Optic Cup Research Articles

A rare presentation of saccular aneurysm at junction of middle carotid artery and internal carotid artery mimicking the normal tension glaucoma

Acquired (pathologic) excavation of the optic cup is not always due to glaucoma. Ophthalmological signs of pathological disc cupping have been recognised in patients with normal intraocular pressures and with optic atrophy of various causes including ischaemic and compressive optic neuropathy, optic neuritis and trauma. Intracranial lesions have been reported to mimic the clinical presentation of glaucomatous optic disc changes and have also resulted in misdiagnosis. Optic atrophy caused by intracranial lesions shows pallor more than cupping. The macular nasal–temporal ratio compares the nasal and temporal thickness of the macular ganglion cell and inner plexiform layer and can be used to differentiate between compressive and non-compressive lesions as depicted in this case. This case report also suggests the importance of different imaging modalities in diagnosing compressive lesions and differentiating them from similar conditions.

Multi-dimensional dense attention network for pixel-wise segmentation of optic disc in colour fundus images.

Segmentation of retinal fragments like blood vessels, Optic Disc (OD), and Optic Cup (OC) enables the early detection of different retinal pathologies like Diabetic Retinopathy (DR), Glaucoma, etc. Accurate segmentation of OD remains challenging due to blurred boundaries, vessel occlusion, and other distractions and limitations. These days, deep learning is rapidly progressing in the segmentation of image pixels, and a number of network models have been proposed for end-to-end image segmentation. However, there are still certain limitations, such as limited ability to represent context, inadequate feature processing, limited receptive field, etc., which lead to the loss of local details and blurred boundaries. A multi-dimensional dense attention network, or MDDA-Net, is proposed for pixel-wise segmentation of OD in retinal images in order to address the aforementioned issues and produce more thorough and accurate segmentation results. In order to acquire powerful contexts when faced with limited context representation capabilities, a dense attention block is recommended. A triple-attention (TA) block is introduced in order to better extract the relationship between pixels and obtain more comprehensive information, with the goal of addressing the insufficient feature processing. In the meantime, a multi-scale context fusion (MCF) is suggested for acquiring the multi-scale contexts through context improvement. Specifically, we provide a thorough assessment of the suggested approach on three difficult datasets. In the MESSIDOR and ORIGA data sets, the suggested MDDA-NET approach obtains accuracy levels of 99.28% and 98.95%, respectively. The experimental results show that the MDDA-Net can obtain better performance than state-of-the-art deep learning models under the same environmental conditions.

Linking physiology and demographics, non-ocular pathology and pharmaceutical drug use to standard OCT measures of the inner retina: The PPP project.

To assess the associations between physiology and demographics, non-ocular pathology and pharmaceutical drug use against peri-papillary retinal nerve fibre layer thickness (pRNFL T) and other optical coherence tomography (OCT) inner retinal measures in normal, healthy eyes. A retrospective, cross-sectional study of 705 consecutive participants with bilateral normal, healthy optic nerves and maculae. PRNFL Ts, vertical cup/disc ratio (CDR), cup volume and macular ganglion cell layer-inner plexiform layer (GCL-IPL) Ts were extracted from Cirrus OCT scans, then regressed against predictor variables of participants' physiology and demographics (eye laterality, refraction, intraocular pressure [IOP], age, sex, race/ethnicity, etc.) and non-ocular pathology and pharmaceutical drug use according to the World Health Organisation classifications. Associations were assessed for statistical significance (p < 0.05) and clinical significance (|β| > 95% limits of agreement for repeated measures). A multitude of non-ocular pathology and pharmaceutical drug use were statistically and clinically significantly associated with deviations in standard OCT inner retinal measures, exceeding the magnitude of other factors such as age, IOP and race/ethnicity. Thinner inner retina and larger optic nerve cup measures were linked to use of systemic corticosteroids, sex hormones/modulators, presence of vasomotor/allergic rhinitis and other diseases and drugs (up to -29.3 [-49.88, -8.72] μm pRNFL T, 0.31 [0.07, 0.54] vertical CDR, 0.29 [0.03, 0.54] mm3 cup volume and -10.18 [-16.62, -3.74] μm macular GCL-IPL T; all p < 0.05). Thicker inner retina and smaller optic nerve cup measures were diffusely associated with use of antineoplastic agents, presence of liver or urinary diseases and other diseases and drugs (up to 67.12 [64.92, 69.31] μm pRNFL T, -0.31 [-0.53, -0.09] vertical CDR, -0.06 [-0.11, 0] mm3 cup volume and 28.84 [14.51, 43.17] μm macular GCL-IPL T; all p < 0.05). There are a multitude of systemic diseases and drugs associated with altered OCT inner retinal measures, with magnitudes far exceeding those of other factors such as age, IOP and race/ethnicity. These systemic factors should at least be considered during OCT assessments to ensure precise interpretation of normal versus pathological inner retinal health.

LC-MANet: Location-constrained joint optic disc and cup segmentation via multiplex aggregation network

Many early ophthalmology-related diseases can be detected through fundus images. The cup-to-disc ratio (CDR) is an important criterion for the early screening and diagnosis of glaucoma. However, accurately calculating it is a challenging task primarily due to blurred boundaries and the physiological structure of the fundus. To alleviate these issues, this paper designs a location-constrained joint optic disc (OD) and optic cup (OC) segmentation method using the multiplex aggregation network (LC-MANet). This method incorporates independent segmentation and joint segmentation within a coarse-to-fine framework. In the independent segmentation stage, this paper utilizes the initial OD and OC as prior location auto-context information to constrain the joint segmentation of OD and OC. The proposed multiplex aggregation network combines features from the corresponding layer and across layers to capture global and local information. This paper employs a multi-channel fusion strategy in image preprocessing to suppress vascular interference in OD independent segmentation. To emphasize the superiority of our method, it is important to highlight the significant number of test images used in the evaluation. Our experiments are conducted on three public datasets, namely RIM-ONE (60 images), Drishti-GS (51 images), and REFUGE (400 images). Experimental results demonstrate that our method outperforms most others in terms of Dice Coefficient and absolute error. The accuracy of glaucoma screening achieved by our proposed method for the Drishti-GS, REFUGE, and RIM-ONE-r3 datasets is 0.9216, 0.9600, and 0.9000, respectively. The proposed framework successfully designs a multiplex aggregation network for a coarse-to-fine joint segmentation model and achieves state-of-the-art performance in OD and OC segmentation. Furthermore, it can be applied to other medical image segmentation tasks.

Optic cup morphology associated with glaucomatous damage: Findings from the Primary Open-Angle African American Glaucoma Genetics (POAAGG) Study

PurposeWhile it has been well established that advanced glaucoma is associated with a large cup-to-disc ratio (CDR), it is not known if the shape of the cup, particularly excavated cups with expanded lower portions (bean-pot cups), play any additional role in glaucomatous damage. We investigated this among individuals of African ancestry, a population that is more vulnerable to glaucoma than any other ethnic group. DesignCase-control study Methods SettingInstitutional (University of Pennsylvania) Subjects3,255 eyes from 1,734 glaucoma cases from the Primary Open-Angle African American Glaucoma Genetics (POAAGG) study. ProcedureTwo graders independently assessed quantitative and qualitative aspects of the optic cup, with any discrepancies adjudicated by an ophthalmologist. The predominant cup shape (>50 %) was chosen in cases in which features of two or more cup shapes were present in the same eye. Comparisons of demographic and ocular characteristics among three cup shape groups (conical, cylindrical, and bean-pot) performed using generalized linear models, and generalized estimated equations applied to account for inter-eye correlation. Main Outcome MeasuresQualitative features of cup shape and phenotypic traits, in conjunction with demographic and genetic information. ResultsOf 3,255 eyes, a total of 1,339 (41.1 %) exhibit a conical cup shape, 1,470 (45.2 %) have a cylindrical cup shape, and 446 (13.7 %) display a bean-pot cup shape. Compared to other cup morphology, bean-pot cups are significantly associated with lower MD, larger CDR, higher IOP, thinner RNFL, and worse VA in logMAR (all p < 0.001). Genetic analysis does not show any association between various genetic variants and cup shape. Factors independently predictive of bean-pot cupping include younger age at diagnosis (aOR 0.96 per 1 year increase in age of enrollment, p < 0.0001), CDR (adjusted odds ratio (aOR) 1.87, p < 0.0001), and the presence of certain optic disc features, including visible pores in the LC (aOR 2.76, p < 0.0001), nasalization of vessels (aOR 2.64, p < 0.0001), and vessel bayonetting (aOR 2.94, p < 0.0001). ConclusionThis study shows the clinical significance of different cup shapes in glaucoma in an African ancestry population and suggests that bean-pot cups are associated with the most severe glaucomatous damage, independent of cup-disc ratio. This association should be considered when determining prognosis following glaucoma interventions.

Progression to bilaterality in unilateral primary congenital glaucoma

PurposeTo evaluate the incidence of rise in intraocular pressure (IOP) in fellow eyes of patients with unilateral primary congenital glaucoma (PCG) and to identify risk factors for IOP increase over long-term follow-up. MethodsThe medical records of unilateral PCG patients who had completed at least 5 years of follow-up were reviewed retrospectively. The incidence of developing ocular hypertension / glaucoma in fellow eyes was analyzed. Fellow eye progressors were those which showed an increase in optic nerve cupping by at least 0.2 since the first presentation or had IOP of >21 mm Hg on two occasions. The risk factors for progression that were analyzed included IOP, visual acuity, axial length, central corneal thickness (CCT), corneal diameters (CD), presence or absence of angle dysgenesis on high-resolution anterior segment optical coherence tomography (AS-OCT), and morphology of aqueous outflow pathways. ResultsAfter a median follow-up of 8.2 years (range, 5-25.5) progression to bilateral disease was found in 17 of 54 patients (32%), of whom 8 (15%) developed ocular hypertension and 9 (17%) developed glaucoma in the fellow eye. Among the unaffected fellow eyes, those with a larger CD (>12 mm), measured after at least 5 years’ follow-up, were ten times more likely to progress (P = 0.01; OR = 9.5 [95% CI, 1.7-54.3]). The presence of a patent supraciliary channel was significantly more frequently associated in fellow eyes compared with affected eyes on AS-OCT (OR = 1.4 [95% CI, 0.46-4.68]). ConclusionsOne-third of unaffected fellow eyes of unilateral PCG eventually progress over time, most often after 5 years. Larger CD at follow-up in the fellow eye is strongly predictive for progression.

Optic Disc Cupping in Neuromyelitis Optica Spectrum Disorder, Myelin Oligodendrocyte Glycoprotein Antibody-Associated Disease, and Multiple Sclerosis and Its Relationship With Optical Coherence Tomography Parameters: A Multicenter Study

Background: Although cupping of the optic nerve is classically a sign of glaucomatous optic neuropathy, it has been shown that cupping can sometimes occur after an episode of optic neuritis (ON). The purpose of this study was to compare cupping in patients after ON from multiple sclerosis (MS), neuromyelitis optica spectrum disorder (NMOSD), or myelin oligodendrocyte glycoprotein antibody-associated disease (MOGAD) and to investigate the relationship between cupping and retinal nerve fiber layer (RNFL) and ganglion cell complex (GCC) thinning. Methods: This was a retrospective cohort involving patients (≥18 years) with ON from 3 institutions. Patients were eligible if they had optical coherence tomography (Cirrus, OCT) performed ≥6 months after a single unilateral ON. The amount of thinning and cupping was estimated from the difference in the OCT parameters between affected and unaffected eyes. Univariable and multivariable regressions were used to investigate the relationship between cupping and ON etiology. Pearson correlation was used to investigate the relationship between cupping and RNFL and GCC. Results: Eighty-six subjects (MS: 35, NMOSD: 26, and MOGAD: 25) were included. There was no significant difference in gender and race between the groups, and most patients (86.1%) were female. Patients with NMOSD were significantly older than patients with MS or MOGAD (P = 0.002). In the univariate model, cupping was significantly higher in the NMOSD group (P = 0.017); however, after adjusting for age, GCC, and RNFL of the affected eye, the difference was no longer statistically significant (P = 0.949). The correlation between cupping asymmetry and RNFL and GCC of the affected eye was inversely strong in patients with MS (R = −0.60 and R = −0.64, respectively), inversely moderate in patients with MOGAD (R = −0.34 and R = −0.40, respectively), and weak in patients with NMOSD (R = −0.03 and R = −0.17, respectively). Conclusions: Our results demonstrated that cupping after ON is correlated with RNFL and GCC thinning; although cupping was overall greater in the NMOSD group, once adjusted for age, RNFL, and GCC, it did not differ among patients with MS, NMOSD, and MOGAD.

Automated Optic Nerve Head Hemoglobin Measurements versus General Ophthalmologists Evaluation to Differentiate Glaucomatous from Large Physiological Cupping: A Diagnostic Performance Comparative Study.

The aim of this study is to compare the diagnostic performance in differentiating patients with glaucoma from those with presumed large physiological optic disc cupping (LPC), using optic nerve head hemoglobin levels (ONH Hb), as a screening method, versus the evaluation of general ophthalmologists. Twenty general ophthalmologists evaluated PowerPoint images of 40 patients with glaucoma and 40 presenting LPC. Presentation of patient's exams were distributed as follows: Group 1 (GI): color retinography (CR), Group 2 (GII): CR + visual field (VF), Group 3 (GIII): CR + optical coherence tomography (OCT), Group 4 (GIV): CR + VF + OCT. The Laguna ONhE software was used to estimate ONH Hb based on CR. Main outcomes were the comparison of sensitivity and accuracy between general ophthalmologists' evaluation and the glaucoma discriminant function (GDF) index from Laguna ONhE and also the agreement between examiners (Kappa statistics). Laguna ONhE GDF index demonstrated higher sensitivity values (GI- 90%; GII-90%; GIII-100%; GIV-100%) comparing to all groups (GI-59%; GII-86.5%; GIII-86.5%; GIV-68.5%). In GI, in which it was observed the worst accuracy result (64.8%), we found 75% for GDF. In GII, the accuracy was 81.3% and we found 55% for GDF. The highest agreement was in GII (Kappa=0.63; 95% CI=0.53-0.72), and the lowest in GI (Kappa=0.30; 95% CI=0.20-0.39). Laguna ONhE software, a low-cost and non-invasive method, showed good sensitivity and great utility as a screening method in differentiating patients with glaucoma from those with LPC, compared with evaluation of general ophthalmologists.

Automated analysis for glaucoma screening of retinal videos acquired with smartphone-based ophthalmoscope

Widespread screening is crucial for the early diagnosis and treatment of glaucoma, the leading cause of visual impairment and blindness. The development of portable technologies, such as smartphone-based ophthalmoscopes, able to image the optical nerve head, represents a resource for large-scale glaucoma screening. Indeed, they consist of an optical device attached to a common smartphone, making the overall device cheap and easy to use. Automated analyses able to assist clinicians are crucial for fast, reproducible, and accurate screening, and can promote its diffusion making it possible even for non-expert ophthalmologists. Images acquired with smartphone ophthalmoscopes differ from that acquired with a fundus camera for the field of view, noise, colour, and the presence of pupil, iris and eyelid. Consequently, algorithms specifically designed for this type of image need to be developed.We propose a completely automated analysis of retinal video acquired with smartphone ophthalmoscopy. The proposed algorithm, based on convolutional neural networks, selects the most relevant frames in the video, segments both optic disc and cup, and computes the cup-to-disc ratio. The developed networks were partially trained on images from a publicly available fundus camera datasets, modified through an original procedure to be statistically equal to the ones acquired with a smartphone ophthalmoscope. The proposed algorithm achieves good results in images acquired from healthy and pathological subjects. Indeed, an accuracy ≥95 % was obtained for both disc and cup segmentation and the computed cup-to-disc ratios denote good agreement with manual analysis (mean difference 9 %), allowing a substantial differentiation between healthy and pathological subjects.

GREnet: Gradually REcurrent Network With Curriculum Learning for 2-D Medical Image Segmentation.

Medical image segmentation is a vital stage in medical image analysis. Numerous deep-learning methods are booming to improve the performance of 2-D medical image segmentation, owing to the fast growth of the convolutional neural network. Generally, the manually defined ground truth is utilized directly to supervise models in the training phase. However, direct supervision of the ground truth often results in ambiguity and distractors as complex challenges appear simultaneously. To alleviate this issue, we propose a gradually recurrent network with curriculum learning, which is supervised by gradual information of the ground truth. The whole model is composed of two independent networks. One is the segmentation network denoted as GREnet, which formulates 2-D medical image segmentation as a temporal task supervised by pixel-level gradual curricula in the training phase. The other is a curriculum-mining network. To a certain degree, the curriculum-mining network provides curricula with an increasing difficulty in the ground truth of the training set by progressively uncovering hard-to-segmentation pixels via a data-driven manner. Given that segmentation is a pixel-level dense-prediction challenge, to the best of our knowledge, this is the first work to function 2-D medical image segmentation as a temporal task with pixel-level curriculum learning. In GREnet, the naive UNet is adopted as the backbone, while ConvLSTM is used to establish the temporal link between gradual curricula. In the curriculum-mining network, UNet++ supplemented by transformer is designed to deliver curricula through the outputs of the modified UNet++ at different layers. Experimental results have demonstrated the effectiveness of GREnet on seven datasets, i.e., three lesion segmentation datasets in dermoscopic images, an optic disc and cup segmentation dataset and a blood vessel segmentation dataset in retinal images, a breast lesion segmentation dataset in ultrasound images, and a lung segmentation dataset in computed tomography (CT).

Research on segmentation model of optic disc and optic cup in fundus

BackgroundGlaucoma is a worldwide eye disease that can cause irreversible vision loss. Early detection of glaucoma is important to reduce vision loss, and retinal fundus image examination is one of the most commonly used solutions for glaucoma diagnosis due to its low cost. Clinically, the cup-disc ratio of fundus images is an important indicator for glaucoma diagnosis. In recent years, there have been an increasing number of algorithms for segmentation and recognition of the optic disc (OD) and optic cup (OC), but these algorithms generally have poor universality, segmentation performance, and segmentation accuracy.MethodsBy improving the YOLOv8 algorithm for segmentation of OD and OC. Firstly, a set of algorithms was designed to adapt the REFUGE dataset’s result images to the input format of the YOLOv8 algorithm. Secondly, in order to improve segmentation performance, the network structure of YOLOv8 was improved, including adding a ROI (Region of Interest) module, modifying the bounding box regression loss function from CIOU to Focal-EIoU. Finally, by training and testing the REFUGE dataset, the improved YOLOv8 algorithm was evaluated.ResultsThe experimental results show that the improved YOLOv8 algorithm achieves good segmentation performance on the REFUGE dataset. In the OD and OC segmentation tests, the F1 score is 0.999.ConclusionsWe improved the YOLOv8 algorithm and applied the improved model to the segmentation task of OD and OC in fundus images. The results show that our improved model is far superior to the mainstream U-Net model in terms of training speed, segmentation performance, and segmentation accuracy.

Increased Netrin downstream of overactive Hedgehog signaling disrupts optic fissure formation.

Uveal coloboma, a developmental eye defect, is caused by failed development of the optic fissure, a ventral structure in the optic stalk and cup where axons exit the eye and vasculature enters. The Hedgehog (Hh) signaling pathway regulates optic fissure development: loss-of-function mutations in the Hh receptor ptch2 produce overactive Hh signaling and can result in coloboma. We previously proposed a model where overactive Hh signaling disrupts optic fissure formation by upregulating transcriptional targets acting both cell- and non-cell-autonomously. Here, we examine the Netrin family of secreted ligands as candidate Hh target genes. We find multiple Netrin ligands upregulated in the zebrafish ptch2 mutant during optic fissure development. Using a gain-of-function approach to overexpress Netrin in a spatiotemporally specific manner, we find that netrin1a or netrin1b overexpression is sufficient to cause coloboma and disrupt wild-type optic fissure formation. We used loss-of-function alleles, CRISPR/Cas9 mutagenesis, and morpholino knockdown to test if loss of Netrin can rescue coloboma in the ptch2 mutant: loss of netrin genes does not rescue the ptch2 mutant phenotype. These results suggest that Netrin is sufficient but not required to disrupt optic fissure formation downstream of overactive Hh signaling in the ptch2 mutant.

MA‐ResUNet: Multi‐attention optic cup and optic disc segmentation based on improved U‐Net

AbstractGlaucoma poses a significant threat to vision, capable of causing irreversible damage and, in severe instances, leading to permanent blindness. Accurate optic cup (OC) and optic disc (OD) segmentation are essential in glaucoma screening. In this study, a novel OC and OD segmentation approach is proposed. Based on U‐Net, it is optimized by introducing cardinality dimensions. Moreover, attention gates are implemented to reinforce salient features while suppressing irrelevant information. Additionally, a convolutional block attention module (CBAM) is integrated into the decoder segment. This fusion hones in on effective information in both channel and spatial dimensions. Meanwhile, an image processing procedure is proposed for image normalization and enhancement. All of these increase the accuracy of the model. This model is evaluated on the ORIGA and REFUGE datasets, demonstrating the model's superiority in OC and OD segmentation compared to the state‐of‐the‐art methods. Additionally, after the proposed image processing, cup‐to‐disc ratio (CDR) prediction on a batch of 155 in‐house fundus images yields an absolute CDR error of 0.099, which is reduced by 0.04 compared to the case where only conventional processing was performed.

Development and characterization of a chronic high intraocular pressure model in New Zealand white rabbits for glaucoma research

Glaucoma is a neurodegenerative disease characterized by visual field loss associated with optic nerve damage and ocular hypertension. The biological basis for the elevated intraocular pressure (IOP) is largely unknown, such that lowering the IOP is currently the only established treatment. Several animal models have been developed to elucidate the mechanism underlying the increased IOP and for use in drug discovery research, but their utility is often limited by the occurrence of severe intraocular inflammation and by technical challenges. In this study, we developed a rabbit glaucoma model that does not require experimental disease induction. Rabbits were chosen as the model because their eyeballs are similar in size to those of humans, and they are easy to breed.By crossing rabbit strains with inherited glaucoma, as indicated by obvious buphthalmos, we produced a strain that exhibits ocular hypertension. The IOP of the Ocular Hypertension (OH) rabbits was significantly higher than that of the wild type (WT; normal New Zealand white rabbits) from the age of 3 weeks to at least 22 weeks. The significantly larger corneal diameter of the OH rabbits indicated ocular enlargement, whereas there was no significant difference in corneal thickness compared with WT rabbits. Anterior segment ocular coherence tomography and gonioscopic observations revealed an open angle in the OH rabbits. Hematoxylin and eosin (HE) staining together with Masson's trichrome staining showed abnormal collagen accumulation in the angle of the OH rabbit's eyes. Furthermore, aqueous humor (AH) outflow imaging following an intravitreal injection of a fluorescent probe into the anterior chamber for tissue-section analysis revealed retention of the probe in the area of collagen deposition in the OH eyes. The OH rabbits also had a time-dependent increase in the cup/disc ratio.In conclusion, investigations using our newly developed rabbit model of open-angle ocular hypertension showed that abnormal accumulation of extracellular matrix at the angle increased AH outflow resistance in the conventional outflow pathway, leading to a high IOP. Furthermore, the OH rabbits exhibited glaucomatous optic disc cupping over time. These findings suggest the utility of the OH rabbits as a model for open-angle glaucoma (OAG).

Assessing Agreement of Clinical Estimation of Vertical Optic Disc Cupping against Retcam Assessment in the Premature Neonate and Prospective Observation for Changes

Aim: To assess agreement between binocular assessment of optic disc cupping and objective evaluation with RetCam imaging in premature infants. To look for difference in changes observed in disc cupping between different birthweight groups and effect of retinopathy of prematurity, intraventricular hemorrhage and sepsis. Methods: A cohort of premature infants were examined prospectively. At Timepoint I (31 – 36 weeks), the vertical optic disc cupping(vCDR) was assessed clinically through a 28D lens. Two RetCam fundus images centred on the optic discs were taken. A blinded assessor measured the vCDR and the average was calculated. This was repeated at Timepoint 2(37– 40 weeks). Exclusion criteria included IOP &gt;21mmHg, abnormality in cornea, enlarged cornea size (&gt;10.0mm) and abnormal eye. Consistency between the 2 methods was assessed with intraclass correlation coefficient (ICC). Bland-Altmann plots were used for agreement analysis. Results: In total, 126 eyes (n= 63 infants) were examined, 504 images captured and assessed. The average vCDR by clinician was 0.30(SD:0.1) and by RetCam 0.32(SD:0.1). The ICC showed moderate correlation however, Bland-Altman plot showed a wide 95% limits of agreement (-0.24, 0.26). Paired t-test did not show significant change in vCDR between the time-points for infants in different birthweight groups but trend of change were identical for both methods. Retinopathy of prematurity, intraventricular hemorrhage and sepsis were not associated with changes in cupping in this cohort. Conclusion: Optic disc cupping with clinical estimation is not interchangeable with RetCam values but showed identical trend of change. Mean optic disc vertical cupping in this population was 0.3 at term.

Entropy and distance-guided super self-ensembling for optic disc and cup segmentation.

Segmenting the optic disc (OD) and optic cup (OC) is crucial to accurately detect changes in glaucoma progression in the elderly. Recently, various convolutional neural networks have emerged to deal with OD and OC segmentation. Due to the domain shift problem, achieving high-accuracy segmentation of OD and OC from different domain datasets remains highly challenging. Unsupervised domain adaptation has taken extensive focus as a way to address this problem. In this work, we propose a novel unsupervised domain adaptation method, called entropy and distance-guided super self-ensembling (EDSS), to enhance the segmentation performance of OD and OC. EDSS is comprised of two self-ensembling models, and the Gaussian noise is added to the weights of the whole network. Firstly, we design a super self-ensembling (SSE) framework, which can combine two self-ensembling to learn more discriminative information about images. Secondly, we propose a novel exponential moving average with Gaussian noise (G-EMA) to enhance the robustness of the self-ensembling framework. Thirdly, we propose an effective multi-information fusion strategy (MFS) to guide and improve the domain adaptation process. We evaluate the proposed EDSS on two public fundus image datasets RIGA+ and REFUGE. Large amounts of experimental results demonstrate that the proposed EDSS outperforms state-of-the-art segmentation methods with unsupervised domain adaptation, e.g., the Dicemean score on three test sub-datasets of RIGA+ are 0.8442, 0.8772 and 0.9006, respectively, and the Dicemean score on the REFUGE dataset is 0.9154.

Characteristic deviations of the optic disc and macula in optic nerve hypoplasia based on OCT.

The purpose of this study was to evaluate the optic disc and macula in a large cohort of patients with different severity of optic nerve hypoplasia (ONH) using high-resolution spectral domain optical coherence tomography (SD-OCT). In total, 36 patients (52 ONH eyes and 17 fellow eyes in unilateral cases) and 45 healthy right eyes from 45 controls were evaluated. All patients underwent an examination to confirm the diagnosis. SD-OCT images of the disc and macula were obtained and analysed both quantitatively and qualitatively. OCT in ONH eyes demonstrated a shorter disc diameter (1061 ± 375 μm vs. 1751 ± 221 μm, p < 0.001), shallower mean cup depth (427 ± 171 μm vs. 551 ± 152 μm, p = 0.01), thinner ganglion cell complex (GCC) perifoveally (47.3 ± 13.0 μm, 60.8 ± 6.0 μm, p < 0.001) and reduced foveal depth (61 ± 36 μm, 119 ± 19 μm, p < 0.001) compared to control eyes. Qualitative analysis showed that 1/3rd of ONH eyes lacked signs of an optic cup, and 2/3rd had reduced or no sign of a foveal pit. Fellow eyes had shorter disc diameter (1446 ± 404 μm vs. 1751 ± 221 μm, p = 0.004) and reduced foveal depth (93 ± 27 μm vs. 119 ± 19 μm, p < 0.001) but similar GCC thickness (60.8 ± 7.1 μm vs. 60.8 ± 6.0 μm, p = 0.738) compared to controls. Disc diameter showed the best correlation with visual acuity in ONH eyes (ρ = 0.517, p < 0.001). ONH eyes have reduced GCC thickness and reduced or no foveal pit. Fellow eyes in presumed unilateral cases have a smaller disc diameter and reduced foveal depth compared to controls, suggesting the possibility of subclinical/mild disease. However, GCC thickness was normal. The correlation between structure and visual function is not always straightforward.

SAMCF: Adaptive global style alignment and multi-color spaces fusion for joint optic cup and disc segmentation

The optic cup (OC) and optic disc (OD) are two critical structures in retinal fundus images, and their relative positions and sizes are essential for effectively diagnosing eye diseases. With the success of deep learning in computer vision, deep learning-based segmentation models have been widely used for joint optic cup and disc segmentation. However, there are three prominent issues that impact the segmentation performance. First, significant differences among datasets collecting from various institutions, protocols, and devices lead to performance degradation of models. Second, we find that images with only RGB information struggle to counteract the interference caused by brightness variations, affecting color representation capability. Finally, existing methods typically ignored the edge perception, facing the challenges in obtaining clear and smooth edge segmentation results. To address these drawbacks, we propose a novel framework based on Style Alignment and Multi-Color Fusion (SAMCF) for joint OC and OD segmentation. Initially, we introduce a domain generalization method to generate uniformly styled images without damaged image content for mitigating domain shift issues. Next, based on multiple color spaces, we propose a feature extraction and fusion network aiming to handle brightness variation interference and improve color representation capability. Lastly, an edge aware loss is designed to generate fine edge segmentation results. Our experiments conducted on three public datasets, DGS, RIM, and REFUGE, demonstrate that our proposed SAMCF achieves superior performance to existing state-of-the-art methods. Moreover, SAMCF exhibits remarkable generalization ability across multiple retinal fundus image datasets, showcasing its outstanding generality.

Risk factors of non-arteritic anterior ischaemic optic neuropathy and central retinal artery occlusion.

To investigate the difference in risk factors between non-arteritic anterior ischaemic optic neuropathy (NAION) and central retinal artery occlusion (CRAO) and develop a predictive diagnostic nomogram. The study included 37 patients with monocular NAION, 20 with monocular CRAO, and 24 with hypertension. Gender, age, and systemic diseases were recorded. Blood routine, lipids, hemorheology, carotid and brachial artery doppler ultrasound, and echocardiography were collected. The optic disc area, cup area, and cup-to-disc ratio (C/D) of the unaffected eye in the NAION and CRAO group and the right eye in the hypertension group were measured. The carotid artery intimal medial thickness (C-IMT) of the affected side of the CRAO group was thicker (P=0.039) and its flow-mediated dilation (FMD) was lower (P=0.049) than the NAION group. Compared with hypertension patients, NAION patients had higher whole blood reduced viscosity low-shear (WBRV-L) and erythrocyte aggregation index (EAI; P=0.045, 0.037), and CRAO patients had higher index of rigidity of erythrocyte (IR) and erythrocyte deformation index (EDI; P=0.004, 0.001). The optic cup and the C/D of the NAION group were smaller than the other two groups (P<0.0001). The diagnostic prediction model showed high diagnostic specificity (83.7%) and sensitivity (85.6%), which was highly related to hypertension, the C-IMT of the affected side, FMD, platelet (PLT), EAI, and C/D. CRAO patients show thicker C-IMT and worse endothelial function than NAION. NAION and CRAO may be related to abnormal hemorheology. A small cup and small C/D may be involved in NAION. The diagnostic nomogram can be used to preliminarily identify NAION and CRAO.

JOINEDTrans: Prior guided multi-task transformer for joint optic disc/cup segmentation and fovea detection

Deep learning-based image segmentation and detection models have largely improved the efficiency of analyzing retinal landmarks such as optic disc (OD), optic cup (OC), and fovea. However, factors including ophthalmic disease-related lesions and low image quality issues may severely complicate automatic OD/OC segmentation and fovea detection. Most existing works treat the identification of each landmark as a single task, and take into account no prior information. To address these issues, we propose a prior guided multi-task transformer framework for joint OD/OC segmentation and fovea detection, named JOINEDTrans. JOINEDTrans effectively combines various spatial features of the fundus images, relieving the structural distortions induced by lesions and other imaging issues. It contains a segmentation branch and a detection branch. To be noted, we employ an encoder with prior-learning in a vessel segmentation task to effectively exploit the positional relationship among vessel, OD/OC, and fovea, successfully incorporating spatial prior into the proposed JOINEDTrans framework. There are a coarse stage and a fine stage in JOINEDTrans. In the coarse stage, OD/OC coarse segmentation and fovea heatmap localization are obtained through a joint segmentation and detection module. In the fine stage, we crop regions of interest for subsequent refinement and use predictions obtained in the coarse stage to provide additional information for better performance and faster convergence. Experimental results demonstrate that JOINEDTrans outperforms existing state-of-the-art methods on the publicly available GAMMA, REFUGE, and PALM fundus image datasets. We make our code available at https://github.com/HuaqingHe/JOINEDTrans.