Automated segmentation of optic disc in SD-OCT images and cup-to-disc ratios quantification by patch searching-based neural canal opening detection

Diagnosing glaucoma in primary eye care and the role of Artificial Intelligence applications for reducing the prevalence of undetected glaucoma in Australia

Glaucoma is the commonest cause of irreversible blindness worldwide, with over 70% of people affected remaining undiagnosed. Early detection is crucial for halting progressive visual impairment in glaucoma patients, as there is no cure available. This narrative review aims to: identify reasons for the significant under-diagnosis of glaucoma globally, particularly in Australia, elucidate the role of primary healthcare in glaucoma diagnosis using Australian healthcare as an example, and discuss how recent advances in artificial intelligence (AI) can be implemented to improve diagnostic outcomes. Glaucoma is a prevalent disease in ageing populations and can have improved visual outcomes through appropriate treatment, making it essential for general medical practice. In countries such as Australia, New Zealand, Canada, USA, and the UK, optometrists serve as the gatekeepers for primary eye care, and glaucoma detection often falls on their shoulders. However, there is significant variation in the capacity for glaucoma diagnosis among eye professionals. Automation with Artificial Intelligence (AI) analysis of optic nerve photos can help optometrists identify high-risk changes and mitigate the challenges of image interpretation rapidly and consistently. Despite its potential, there are significant barriers and challenges to address before AI can be deployed in primary healthcare settings, including external validation, high quality real-world implementation, protection of privacy and cybersecurity, and medico-legal implications. Overall, the incorporation of AI technology in primary healthcare has the potential to reduce the global prevalence of undiagnosed glaucoma cases by improving diagnostic accuracy and efficiency.

Applications of Artificial Intelligence and Deep Learning in Glaucoma

Diagnosis and detection of progression of glaucoma remains challenging. Artificial intelligence-based tools have the potential to improve and standardize the assessment of glaucoma but development of these algorithms is difficult given the multimodal and variable nature of the diagnosis. Currently, most algorithms are focused on a single imaging modality, specifically screening and diagnosis based on fundus photos or optical coherence tomography images. Use of anterior segment optical coherence tomography and goniophotographs is limited. The majority of algorithms designed for disease progression prediction are based on visual fields. No studies in our literature search assessed the use of artificial intelligence for treatment response prediction and no studies conducted prospective testing of their algorithms. Additional challenges to the development of artificial intelligence-based tools include scarcity of data and a lack of consensus in diagnostic criteria. Although research in the use of artificial intelligence for glaucoma is promising, additional work is needed to develop clinically usable tools.

Automatic Segmentation of the Optic Nerve Head Region in Optical Coherence Tomography: A Methodological Review

The optic nerve head (ONH) represents the intraocular section of the optic nerve, which is prone to damage by intraocular pressure (IOP). The advent of optical coherence tomography (OCT) has enabled the evaluation of novel ONH parameters, namely the depth and curvature of the lamina cribrosa (LC). Together with the Bruch's membrane minimum-rim-width (BMO-MRW), these seem to be promising ONH parameters for diagnosis and monitoring of retinal diseases such as glaucoma. Nonetheless, these OCT derived biomarkers are mostly extracted through manual segmentation, which is time-consuming and prone to bias, thus limiting their usability in clinical practice. The automatic segmentation of ONH in OCT scans could further improve the current clinical management of glaucoma and other diseases. This review summarizes the current state-of-the-art in automatic segmentation of the ONH in OCT. PubMed and Scopus were used to perform a systematic review. Additional works from other databases (IEEE, Google Scholar and ARVO IOVS) were also included, resulting in a total of 29 reviewed studies. For each algorithm, the methods, the size and type of dataset used for validation, and the respective results were carefully analysed. The results show a lack of consensus regarding the definition of segmented regions, extracted parameters and validation approaches, highlighting the importance and need of standardized methodologies for ONH segmentation. Only with a concrete set of guidelines, these automatic segmentation algorithms will build trust in data-driven segmentation models and be able to enter clinical practice.

Automatic Anisotropic Diffusion Filtering and Graph-search Segmentation of Macular Spectral-domain Optical Coherence Tomographic (SD-OCT) Images

BACKGROUND

Optical Coherence Tomography (OCT) is a non-invasive medical imaging technique that provides high-resolution cross-sectional images of the retina. There is a need to develop algorithms for obtaining quantitative and qualitative information about the retina which are essential for assessing and managing eye conditions.

METHODS

This work emphasizes on an automated image processing algorithm for segmenting retinal layers. It involves preprocessing of the acquired retinal SD-OCT image (B-scan) using the proposed automatic Anisotropic diffusion filter, followed with contrast stretching to suppress intrinsic speckle noise without blurring structural edges. Graph search segmentation using Dijkstra algorithm with a combination of threshold and axial gradient as the cost function is used to segment the retinal layer boundaries.

RESULTS

The algorithm was performed and the average thickness of the segmented retina was computed for the 3D retinal scan (128 B-scans) of 8 subjects (4 normal and 4 abnormal) using Early Treatment Diabetic Retinopathy Screening (ETDRS) chart.

CONCLUSION

Segmentation was evaluated using manually segmented B-scan by an Ophthalmologist as ground truth and accuracy was found to be 99.14 ± 0.27%.

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.

Liver tissue classification of en face images by fractal dimension-based support vector machine

Full-field optical coherence tomography (FF-OCT) has been reported with its label-free subcellular imaging performance. To realize quantitive cancer detection, the support vector machine model of classifying normal and cancerous human liver tissue is proposed with en face tomographic images. Twenty samples (10 normal and 10 cancerous) were operated from humans and composed of 285 en face tomographic images. Six histogram features and one proposed fractal dimension parameter that reveal the refractive index inhomogeneities of tissue were extracted and made up the training set. The other different 16 samples (8 normal and 8 cancerous) were imaged (190 images) and employed as the test set with the same features. First, a subcellular-resolution tomographic image library for four histopathological areas in liver tissue was established. Second, the area under the receiver operating characteristics of 0.9378, 0.9858, 0.9391, 0.9517 for prediction of the cancerous hepatic cell, central vein, fibrosis, and portal vein were measured with the test set. The results indicate that the proposed classifier from FF-OCT images shows promise as a label-free assessment of quantified tumor detection, suggesting the fractal dimension-based classifier could aid clinicians in detecting tumor boundaries for resection in surgery in the future.

Feasibility of support vector machine learning in age-related macular degeneration using small sample yielding sparse optical coherence tomography data

PURPOSE

A retrospective pilot study is conducted to demonstrate the utility of a novel support vector machine learning (SVML) algorithm in a small three-dimensional (3D) sample yielding sparse optical coherence tomography (spOCT) data for the automatic monitoring of neovascular (wet) age-related macular degeneration (wAMD).

METHODS

From the anti-vascular endothelial growth factor injection database, 588 consecutive pairs of OCT volumes (57.624 B-scans) were selected in 70 randomly chosen wAMD patients treated with ranibizumab. The SVML algorithm was applied to 183 OCT volume pairs (17.934 B-scans) in 30 patients. Four independent, diagnosis-blinded retina specialists indicated whether wAMD activity was present between 100 pairs of consecutive OCT volumes (9800 B-scans) in the remaining 40 patients for comparison with the SVML algorithm and a non-complex baseline algorithm using only retinal thickness. The SVML algorithm was assessed using inter-observer variability and receiver operating characteristic (ROC) analyses.

RESULTS

The retina specialists showed an average Cohen's κ of 0.57 ± 0.13 (minimum: 0.41, maximum: 0.83). The average κ between the proposed algorithm and the retina specialists was 0.62 ± 0.05 and 0.43 ± 0.14 between the baseline algorithm and the retina specialists. Using each of the four retina specialists as the reference, the proposed method showed a superior area under the ROC curve of 0.91 ± 0.03 compared to the ROC 0.81 ± 0.05 shown by the baseline algorithm.

CONCLUSION

The SVML algorithm was as effective as the retina specialists were in detecting activity in wAMD. Support vector machine learning (SVML) may be a useful monitoring tool in wAMD suited for small samples that yield sparse OCT data possibly derived from self-measuring OCT-robots.

Region-segmentation strategy for Bruch's membrane opening detection in spectral domain optical coherence tomography images

Bruch's membrane opening (BMO) is an important biomarker in the progression of glaucoma. Bruch's membrane opening minimum rim width (BMO-MRW), cup-to-disc ratio in spectral domain optical coherence tomography (SD-OCT) and lamina cribrosa depth based on BMO are important measurable parameters for glaucoma diagnosis. The accuracy of measuring these parameters is significantly affected by BMO detection. In this paper, we propose a method for automatically detecting BMO in SD-OCT volumes accurately to reduce the impact of the border tissue and vessel shadows. The method includes three stages: a coarse detection stage composed by retinal pigment epithelium layer segmentation, optic disc segmentation, and multi-modal registration; a fixed detection stage based on the U-net in which BMO detection is transformed into a region segmentation problem and an area bias component is proposed in the loss function; and a post-processing stage based on the consistency of results to remove outliers. Experimental results show that the proposed method outperforms previous methods and achieves a mean error of 42.38 μm.

Applications of Artificial Intelligence in Ophthalmology: General Overview

With the emergence of unmanned plane, autonomous vehicles, face recognition, and language processing, the artificial intelligence (AI) has remarkably revolutionized our lifestyle. Recent studies indicate that AI has astounding potential to perform much better than human beings in some tasks, especially in the image recognition field. As the amount of image data in imaging center of ophthalmology is increasing dramatically, analyzing and processing these data is in urgent need. AI has been tried to apply to decipher medical data and has made extraordinary progress in intelligent diagnosis. In this paper, we presented the basic workflow for building an AI model and systematically reviewed applications of AI in the diagnosis of eye diseases. Future work should focus on setting up systematic AI platforms to diagnose general eye diseases based on multimodal data in the real world.

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.

ASI aurora search: an attempt of intelligent image processing for circular fisheye lens

The circular fisheye lens exhibits an approximately 180° angular field-of-view (FOV), which is much larger than that of an ordinary lens. Thus, images captured with a circular fisheye lens are distributed non-uniformly with spherical deformation. Along with the fast development of deep neural networks for normal images, how to apply it to achieve intelligent image processing for a circular fisheye lens is a new task of significant importance. In this paper, we take the aurora images captured with all-sky-imagers (ASI) as a typical example. By analyzing the imaging principle of ASI and the magnetic characteristics of the aurora, a deformed region division (DRD) scheme is proposed to replace the region proposals network (RPN) in the advanced mask regional convolutional neural network (Mask R-CNN) framework. Thus, each image can be regarded as a "bag" of deformed regions represented with CNN features. After clustering all CNN features to generate a vocabulary, each deformed region is quantified to its nearest center for indexing. On the stage of an online search, a similarity score is computed by measuring the distances between regions in the query image and all regions in the data set, and the image with the highest value is outputted as the top rank search result. Experimental results show that the proposed method greatly improves the search accuracy and efficiency, demonstrating that it is a valuable attempt of intelligent image processing for circular fisheye lenses.