consists of two aspects: 1) automatic detection of initial optimum object boundary based on a Region Classification Model (RCM) in a pixel-level multidimensional feature space; 2) an Adaptive Edge Smoothing Update model (AESU) of contour points (e.g. misclassified or irregular points) based on iterative force field calculations with contours obtained from the RCM by minimising energy function (an approach that does not require predefined geometric templates to guide auto-segmentation). Such an approach provides robustness in capturing a range of variations and shapes. We have conducted a comprehensive comparison between our approach and the state-of-the-art existing deformable models and validated it with publicly available datasets. The experimental evaluation shows that the proposed approach significantly outperforms existing methods. The generality of the proposed approach will enable segmentation and detection of other object boundaries and provide added value in the field of medical image processing and analysis.

Contrast based circular approximation for accurate and robust optic disc segmentation in retinal images

A new method for automatic optic disc localization and segmentation is presented. The localization procedure combines vascular and brightness information to provide the best estimate of the optic disc center which is the starting point for the segmentation algorithm. A detection rate of 99.58% and 100% was achieved for the Messidor and ONHSD databases, respectively. A simple circular approximation to the optic disc boundary is proposed based on the maximum average contrast between the inner and outer ring of a circle centered on the estimated location. An average overlap coefficient of 0.890 and 0.865 was achieved for the same datasets, outperforming other state of the art methods. The results obtained confirm the advantages of using a simple circular model under non-ideal conditions as opposed to more complex deformable models.

Optical Coherence Tomography Analysis Based Prediction of Humphrey 24-2 Visual Field Thresholds in Patients With Glaucoma

Purpose

A pilot study showed that prediction of individual Humphrey 24-2 visual field (HVF 24-2) sensitivity thresholds from optical coherence tomography (OCT) image analysis is possible. We evaluate performance of an improved approach as well as 3 other predictive algorithms on a new, fully independent set of glaucoma subjects.

Methods

Subjects underwent HVF 24-2 and 9-field OCT (Heidelberg Spectralis) testing. Nerve fiber (NFL), and ganglion cell and inner plexiform (GCL+IPL) layers were cosegmented and partitioned into 52 sectors matching HVF 24-2 test locations. The Wilcoxon rank sum test was applied to test correlation R, root mean square error (RMSE), and limits of agreement (LoA) between actual and predicted thresholds for four prediction models. The training data consisted of the 9-field OCT and HVF 24-2 thresholds of 111 glaucoma patients from our pilot study.

Results

We studied 112 subjects (112 eyes) with early, moderate, or advanced primary and secondary open angle glaucoma. Subjects with less than 9 scans (15/112) or insufficient quality segmentations (11/97) were excluded. Retinal ganglion cell axonal complex (RGC-AC) optimized had superior average R = 0.74 (95% confidence interval [CI], 0.67-0.76) and RMSE = 5.42 (95% CI, 5.1-5.7) dB, which was significantly better (P < 0.05/3) than the other three models: Naïve (R = 0.49; 95% CI, 0.44-0.54; RMSE = 7.24 dB; 95% CI, 6.6-7.8 dB), Garway-Heath (R = 0.66; 95% CI, 0.60-0.68; RMSE = 6.07 dB; 95% CI, 5.7-6.5 dB), and Donut (R = 0.67; 95% CI, 0.61-0.69; RMSE = 6.08 dB, 95% CI, 5.8-6.4 dB).

Conclusions

The proposed RGC-AC optimized predictive algorithm based on 9-field OCT image analysis and the RGC-AC concept is superior to previous methods and its performance is close to the reproducibility of HVF 24-2.

Similarity regularized sparse group lasso for cup to disc ratio computation

Automatic cup to disc ratio (CDR) computation from color fundus images has shown to be promising for glaucoma detection. Over the past decade, many algorithms have been proposed. In this paper, we first review the recent work in the area and then present a novel similarity-regularized sparse group lasso method for automated CDR estimation. The proposed method reconstructs the testing disc image based on a set of reference disc images by integrating the similarity between testing and the reference disc images with the sparse group lasso constraints. The reconstruction coefficients are then used to estimate the CDR of the testing image. The proposed method has been validated using 650 images with manually annotated CDRs. Experimental results show an average CDR error of 0.0616 and a correlation coefficient of 0.7, outperforming other methods. The areas under curve in the diagnostic test reach 0.843 and 0.837 when manual and automatically segmented discs are used respectively, better than other methods as well.

Joint optic disc and cup boundary extraction from monocular fundus images

BACKGROUND AND OBJECTIVE

Accurate segmentation of optic disc and cup from monocular color fundus images plays a significant role in the screening and diagnosis of glaucoma. Though optic cup is characterized by the drop in depth from the disc boundary, most existing methods segment the two structures separately and rely only on color and vessel kink based cues due to the lack of explicit depth information in color fundus images.

METHODS

We propose a novel boundary-based Conditional Random Field formulation that extracts both the optic disc and cup boundaries in a single optimization step. In addition to the color gradients, the proposed method explicitly models the depth which is estimated from the fundus image itself using a coupled, sparse dictionary trained on a set of image-depth map (derived from Optical Coherence Tomography) pairs.

RESULTS

The estimated depth achieved a correlation coefficient of 0.80 with respect to the ground truth. The proposed segmentation method outperformed several state-of-the-art methods on five public datasets. The average dice coefficient was in the range of 0.87-0.97 for disc segmentation across three datasets and 0.83 for cup segmentation on the DRISHTI-GS1 test set. The method achieved a good glaucoma classification performance with an average AUC of 0.85 for five fold cross-validation on RIM-ONE v2.

CONCLUSIONS

We propose a method to jointly segment the optic disc and cup boundaries by modeling the drop in depth between the two structures. Since our method requires a single fundus image per eye during testing it can be employed in the large-scale screening of glaucoma where expensive 3D imaging is unavailable.

A Population-Based Assessment of the Agreement Between Grading of Goniophotographic Images and Gonioscopy in the Chinese-American Eye Study (CHES)

Purpose

To compare grading of goniophotographic images and gonioscopy in assessing the iridocorneal angle.

Methods

In a population-based, cross-sectional study, participants underwent gonioscopy and goniophotographic imaging during the same visit. The iridocorneal angle was classified as closed if the posterior trabecular meshwork could not be seen. A single masked observer graded the goniophotographic images, and each eye was classified as having angle closure based on the number of closed quadrants. Agreement between the methods was analyzed by calculating kappa (κ) and first-order agreement coefficient (AC1) statistics and comparison of area under receiver operating characteristic curves (AUC).

Results

A total of 4149 Chinese Americans (3994 eyes) were included in this study. The agreement for angle closure diagnosis between gonioscopy and EyeCam was moderate to excellent (κ = 0.60, AC1 0.90, AUC 0.76–0.80).

Conclusions

Detection of iridocorneal angle closure based on goniophotographic imaging shows moderate to very good agreement with angle closure assessment using gonioscopy.

A machine-learning graph-based approach for 3D segmentation of Bruch's membrane opening from glaucomatous SD-OCT volumes

Bruch's membrane opening-minimum rim width (BMO-MRW) is a recently proposed structural parameter which estimates the remaining nerve fiber bundles in the retina and is superior to other conventional structural parameters for diagnosing glaucoma. Measuring this structural parameter requires identification of BMO locations within spectral domain-optical coherence tomography (SD-OCT) volumes. While most automated approaches for segmentation of the BMO either segment the 2D projection of BMO points or identify BMO points in individual B-scans, in this work, we propose a machine-learning graph-based approach for true 3D segmentation of BMO from glaucomatous SD-OCT volumes. The problem is formulated as an optimization problem for finding a 3D path within the SD-OCT volume. In particular, the SD-OCT volumes are transferred to the radial domain where the closed loop BMO points in the original volume form a path within the radial volume. The estimated location of BMO points in 3D are identified by finding the projected location of BMO points using a graph-theoretic approach and mapping the projected locations onto the Bruch's membrane (BM) surface. Dynamic programming is employed in order to find the 3D BMO locations as the minimum-cost path within the volume. In order to compute the cost function needed for finding the minimum-cost path, a random forest classifier is utilized to learn a BMO model, obtained by extracting intensity features from the volumes in the training set, and computing the required 3D cost function. The proposed method is tested on 44 glaucoma patients and evaluated using manual delineations. Results show that the proposed method successfully identifies the 3D BMO locations and has significantly smaller errors compared to the existing 3D BMO identification approaches.