Towards standardising retinal OCT angiography image analysis with open-source toolbox OCTAVA.

Quantitative assessment of retinal microvasculature in optical coherence tomography angiography (OCTA) images is important for studying, diagnosing, monitoring, and guiding the treatment of ocular and systemic diseases. However, the OCTA user community lacks universal and transparent image analysis tools that can be applied to images from a range of OCTA instruments and provide reliable and consistent microvascular metrics from diverse datasets. We present a retinal extension to the OCTA Vascular Analyser (OCTAVA) that addresses the challenges of providing robust, easy-to-use, and transparent analysis of retinal OCTA images. OCTAVA is a user-friendly, open-source toolbox that can analyse retinal OCTA images from various instruments. The toolbox delivers seven microvascular metrics for the whole image or subregions and six metrics characterising the foveal avascular zone. We validate OCTAVA using images collected by four commercial OCTA instruments demonstrating robust performance across datasets from different instruments acquired at different sites from different study cohorts. We show that OCTAVA delivers values for retinal microvascular metrics comparable to the literature and reduces their variation between studies compared to their commercial equivalents. By making OCTAVA publicly available, we aim to expand standardised research and thereby improve the reproducibility of quantitative analysis of retinal microvascular imaging. Such improvements will help to better identify more reliable and sensitive biomarkers of ocular and systemic diseases.

Early inner plexiform layer thinning and retinal nerve fiber layer thickening in excitotoxic retinal injury using deep learning-assisted optical coherence tomography.

Excitotoxicity from the impairment of glutamate uptake constitutes an important mechanism in neurodegenerative diseases such as Alzheimer's, multiple sclerosis, and Parkinson's disease. Within the eye, excitotoxicity is thought to play a critical role in retinal ganglion cell death in glaucoma, diabetic retinopathy, retinal ischemia, and optic nerve injury, yet how excitotoxic injury impacts different retinal layers is not well understood. Here, we investigated the longitudinal effects of N-methyl-D-aspartate (NMDA)-induced excitotoxic retinal injury in a rat model using deep learning-assisted retinal layer thickness estimation. Before and after unilateral intravitreal NMDA injection in nine adult Long Evans rats, spectral-domain optical coherence tomography (OCT) was used to acquire volumetric retinal images in both eyes over 4 weeks. Ten retinal layers were automatically segmented from the OCT data using our deep learning-based algorithm. Retinal degeneration was evaluated using layer-specific retinal thickness changes at each time point (before, and at 3, 7, and 28 days after NMDA injection). Within the inner retina, our OCT results showed that retinal thinning occurred first in the inner plexiform layer at 3 days after NMDA injection, followed by the inner nuclear layer at 7 days post-injury. In contrast, the retinal nerve fiber layer exhibited an initial thickening 3 days after NMDA injection, followed by normalization and thinning up to 4 weeks post-injury. Our results demonstrated the pathological cascades of NMDA-induced neurotoxicity across different layers of the retina. The early inner plexiform layer thinning suggests early dendritic shrinkage, whereas the initial retinal nerve fiber layer thickening before subsequent normalization and thinning indicates early inflammation before axonal loss and cell death. These findings implicate the inner plexiform layer as an early imaging biomarker of excitotoxic retinal degeneration, whereas caution is warranted when interpreting the ganglion cell complex combining retinal nerve fiber layer, ganglion cell layer, and inner plexiform layer thicknesses in conventional OCT measures. Deep learning-assisted retinal layer segmentation and longitudinal OCT monitoring can help evaluate the different phases of retinal layer damage upon excitotoxicity.

Retinal capillary perfusion heterogeneity in diabetic retinopathy detected by optical coherence tomography angiography.

BACKGROUND: Diabetic retinopathy (DR) is a leading cause of blindness and involves retinal capillary damage, microaneurysms, and altered blood flow regulation. Optical coherence tomography angiography (OCTA) is a non-invasive way of visualizing retinal vasculature but has not been used extensively to study blood flow heterogeneity. The purpose of this study is to detect and quantify blood flow heterogeneity utilizing en-face swept source OCTA in patients with DR. METHODS: This is a prospective clinical study which examined patients with either type 1 or 2 diabetes mellitus. Each included eye was graded clinically as no DR, mild DR, or moderate-severe DR. Ten consecutive en face 6 × 6 mm foveal SS-OCTA images were obtained from each eye using a PLEX Elite 9000 (Zeiss Meditec, Dublin, CA). Built-in fixation-tracking, follow-up functions were utilized to reduce motion artifacts and ensure same location imaging in sequential frames. Images of the superficial and deep vascular complexes (SVC and DVC) were arranged in temporal stacks of 10 and registered to a reference frame for segmentation using a deep neural network. The vessel segmentation was then masked onto each stack to calculate the pixel intensity coefficient of variance (PICoV) and map the spatiotemporal perfusion heterogeneity of each stack. RESULTS: Twenty-nine eyes were included: 7 controls, 7 diabetics with no DR, 8 mild DR, and 7 moderate-severe DR. The PICoV correlated significantly and positively with DR severity. In patients with DR, the perfusion heterogeneity was higher in the temporal half of the macula, particularly in areas of capillary dropout. PICoV also correlates as expected with the established OCTA metrics of perfusion density and vessel density. CONCLUSION: PICoV is a novel way to analyze OCTA imaging and quantify perfusion heterogeneity. Retinal capillary perfusion heterogeneity in both the SVC and DVC increased with DR severity. This may be related to the loss of retinal capillary perfusion autoregulation in diabetic retinopathy.

Polarization-Diversity Optical Coherence Tomography Assessment of Choroidal Nevi.

Purpose: The purpose of this study was to demonstrate the utility of polarization-diversity optical coherence tomography (PD-OCT), a noninvasive imaging technique with melanin-specific contrast, in the quantitative and qualitative assessment of choroidal nevi. Methods: Nevi were imaged with a custom-built 55-degree field-of-view (FOV) 400 kHz PD-OCT system. Imaging features on PD-OCT were compared to those on fundus photography, auto-fluorescence, ultrasound, and non-PD-OCT images. Lesions were manually segmented for size measurement and metrics for objective assessment of melanin distributions were calculated, including degree of polarization uniformity (DOPU), attenuation coefficient, and melanin occupancy rate (MOR). Results: We imaged 17 patients (mean age = 69.5 years, range = 37-90) with 11 pigmented, 3 non-pigmented, and 3 mixed pigmentation nevi. Nevi with full margin acquisition had an average longest basal diameter of 5.1 mm (range = 2.99-8.72 mm) and average height of 0.72 mm (range = 0.37 mm-2.09 mm). PD-OCT provided clear contrast of choroidal melanin content, distribution, and delineation of nevus margins for melanotic nevi. Pigmented nevi were found to have lower DOPU, higher attenuation coefficient, and higher MOR than non-pigmented lesions. Melanin content on PD-OCT was consistent with pigmentation on fundus in 15 of 17 nevi (88%). Conclusions: PD-OCT allows objective assessment of choroidal nevi melanin content and distribution. In addition, melanin-specific contrast by PD-OCT enables clear nevus margin delineation and may improve serial growth surveillance. Further investigation is needed to determine the clinical significance and prognostic value of melanin characterization by PD-OCT in the evaluation of choroidal nevi.

PseudoSegRT: efficient pseudo-labelling for intraoperative OCT segmentation.

PURPOSE: Robotic ophthalmic microsurgery has significant potential to help improve the success of challenging procedures and overcome the physical limitations of the surgeon. Intraoperative optical coherence tomography (iOCT) has been reported for the visualisation of ophthalmic surgical manoeuvres, where deep learning methods can be used for real-time tissue segmentation and surgical tool tracking. However, many of these methods rely heavily on labelled datasets, where producing annotated segmentation datasets is a time-consuming and tedious task. METHODS: To address this challenge, we propose a robust and efficient semi-supervised method for boundary segmentation in retinal OCT to guide a robotic surgical system. The proposed method uses U-Net as the base model and implements a pseudo-labelling strategy which combines the labelled data with unlabelled OCT scans during training. After training, the model is optimised and accelerated with the use of TensorRT. RESULTS: Compared with fully supervised learning, the pseudo-labelling method can improve the generalisability of the model and show better performance for unseen data from a different distribution using only 2% of labelled training samples. The accelerated GPU inference takes less than 1 millisecond per frame with FP16 precision. CONCLUSION: Our approach demonstrates the potential of using pseudo-labelling strategies in real-time OCT segmentation tasks to guide robotic systems. Furthermore, the accelerated GPU inference of our network is highly promising for segmenting OCT images and guiding the position of a surgical tool (e.g. needle) for sub-retinal injections.

Segmentation-guided domain adaptation and data harmonization of multi-device retinal optical coherence tomography using cycle-consistent generative adversarial networks.

BACKGROUND: Medical images such as Optical Coherence Tomography (OCT) images acquired from different devices may show significantly different intensity profiles. An automatic segmentation model trained on images from one device may perform poorly when applied to images acquired using another device, resulting in a lack of generalizability. This study addresses this issue using domain adaptation methods improved by Cycle-Consistent Generative Adversarial Networks (CycleGAN), especially when the ground-truth labels are only available in the source domain. METHODS: A two-stage pipeline is proposed to generate segmentation in the target domain. The first stage involves the training of a state-of-the-art segmentation model in the source domain. The second stage aims to adapt the images from the target domain to the source domain. The adapted target domain images are segmented using the model in the first stage. Ablation tests were performed with integration of different loss functions, and the statistical significance of these models is reported. Both the segmentation performance and the adapted image quality metrics were evaluated. RESULTS: Regarding the segmentation Dice score, the proposed model ssppg achieves a significant improvement of 46.24% compared to without adaptation and reaches 87.4% of the upper limit of the segmentation performance. Furthermore, image quality metrics, including FID and KID scores, indicate that adapted images with better segmentation also have better image qualities. CONCLUSION: The proposed method demonstrates the effectiveness of segmentation-driven domain adaptation in retinal imaging processing. It reduces the labor cost of manual labeling, incorporates prior anatomic information to regulate and guide domain adaptation, and provides insights into improving segmentation qualities in image domains without labels.

Reverse translation of artificial intelligence in glaucoma: Connecting basic science with clinical applications.

Artificial intelligence (AI) has been approved for biomedical research in diverse areas from bedside clinical studies to benchtop basic scientific research. For ophthalmic research, in particular glaucoma, AI applications are rapidly growing for potential clinical translation given the vast data available and the introduction of federated learning. Conversely, AI for basic science remains limited despite its useful power in providing mechanistic insight. In this perspective, we discuss recent progress, opportunities, and challenges in the application of AI in glaucoma for scientific discoveries. Specifically, we focus on the research paradigm of reverse translation, in which clinical data are first used for patient-centered hypothesis generation followed by transitioning into basic science studies for hypothesis validation. We elaborate on several distinctive areas of research opportunities for reverse translation of AI in glaucoma including disease risk and progression prediction, pathology characterization, and sub-phenotype identification. We conclude with current challenges and future opportunities for AI research in basic science for glaucoma such as inter-species diversity, AI model generalizability and explainability, as well as AI applications using advanced ocular imaging and genomic data.

Pilot study of optical coherence tomography angiography-derived microvascular metrics in hands and feet of healthy and diabetic people.

Optical coherence tomography angiography (OCTA) is a non-invasive, high-resolution imaging modality with growing application in dermatology and microvascular assessment. Accepted reference values for OCTA-derived microvascular parameters in skin do not yet exist but need to be established to drive OCTA into the clinic. In this pilot study, we assess a range of OCTA microvascular metrics at rest and after post-occlusive reactive hyperaemia (PORH) in the hands and feet of 52 healthy people and 11 people with well-controlled type 2 diabetes mellitus (T2DM). We calculate each metric, measure test-retest repeatability, and evaluate correlation with demographic risk factors. Our study delivers extremity-specific, age-dependent reference values and coefficients of repeatability of nine microvascular metrics at baseline and at the maximum of PORH. Significant differences are not seen for age-dependent microvascular metrics in hand, but they are present for several metrics in the foot. Significant differences are observed between hand and foot, both at baseline and maximum PORH, for most of the microvascular metrics with generally higher values in the hand. Despite a large variability over a range of individuals, as is expected based on heterogeneous ageing phenotypes of the population, the test-retest repeatability is 3.5% to 18% of the mean value for all metrics, which highlights the opportunities for OCTA-based studies in larger cohorts, for longitudinal monitoring, and for assessing the efficacy of interventions. Additionally, branchpoint density in the hand and foot and changes in vessel diameter in response to PORH stood out as good discriminators between healthy and T2DM groups, which indicates their potential value as biomarkers. This study, building on our previous work, represents a further step towards standardised OCTA in clinical practice and research.

Adaptive optics scanning laser ophthalmoscopy and optical coherence tomography (AO-SLO-OCT) system for in vivo mouse retina imaging.

Optical coherence tomography (OCT) and scanning laser ophthalmoscopy (SLO) are imaging technologies invented in the 1980s that have revolutionized the field of in vivo retinal diagnostics and are now commonly used in ophthalmology clinics as well as in vision science research. Adaptive optics (AO) technology enables high-fidelity correction of ocular aberrations, resulting in improved resolution and sensitivity for both SLO and OCT systems. The potential of gathering multi-modal cellular-resolution information in a single instrument is of great interest to the ophthalmic imaging community. Although similar instruments have been developed for imaging the human retina, developing such a system for mice will benefit basic science research and should help with further dissemination of AO technology. Here, we present our work integrating OCT into an existing mouse retinal AO-SLO system, resulting in a multi-modal AO-enhanced imaging system of the living mouse eye. The new system allows either independent or simultaneous data acquisition of AO-SLO and AO-OCT, depending on the requirements of specific scientific experiments. The system allows a data acquisition speed of 200 kHz A-scans/pixel rate for OCT and SLO, respectively. It offers ∼6 µm axial resolution for AO-OCT and a ∼1 µm lateral resolution for AO-SLO-OCT imaging.

Effects of Myopia and Glaucoma on the Neural Canal and Lamina Cribrosa Using Optical Coherence Tomography.

PRCIS: Glaucoma was associated with axial bowing and rotation of Bruchs membrane opening (BMO) and anterior laminar insertion (ALI), skewed neural canal, and deeper anterior lamina cribrosa surface (ALCS). Longer axial length was associated with wider, longer, and more skewed neural canal and flatter ALCS. PURPOSE: Investigate the effects of myopia and glaucoma in the prelaminar neural canal and anterior lamina cribrosa using 1060-nm swept-source optical coherence tomography. PATIENTS: 19 control (38 eyes) and 38 glaucomatous subjects (63 eyes). MATERIALS AND METHODS: Participants were imaged with swept-source optical coherence tomography, and the images were analyzed for the BMO and ALI dimensions, prelaminar neural canal dimensions, and ALCS depth. RESULTS: Glaucomatous eyes had more bowed and nasally rotated BMO and ALI, more horizontally skewed prelaminar neural canal, and deeper ALCS than the control eyes. Increased axial length was associated with a wider, longer, and more horizontally skewed neural canal and a decrease in the ALCS depth and curvature. CONCLUSION: Our findings suggest that glaucomatous posterior bowing or cupping of lamina cribrosa can be significantly confounded by the myopic expansion of the neural canal. This may be related to higher glaucoma risk associated with myopia from decreased compliance and increased susceptibility to IOP-related damage of LC being pulled taut.

Long-term assessment of internal limiting membrane peeling for full-thickness macular hole using en face adaptive optics and conventional optical coherence tomography.

OBJECTIVE: To evaluate the long-term structural and microvascular retinal effects of internal limiting membrane peeling for full-thickness macular hole (FTMH) using en face adaptive optics optical coherence tomography (AO-OCT), conventional OCT, and OCT angiography (OCTA). DESIGN: Interventional case series. PARTICIPANTS: Patients with FTMH treated with vitrectomy, internal limiting membrane peeling, and gas tamponade. METHODS: Eleven eyes with FTMH that had at least 12 months of postoperative follow-up were enrolled in the study. En face AO-OCT was used to image the superficial retina in the peeled and nonpeeled areas. En face structural OCT was performed to image the inner retinal dimples (IRDs), macular thickness, and retinal nerve fibre layer (RNFL). En face OCTA was used to examine the integrity of the peripapillary nerve fibre layer (NFL) plexus. RESULTS: AO-OCT showed RFNL wrapping around the IRDs, and no obvious peripapillary NFL plexus dropout was seen with OCTA. Scattered hyper-reflective dots were observed on the surface of the peeled retina in all patients imaged with AO-OCT. No significant differences were found in IRD number (91.5 ± 24.4 versus 77.2 ± 14.7; P = 2.07), IRD proportionate area (8.36 ± 3.34 versus 7.53 ± 2.60; P = 0.159), or macular thickness between the 6- and 12-month (or greater) postoperative visits. CONCLUSION: IRDs do not to progress beyond 6 months postoperatively, and no obvious damage to RFNL and peripapillary NFL plexus was detected. Hyper-reflective dots on the surface of the retina suggestive of possible Müller cell reactive gliosis were identified with AO-OCT.

Müller cell degeneration and microglial dysfunction in the Alzheimer's retina.

Amyloid beta (Aß) deposits in the retina of the Alzheimer's disease (AD) eye may provide a useful diagnostic biomarker for AD. This study focused on the relationship of Aß with macroglia and microglia, as these glial cells are hypothesized to play important roles in homeostasis and clearance of Aß in the AD retina. Significantly higher Aß load was found in AD compared to controls, and specifically in the mid-peripheral region. AD retina showed significantly less immunoreactivity against glial fibrillary acidic protein (GFAP) and glutamine synthetase (GS) compared to control eyes. Immunoreactivity against ionized calcium binding adapter molecule-1 (IBA-1), a microglial marker, demonstrated a higher level of microgliosis in AD compared to control retina. Within AD retina, more IBA-1 immunoreactivity was present in the mid-peripheral retina, which contained more Aß than the central AD retina. GFAP co-localized rarely with Aß, while IBA-1 co-localized with Aß in more layers of control than AD donor retina. These results suggest that dysfunction of the Müller and microglial cells may be key features of the AD retina.

Numerical calibration method for a multiple spectrometer-based OCT system.

The present paper introduces a numerical calibration method for the easy and practical implementation of multiple spectrometer-based spectral-domain optical coherence tomography (SD-OCT) systems. To address the limitations of the traditional hardware-based spectrometer alignment across more than one spectrometer, we applied a numerical spectral calibration algorithm where the pixels corresponding to the same wavelength in each unit are identified through spatial- and frequency-domain interferometric signatures of a mirror sample. The utility of dual spectrometer-based SD-OCT imaging is demonstrated through in vivo retinal imaging at two different operation modes with high-speed and dual balanced acquisitions, respectively, in which the spectral alignment is critical to achieve improved retinal image data without any artifacts caused by misalignment of the spectrometers.

The effect of stiffened diabetic red blood cells on wall shear stress in a reconstructed 3D microaneurysm.

Blood flow within the vasculature of the retina has been found to influence the progression of diabetic retinopathy. In this research cell resolved blood flow simulations are used to study the pulsatile flow of whole blood through a segmented retinal microaneurysm. Images were collected using adaptive optics optical coherence tomography of the retina of a patient with diabetic retinopathy, and a sidewall (sacciform) microaneurysm was segmented from the volumetric data. The original microaneurysm neck width was varied to produce two additional aneurysm geometries in order to probe the influence of neck width on the transport of red blood cells and platelets into the aneurysm. Red blood cell membrane stiffness was also increased to resolve the impact of rigid red blood cells, as a result of diabetes, in blood flow. Wall shear stress and wall shear stress gradients were calculated throughout the aneurysm domains, and the quantification of the influence of the red blood cells is presented. Average wall shear stress and wall shear stress gradients increased due to the increase of red blood cell membrane stiffness. Stiffened red blood cells were also found to induce higher local wall shear stress and wall shear stress gradients as they passed through the leading and draining parental vessels. Stiffened red blood cells were found to penetrate the aneurysm sac more than healthy red blood cells, as well as decreasing the margination of platelets to the vessel walls of the parental vessel, which caused a decrease in platelet penetration into the aneurysm sac.

Clinical explainable differential diagnosis of polypoidal choroidal vasculopathy and age-related macular degeneration using deep learning.

BACKGROUND: This study aims to achieve an automatic differential diagnosis between two types of retinal pathologies with similar pathological features - Polypoidal choroidal vasculopathy (PCV) and wet age-related macular degeneration (AMD) from volumetric optical coherence tomography (OCT) images, and identify clinically-relevant pathological features, using an explainable deep-learning-based framework. METHODS: This is a retrospective study with data from a cross-sectional cohort. The OCT volume of 73 eyes from 59 patients was included in this study. Disease differentiation was achieved through single-B-scan-based classification followed by a volumetric probability prediction aggregation step. We compared different labeling strategies with and without identifying pathological B-scans within each OCT volume. Clinical interpretability was achieved through normalized aggregation of B-scan-based saliency maps followed by maximum-intensity-projection onto the en face plane. We derived the PCV score from the proposed differential diagnosis framework with different labeling strategies. The en face projection of saliency map was validated with the pathologies identified in Indocyanine green angiography (ICGA). RESULTS: Model trained with both labeling strategies achieved similar level differentiation power (>90%), with good correspondence between pathological features detected from the projected en face saliency map and ICGA. CONCLUSIONS: This study demonstrated the potential clinical application of non-invasive differential diagnosis using AI-driven OCT-based analysis, with minimal requirement of labeling efforts, along with clinical explainability achieved through automatically detected disease-related pathologies.

ADAPTIVE OPTICS OPTICAL COHERENCE TOMOGRAPHY IN A CASE OF ACUTE ZONAL OCCULT OUTER RETINOPATHY.

PURPOSE: To report a case of acute zonal occult outer retinopathy in which adaptive optics (AO) facilitated visualization of abnormal photoreceptors previously thought to be in an area of normal retina on conventional optical coherence tomography (OCT). METHODS: Case report. RESULTS: A 51-year-old woman presents with 11-month history of photopsias and scotoma in the temporal visual field of her left eye. Ocular imaging including fluorescein angiography, fundus autofluorescence and OCT suggested the diagnosis of acute zonal occult outer retinopathy in the left eye. Adaptive optics optical coherence tomography (AO-OCT) revealed photoreceptor abnormalities not previously identified in conventional OCT, in areas apparently normal on multimodal imaging. On enface and cross-sectional AO-OCT, round and evenly spaced hyperreflectivity corresponding to normal cone mosaic (Pattern 1) was adjacent to unevenly and disrupted cone hyperreflectivity (Pattern 2) and areas with hyporeflectivity or no cone reflectivity (Pattern 3). Cross-sectional AO-OCT of Patterns 2 and 3 also revealed attenuation of ellipsoid zone with loss of interdigitation zone. CONCLUSION: Adaptive optics OCT documented cone photoreceptors in finer details than conventional OCT and revealed early changes in a patient with acute zonal occult outer retinopathy, in an area of the retina thought to be normal on conventional multimodal imaging. These findings may provide important insight into pathogenesis and progression of the disease.

Quantitative Optical Coherence Tomography Angiography in Patients with Moyamoya Vasculopathy: A Pilot Study.

Moyamoya (MM) disease is a chronic cerebrovascular disease that can lead to progressive stenosis of the terminal portions of the internal carotid arteries and their proximal branches. We sought to investigate and quantify retinal vascular changes in patients with MM vasculopathy (MMV) using optical coherence tomography angiography (OCTA) compared to healthy controls. Our findings reveal retinal microvascular changes in patients with MMV and highlights the potential of OCTA imaging for the detection of subclinical retinal pathology.

Effect of optical coherence tomography and angiography sampling rate towards diabetic retinopathy severity classification.

Optical coherence tomography (OCT) and OCT angiography (OCT-A) may benefit the screening of diabetic retinopathy (DR). This study investigated the effect of laterally subsampling OCT/OCT-A en face scans by up to a factor of 8 when using deep neural networks for automated referable DR classification. There was no significant difference in the classification performance across all evaluation metrics when subsampling up to a factor of 3, and only minimal differences up to a factor of 8. Our findings suggest that OCT/OCT-A can reduce the number of samples (and hence the acquisition time) for a volume for a given field of view on the retina that is acquired for rDR classification.

Wavefront sensor-less adaptive optics using deep reinforcement learning.

Image degradation due to wavefront aberrations can be corrected with adaptive optics (AO). In a typical AO configuration, the aberrations are measured directly using a Shack-Hartmann wavefront sensor and corrected with a deformable mirror in order to attain diffraction limited performance for the main imaging system. Wavefront sensor-less adaptive optics (SAO) uses the image information directly to determine the aberrations and provide guidance for shaping the deformable mirror, often iteratively. In this report, we present a Deep Reinforcement Learning (DRL) approach for SAO correction using a custom-built fluorescence confocal scanning laser microscope. The experimental results demonstrate the improved performance of the DRL approach relative to a Zernike Mode Hill Climbing algorithm for SAO.

LF-UNet - A novel anatomical-aware dual-branch cascaded deep neural network for segmentation of retinal layers and fluid from optical coherence tomography images.

Computer-assistant diagnosis of retinal disease relies heavily on the accurate detection of retinal boundaries and other pathological features such as fluid accumulation. Optical coherence tomography (OCT) is a non-invasive ophthalmological imaging technique that has become a standard modality in the field due to its ability to detect cross-sectional retinal pathologies at the micrometer level. In this work, we presented a novel framework to achieve simultaneous retinal layers and fluid segmentation. A dual-branch deep neural network, termed LF-UNet, was proposed which combines the expansion path of the U-Net and original fully convolutional network, with a dilated network. In addition, we introduced a cascaded network framework to include the anatomical awareness embedded in the volumetric image. Cross validation experiments showed that the proposed LF-UNet has superior performance compared to the state-of-the-art methods, and that incorporating the relative positional map structural prior information could further improve the performance regardless of the network. The generalizability of the proposed network was demonstrated on an independent dataset acquired from the same types of device with different field of view, or images acquired from different device.