Graph convolutional network based optic disc and cup segmentation on fundus images

Highly Accurate and Precise Automated Cup-to-Disc Ratio Quantification for Glaucoma Screening

Objective

An enlarged cup-to-disc ratio (CDR) is a hallmark of glaucomatous optic neuropathy. Manual assessment of the CDR may be less accurate and more time-consuming than automated methods. Here, we sought to develop and validate a deep learning-based algorithm to automatically determine the CDR from fundus images.

Design

Algorithm development for estimating CDR using fundus data from a population-based observational study.

Participants

A total of 181 768 fundus images from the United Kingdom Biobank (UKBB), Drishti_GS, and EyePACS.

Methods

FastAI and PyTorch libraries were used to train a convolutional neural network-based model on fundus images from the UKBB. Models were constructed to determine image gradability (classification analysis) as well as to estimate CDR (regression analysis). The best-performing model was then validated for use in glaucoma screening using a multiethnic dataset from EyePACS and Drishti_GS.

Main Outcome Measures

The area under the receiver operating characteristic curve and coefficient of determination.

Results

Our gradability model vgg19_batch normalization (bn) achieved an accuracy of 97.13% on a validation set of 16 045 images, with 99.26% precision and area under the receiver operating characteristic curve of 96.56%. Using regression analysis, our best-performing model (trained on the vgg19_bn architecture) attained a coefficient of determination of 0.8514 (95% confidence interval [CI]: 0.8459-0.8568), while the mean squared error was 0.0050 (95% CI: 0.0048-0.0051) and mean absolute error was 0.0551 (95% CI: 0.0543-0.0559) on a validation set of 12 183 images for determining CDR. The regression point was converted into classification metrics using a tolerance of 0.2 for 20 classes; the classification metrics achieved an accuracy of 99.20%. The EyePACS dataset (98 172 healthy, 3270 glaucoma) was then used to externally validate the model for glaucoma classification, with an accuracy, sensitivity, and specificity of 82.49%, 72.02%, and 82.83%, respectively.

Conclusions

Our models were precise in determining image gradability and estimating CDR. Although our artificial intelligence-derived CDR estimates achieve high accuracy, the CDR threshold for glaucoma screening will vary depending on other clinical parameters.

Financial Disclosures

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Performance Evaluation of Different Object Detection Models for the Segmentation of Optical Cups and Discs

Glaucoma is an eye disease that gradually deteriorates vision. Much research focuses on extracting information from the optic disc and optic cup, the structure used for measuring the cup-to-disc ratio. These structures are commonly segmented with deeplearning techniques, primarily using Encoder-Decoder models, which are hard to train and time-consuming. Object detection models using convolutional neural networks can extract features from fundus retinal images with good precision. However, the superiority of one model over another for a specific task is still being determined. The main goal of our approach is to compare object detection model performance to automate segment cups and discs on fundus images. This study brings the novelty of seeing the behavior of different object detection models in the detection and segmentation of the disc and the optical cup (Mask R-CNN, MS R-CNN, CARAFE, Cascade Mask R-CNN, GCNet, SOLO, Point_Rend), evaluated on Retinal Fundus Images for Glaucoma Analysis (REFUGE), and G1020 datasets. Reported metrics were Average Precision (AP), F1-score, IoU, and AUCPR. Several models achieved the highest AP with a perfect 1.000 when the threshold for IoU was set up at 0.50 on REFUGE, and the lowest was Cascade Mask R-CNN with an AP of 0.997. On the G1020 dataset, the best model was Point_Rend with an AP of 0.956, and the worst was SOLO with 0.906. It was concluded that the methods reviewed achieved excellent performance with high precision and recall values, showing efficiency and effectiveness. The problem of how many images are needed was addressed with an initial value of 100, with excellent results. Data augmentation, multi-scale handling, and anchor box size brought improvements. The capability to translate knowledge from one database to another shows promising results too.

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.

Graph deep network for optic disc and optic cup segmentation for glaucoma disease using retinal imaging

The fundus imaging method of eye screening detects eye diseases by segmenting the optic disc (OD) and optic cup (OC). OD and OC are still challenging to segment accurately. This work proposes three-layer graph-based deep architecture with an enhanced fusion method for OD and OC segmentation. CNN encoder-decoder architecture, extended graph network, and approximation via fusion-based rule are explored for connecting local and global information. A graph-based model is developed for combining local and overall knowledge. By extending feature masking, regularization of repetitive features with fusion for combining channels has been done. The performance of the proposed network is evaluated through the analysis of different metric parameters such as dice similarity coefficient (DSC), intersection of union (IOU), accuracy, specificity, sensitivity. Experimental verification of this methodology has been done using the four benchmarks publicly available datasets DRISHTI-GS, RIM-ONE for OD, and OC segmentation. In addition, DRIONS-DB and HRF fundus imaging datasets were analyzed for optimizing the model's performance based on OD segmentation. DSC metric of methodology achieved 0.97 and 0.96 for DRISHTI-GS and RIM-ONE, respectively. Similarly, IOU measures for DRISHTI-GS and RIM-ONE datasets were 0.96 and 0.93, respectively, for OD measurement. For OC segmentation, DSC and IOU were measured as 0.93 and 0.90 respectively for DRISHTI-GS and 0.83 and 0.82 for RIM-ONE data. The proposed technique improved value of metrics with most of the existing methods in terms of DSC and IOU of the results metric of the experiments for OD and OC segmentation.

Machine Learning and Deep Learning Techniques for Optic Disc and Cup Segmentation - A Review

Background

Globally, glaucoma is the second leading cause of blindness. Detecting glaucoma in the early stages is essential to avoid disease complications, which lead to blindness. Thus, computer-aided diagnosis systems are powerful tools to overcome the shortage of glaucoma screening programs.

Methods

A systematic search of public databases, including PubMed, Google Scholar, and other sources, was performed to identify relevant studies to overview the publicly available fundus image datasets used to train, validate, and test machine learning and deep learning methods. Additionally, existing machine learning and deep learning methods for optic cup and disc segmentation were surveyed and critically reviewed.

Results

Eight fundus images datasets were publicly available with 15,445 images labeled with glaucoma or non-glaucoma, and manually annotated optic disc and cup boundaries were found. Five metrics were identified for evaluating the developed models. Finally, three main deep learning architectural designs were commonly used for optic disc and optic cup segmentation.

Conclusion

We provided future research directions to formulate robust optic cup and disc segmentation systems. Deep learning can be utilized in clinical settings for this task. However, many challenges need to be addressed before using this strategy in clinical trials. Finally, two deep learning architectural designs have been widely adopted, such as U-net and its variants.

GDCSeg-Net: general optic disc and cup segmentation network for multi-device fundus images

Accurate segmentation of optic disc (OD) and optic cup (OC) in fundus images is crucial for the analysis of many retinal diseases, such as the screening and diagnosis of glaucoma and atrophy segmentation. Due to domain shift between different datasets caused by different acquisition devices and modes and inadequate training caused by small sample dataset, the existing deep-learning-based OD and OC segmentation networks have poor generalization ability for different fundus image datasets. In this paper, adopting the mixed training strategy based on different datasets for the first time, we propose an encoder-decoder based general OD and OC segmentation network (named as GDCSeg-Net) with the newly designed multi-scale weight-shared attention (MSA) module and densely connected depthwise separable convolution (DSC) module, to effectively overcome these two problems. Experimental results show that our proposed GDCSeg-Net is competitive with other state-of-the-art methods on five different public fundus image datasets, including REFUGE, MESSIDOR, RIM-ONE-R3, Drishti-GS and IDRiD.

Graph Neural Networks and Their Current Applications in Bioinformatics

Graph neural networks (GNNs), as a branch of deep learning in non-Euclidean space, perform particularly well in various tasks that process graph structure data. With the rapid accumulation of biological network data, GNNs have also become an important tool in bioinformatics. In this research, a systematic survey of GNNs and their advances in bioinformatics is presented from multiple perspectives. We first introduce some commonly used GNN models and their basic principles. Then, three representative tasks are proposed based on the three levels of structural information that can be learned by GNNs: node classification, link prediction, and graph generation. Meanwhile, according to the specific applications for various omics data, we categorize and discuss the related studies in three aspects: disease prediction, drug discovery, and biomedical imaging. Based on the analysis, we provide an outlook on the shortcomings of current studies and point out their developing prospect. Although GNNs have achieved excellent results in many biological tasks at present, they still face challenges in terms of low-quality data processing, methodology, and interpretability and have a long road ahead. We believe that GNNs are potentially an excellent method that solves various biological problems in bioinformatics research.

Anatomy-aided deep learning for medical image segmentation: a review

Deep learning (DL) has become widely used for medical image segmentation in recent years. However, despite these advances, there are still problems for which DL-based segmentation fails. Recently, some DL approaches had a breakthrough by using anatomical information which is the crucial cue for manual segmentation. In this paper, we provide a review of anatomy-aided DL for medical image segmentation which covers systematically summarized anatomical information categories and corresponding representation methods. We address known and potentially solvable challenges in anatomy-aided DL and present a categorized methodology overview on using anatomical information with DL from over 70 papers. Finally, we discuss the strengths and limitations of the current anatomy-aided DL approaches and suggest potential future work.