Stitched vision transformer for age-related macular degeneration detection using retinal optical coherence tomography images.

Age-related macular degeneration (AMD) is an eye disease that leads to the deterioration of the central vision area of the eye and can gradually result in vision loss in elderly individuals. Early identification of this disease can significantly impact patient treatment outcomes. Furthermore, given the increasing elderly population globally, the importance of automated methods for rapidly monitoring at-risk individuals and accurately diagnosing AMD is growing daily. One standard method for diagnosing AMD is using optical coherence tomography (OCT) images as a non-invasive imaging technology. In recent years, numerous deep neural networks have been proposed for the classification of OCT images. Utilizing pre-trained neural networks can speed up model deployment in related tasks without compromising accuracy. However, most previous methods overlook the feasibility of leveraging pre-existing trained networks to search for an optimal architecture for AMD staging on a new target dataset. In this study, our objective was to achieve an optimal architecture in the efficiency-accuracy trade-off for classifying retinal OCT images. To this end, we employed pre-trained medical vision transformer (MedViT) models. MedViT combines convolutional and transformer neural networks, explicitly designed for medical image classification. Our approach involved pre-training two distinct MedViT models on a source dataset with labels identical to those in the target dataset. This pre-training was conducted in a supervised manner. Subsequently, we evaluated the performance of the pre-trained MedViT models for classifying retinal OCT images from the target Noor Eye Hospital (NEH) dataset into the normal, drusen, and choroidal neovascularization (CNV) classes in zero-shot settings and through five-fold cross-validation. Then, we proposed a stitching approach to search for an optimal model from two MedViT family models. The proposed stitching method is an efficient architecture search algorithm known as stitchable neural networks. Stitchable neural networks create a candidate model in search space for each pair of stitchable layers by inserting a linear layer between them. A pair of stitchable layers consists of layers, each selected from one input model. While stitchable neural networks had previously been tested on more extensive and general datasets, this study demonstrated that stitching networks could also be helpful in smaller medical datasets. The results of this approach indicate that when pre-trained models were available for OCT images from another dataset, it was possible to achieve a model in 100 epochs with an accuracy of over 94.9% in classifying images from the NEH dataset. The results of this study demonstrate the efficacy of stitchable neural networks as a fine-tuning method for OCT image classification. This approach not only leads to higher accuracy but also considers architecture optimization at a reasonable computational cost.

Deep Neural Networks for Automated Outer Plexiform Layer Subsidence Detection on Retinal OCT of Patients With Intermediate AMD.

Purpose: The subsidence of the outer plexiform layer (OPL) is an important imaging biomarker on optical coherence tomography (OCT) associated with early outer retinal atrophy and a risk factor for progression to geographic atrophy in patients with intermediate age-related macular degeneration (AMD). Deep neural networks (DNNs) for OCT can support automated detection and localization of this biomarker. Methods: The method predicts potential OPL subsidence locations on retinal OCTs. A detection module (DM) infers bounding boxes around subsidences with a likelihood score, and a classification module (CM) assesses subsidence presence at the B-scan level. Overlapping boxes between B-scans are combined and scored by the product of the DM and CM predictions. The volume-wise score is the maximum prediction across all B-scans. One development and one independent external data set were used with 140 and 26 patients with AMD, respectively. Results: The system detected more than 85% of OPL subsidences with less than one false-positive (FP)/scan. The average area under the curve was 0.94 ± 0.03 for volume-level detection. Similar or better performance was achieved on the independent external data set. Conclusions: DNN systems can efficiently perform automated retinal layer subsidence detection in retinal OCT images. In particular, the proposed DNN system detects OPL subsidence with high sensitivity and a very limited number of FP detections. Translational Relevance: DNNs enable objective identification of early signs associated with high risk of progression to the atrophic late stage of AMD, ideally suited for screening and assessing the efficacy of the interventions aiming to slow disease progression.

Calcified Drusen Prevent the Detection of Underlying Choriocapillaris Using Swept-Source Optical Coherence Tomography Angiography.

Purpose: In age-related macular degeneration (AMD), choriocapillaris flow deficits (CCFDs) under soft drusen can be measured using established compensation strategies. This study investigated whether CCFDs can be quantified under calcified drusen (CaD). Methods: CCFDs were measured in normal eyes (n = 30) and AMD eyes with soft drusen (n = 30) or CaD (n = 30). CCFD density masks were generated to highlight regions with higher CCFDs. Masks were also generated for soft drusen and CaD based on both structural en face OCT images and corresponding B-scans. Dice similarity coefficients were calculated between the CCFD density masks and both the soft drusen and CaD masks. A phantom experiment was conducted to simulate the impact of light scattering that arises from CaD. Results: Area measurements of CCFDs were highly correlated with those of CaD but not soft drusen, suggesting an association between CaD and underlying CCFDs. However, unlike soft drusen, the detected optical coherence tomography (OCT) signals underlying CaD did not arise from the defined CC layer but were artifacts caused by the multiple scattering property of CaD. Phantom experiments showed that the presence of highly scattering material similar to the contents of CaD caused an artifactual scattering tail that falsely generated a signal in the CC structural layer but the underlying flow could not be detected. Similarly, CaD also caused an artifactual scattering tail and prevented the penetration of light into the choroid, resulting in en face hypotransmission defects and an inability to detect blood flow within the choriocapillaris. Upon resolution of the CaD, the CC perfusion became detectable. Conclusions: The high scattering property of CaD leads to a scattering tail under these drusen that gives the illusion of a quantifiable optical coherence tomography angiography signal, but this signal does not contain the angiographic information required to assess CCFDs. For this reason, CCFDs cannot be reliably measured under CaD, and CaD must be identified and excluded from macular CCFD measurements.

Study protocol: optical coherence tomography angiography for the detection of neovascular age-related macular degeneration: a comprehensive multicentre diagnostic accuracy study in the UK-the ATHENA study.

INTRODUCTION: The diagnosis of neovascular age-related macular degeneration (nAMD), the leading cause of visual impairment in the developed world, relies on the interpretation of various imaging tests of the retina. These include invasive angiographic methods, such as Fundus Fluorescein Angiography (FFA) and, on occasion, Indocyanine-Green Angiography (ICGA). Newer, non-invasive imaging modalities, predominately Optical Coherence Tomography (OCT) and Optical Coherence Tomography Angiography (OCTA), have drastically transformed the diagnostic approach to nAMD. The aim of this study is to undertake a comprehensive diagnostic accuracy assessment of the various imaging modalities used in clinical practice for the diagnosis of nAMD (OCT, OCTA, FFA and, when a variant of nAMD called Polypoidal Choroidal Vasculopathy is suspected, ICGA) both alone and in various combinations. METHODS AND ANALYSIS: This is a non-inferiority, prospective, randomised diagnostic accuracy study of 1067 participants. Participants are patients with clinical features consistent with nAMD who present to a National Health Service secondary care ophthalmology unit in the UK. Patients will undergo OCT as per standard practice and those with suspicious features of nAMD on OCT will be approached for participation in the study. Patients who agree to take part will also undergo both OCTA and FFA (and ICGA if indicated). Interpretation of the imaging tests will be undertaken by clinicians at recruitment sites. A randomised design was selected to avoid bias from consecutive review of all imaging tests by the same clinician. The primary outcome of the study will be the difference in sensitivity and specificity between OCT+OCTA and OCT+FFA (±ICGA) for nAMD detection as interpreted by clinicians at recruitment sites. ETHICS AND DISSEMINATION: The study has been approved by the South Central-Oxford B Research Ethics Committee with reference number 21/SC/0412.Dissemination of study results will involve peer-review publications, presentations at major national and international scientific conferences. TRIAL REGISTRATION NUMBER: ISRCTN18313457.

Interhemispheric functional in age-related macular degeneration patient: a resting-state functional MRI study.

Age-related macular degeneration (AMD) is a prevalent disease leading to severe visual impairment in the elderly population. Despite this, the pathogenesis of AMD remains largely unexplored. The application of resting-state functional MRI (rs-fMRI) allows for the detection of coherent intrinsic brain activities along with the interactions taking place between the two hemispheres. In the frame of our study, we utilize voxel-mirrored homotopic connectivity (VMHC) as an rs-fMRI method to carry out a comparative analysis of functional homotopy between the two hemispheres with the aim of further understanding the pathogenesis of AMD patients. In our study, we utilized the VMHC method to explore levels of brain activity in individuals diagnosed with AMD, planning to investigate potential links with their clinical characteristics. We extended our invitation to 20 AMD patients and 20 healthy controls from Jiangxi Provincial People's Hospital to participate in this research. rs-fMRIs were captured for each participant, and associated neural activity levels were examined using the VMHC method. Remarkably, our comparative examination with the healthy control group revealed significantly reduced VMHC in the cuneus, superior occipital lobe, precentral gyrus, and superior parietal lobule in the patient cohort. Utilizing the VMHC method allows us to identify discrepancies in the visual pathways of AMD patients compared with standard controls, potentially explaining the common challenges among AMD patients with object recognition, face recognition, and reading.

Defining the structure-function relationship of specific lesions in early and advanced age-related macular degeneration.

The objective of this study is to define structure-function relationships of pathological lesions related to age-related macular degeneration (AMD) using microperimetry and multimodal retinal imaging. We conducted a cross-sectional study of 87 patients with AMD (30 eyes with early and intermediate AMD and 110 eyes with advanced AMD), compared to 33 normal controls (66 eyes) recruited from a single tertiary center. All participants had enface and cross-sectional optical coherence tomography (Heidelberg HRA-2), OCT angiography, color and infra-red (IR) fundus and microperimetry (MP) (Nidek MP-3) performed. Multimodal images were graded for specific AMD pathological lesions. A custom marking tool was used to demarcate lesion boundaries on corresponding enface IR images, and subsequently superimposed onto MP color fundus photographs with retinal sensitivity points (RSP). The resulting overlay was used to correlate pathological structural changes to zonal functional changes. Mean age of patients with early/intermediate AMD, advanced AMD and controls were 73(SD = 8.2), 70.8(SD = 8), and 65.4(SD = 7.7) years respectively. Mean retinal sensitivity (MRS) of both early/intermediate (23.1 dB; SD = 5.5) and advanced AMD (18.1 dB; SD = 7.8) eyes were significantly worse than controls (27.8 dB, SD = 4.3) (p < 0.01). Advanced AMD eyes had significantly more unstable fixation (70%; SD = 63.6), larger mean fixation area (3.9 mm2; SD = 3.0), and focal fixation point further away from the fovea (0.7 mm; SD = 0.8), than controls (29%; SD = 43.9; 2.6 mm2; SD = 1.9; 0.4 mm; SD = 0.3) (p ≤ 0.01). Notably, 22 fellow eyes of AMD eyes (25.7 dB; SD = 3.0), with no AMD lesions, still had lower MRS than controls (p = 0.04). For specific AMD-related lesions, end-stage changes such as fibrosis (5.5 dB, SD = 5.4 dB) and atrophy (6.2 dB, SD = 7.0 dB) had the lowest MRS; while drusen and pigment epithelial detachment (17.7 dB, SD = 8.0 dB) had the highest MRS. Peri-lesional areas (20.2 dB, SD = 7.6 dB) and surrounding structurally normal areas (22.2 dB, SD = 6.9 dB) of the retina with no AMD lesions still had lower MRS compared to controls (27.8 dB, SD = 4.3 dB) (p < 0.01). Our detailed topographic structure-function correlation identified specific AMD pathological changes associated with a poorer visual function. This can provide an added value to the assessment of visual function to optimize treatment outcomes to existing and potentially future novel therapies.

FNeXter: A Multi-Scale Feature Fusion Network Based on ConvNeXt and Transformer for Retinal OCT Fluid Segmentation.

The accurate segmentation and quantification of retinal fluid in Optical Coherence Tomography (OCT) images are crucial for the diagnosis and treatment of ophthalmic diseases such as age-related macular degeneration. However, the accurate segmentation of retinal fluid is challenging due to significant variations in the size, position, and shape of fluid, as well as their complex, curved boundaries. To address these challenges, we propose a novel multi-scale feature fusion attention network (FNeXter), based on ConvNeXt and Transformer, for OCT fluid segmentation. In FNeXter, we introduce a novel global multi-scale hybrid encoder module that integrates ConvNeXt, Transformer, and region-aware spatial attention. This module can capture long-range dependencies and non-local similarities while also focusing on local features. Moreover, this module possesses the spatial region-aware capabilities, enabling it to adaptively focus on the lesions regions. Additionally, we propose a novel self-adaptive multi-scale feature fusion attention module to enhance the skip connections between the encoder and the decoder. The inclusion of this module elevates the model's capacity to learn global features and multi-scale contextual information effectively. Finally, we conduct comprehensive experiments to evaluate the performance of the proposed FNeXter. Experimental results demonstrate that our proposed approach outperforms other state-of-the-art methods in the task of fluid segmentation.

Correlation between ellipsoid zone thickness and the presence of subretinal drusenoid deposits in age-related macular degeneration.

PURPOSE: Subretinal drusenoid deposits (SDDs) in age-related macular degeneration (AMD) are associated with systemic vascular diseases that compromise ocular perfusion. We demonstrate that SDDs are associated with decreased ellipsoid zone (EZ) thickness, further evidence of hypoxic damage. METHODS: Post hoc analysis of a cross-sectional study. 165 AMD subjects (aged 51-100; 61% women). Spectral-domain optical coherence tomography was obtained in both eyes. Masked readers assigned subjects to three groups: drusen only, SDD+drusen (SDD+D) and SDD only. EZ thickness was measured subfoveally and 2000 µm nasally, temporally, superiorly and inferiorly from the fovea. Univariate testing was performed using two-tailed t-tests with Bonferroni correction. RESULTS: The mean EZ thickness differences between the SDD+D and drusen-only groups were (in µm) 1.10, 0.67, 1.21, 1.10 and 0.50 at the foveal, nasal, temporal, superior and inferior locations, respectively (p=0.08 inferiorly, otherwise p≤0.01); between the SDD-only and drusen-only groups, the differences were 3.48, 2.48, 2.42, 2.08 and 1.42 (p≤0.0002). Differences in EZ thicknesses across all subjects and between groups were not significantly different based on gender, race or age. CONCLUSION: Subjects with SDDs (±drusen) had thinner EZs than those with drusen only, and the inferior EZ was least affected. EZs were thinnest in SDD-only subjects. This thinning gradation is consistent with progressive destruction of highly oxygen-sensitive mitochondria in the EZ from hypoxia. These findings support the reduced ophthalmic perfusion hypothesis for the formation of SDDs secondary to high-risk systemic vasculopathy.

Prediction of neovascular age-related macular degeneration recurrence using optical coherence tomography images with a deep neural network.

Neovascular age-related macular degeneration (nAMD) can result in blindness if left untreated, and patients often require repeated anti-vascular endothelial growth factor injections. Although, the treat-and-extend method is becoming popular to reduce vision loss attributed to recurrence, it may pose a risk of overtreatment. This study aimed to develop a deep learning model based on DenseNet201 to predict nAMD recurrence within 3 months after confirming dry-up 1 month following three loading injections in treatment-naïve patients. A dataset of 1076 spectral domain optical coherence tomography (OCT) images from 269 patients diagnosed with nAMD was used. The performance of the model was compared with that of 6 ophthalmologists, using 100 randomly selected samples. The DenseNet201-based model achieved 53.0% accuracy in predicting nAMD recurrence using a single pre-injection image and 60.2% accuracy after viewing all the images immediately after the 1st, 2nd, and 3rd injections. The model outperformed experienced ophthalmologists, with an average accuracy of 52.17% using a single pre-injection image and 53.3% after examining four images before and after three loading injections. In conclusion, the artificial intelligence model demonstrated a promising ability to predict nAMD recurrence using OCT images and outperformed experienced ophthalmologists. These findings suggest that deep learning models can assist in nAMD recurrence prediction, thus improving patient outcomes and optimizing treatment strategies.

Phenotype of bilateral EYS-associated occult macular dystrophies based on multimodal imaging.

BACKGROUND: The study aimed to confirm the multimodal imaging of occult macular dystrophy (OMD) with two heterozygous mutations, including an unreported heterozygous EYS mutation. METHODS: The study utilised several diagnostic methods, including Optos wide-field imaging, Bruch's membrane opening-minimum rim width (BMO-MRW), optical coherence tomography (OCT), multifocal electroretinogram (mf-ERG), fundus fluorescein angiography (FFA), indocyanine green angiography (ICGA), and green light autofluorescence (FAF-G) imaging, and genetic testing. RESULTS: The mf-ERG imaging demonstrated decreased P1 amplitudes in both eyes. This was consistent with the FAF-G imaging and OCT results, confirming the bilateral discontinuity of photoreceptors in the macular region. FFA and ICGA revealed persistent macular hypoperfusion not only within the photoreceptors of the macular area but also in the choriocapillaris. Next-generation sequencing results confirmed the presence of two heterozygous mutations in the patient: RP1L1 (c.4273G>C: p. Asp1425His), a hotspot mutation for OMD, and an unreported EYS mutation (c.7382T>A: p. Leu2461Ter) commonly found in retinitis pigmentosa (RP). Analysis using AlphaFold2 further confirmed the impact of the EYS c.7382T>A: p. Leu2461Ter variant on the functional protein conformation. CONCLUSION: We report an unreported heterozygous EYS mutation that could serve as a promising diagnostic marker for OMD.

Ensemble of deep convolutional neural networks is more accurate and reliable than board-certified ophthalmologists at detecting multiple diseases in retinal fundus photographs.

AIMS: To develop an algorithm to classify multiple retinal pathologies accurately and reliably from fundus photographs and to validate its performance against human experts. METHODS: We trained a deep convolutional ensemble (DCE), an ensemble of five convolutional neural networks (CNNs), to classify retinal fundus photographs into diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD) and normal eyes. The CNN architecture was based on the InceptionV3 model, and initial weights were pretrained on the ImageNet dataset. We used 43 055 fundus images from 12 public datasets. Five trained ensembles were then tested on an 'unseen' set of 100 images. Seven board-certified ophthalmologists were asked to classify these test images. RESULTS: Board-certified ophthalmologists achieved a mean accuracy of 72.7% over all classes, while the DCE achieved a mean accuracy of 79.2% (p=0.03). The DCE had a statistically significant higher mean F1-score for DR classification compared with the ophthalmologists (76.8% vs 57.5%; p=0.01) and greater but statistically non-significant mean F1-scores for glaucoma (83.9% vs 75.7%; p=0.10), AMD (85.9% vs 85.2%; p=0.69) and normal eyes (73.0% vs 70.5%; p=0.39). The DCE had a greater mean agreement between accuracy and confident of 81.6% vs 70.3% (p<0.001). DISCUSSION: We developed a deep learning model and found that it could more accurately and reliably classify four categories of fundus images compared with board-certified ophthalmologists. This work provides proof-of-principle that an algorithm is capable of accurate and reliable recognition of multiple retinal diseases using only fundus photographs.

Morphological changes of macular neovascularization during long-term anti-VEGF-therapy in neovascular age-related macular degeneration.

PURPOSE: To analyze the morphological changes of macular neovascularization (MNV) in exudative neovascular age-related macular degeneration under long-term intravitreal anti-vascular endothelial growth factor (VEGF) therapy in a retrospective cohort study. METHODS AND PATIENTS: We evaluated 143 nAMD eyes of 94 patients (31 male, 63 female; initial age 55-97 y, mean age 75.9 ± 7.5 y), who started anti-VEGF therapy (IVAN pro re nata (PRN) protocol) between 2009-2018 and received ongoing therapy until the last recorded visit (mean follow-up 5.3 ± 2.9 y, range 1-14 y). The mean total number of injections was 33.3 ± 19.8 with 7.0 ± 2.3 injections/year. MNV size and, if present, associated complete retinal pigment epithelium (RPE) and outer retina atrophy (cRORA) size were measured on optical coherence tomography (OCT) volume scans at the initial visit and for each year of follow-up. MNV and cRORA were identified on B-scans and their respective borders were manually transposed onto the en-face near infrared image and measured in mm2. RESULTS: MNV enlarged through follow-up, with a mean growth rate of 1.24 mm2 / year. The mean growth in MNV size was independent of initial MNV size, age, gender, MNV subtypes or number of injections per year. Nevertheless, a great interindividual variation in size and growth was observed. cRORA developed in association with increasing MNV size and its incidence increased linearly over follow-up. cRORA lesions also showed continuous growth by a rate of 1.22 mm2 / year. CONCLUSIONS: Despite frequent long-term anti-VEGF therapy, we observed ongoing MNV growth. This is consistent with the concept that the development of MNV may be a physiological biological repair mechanism to preserve RPE and photoreceptor function, provided hyperpermeability and fluid exudation are controlled. Whether recurring low VEGF levels or other factors are responsible for MNV growth remains controversial.

Predicting OCT biological marker localization from weak annotations.

Recent developments in deep learning have shown success in accurately predicting the location of biological markers in Optical Coherence Tomography (OCT) volumes of patients with Age-Related Macular Degeneration (AMD) and Diabetic Retinopathy (DR). We propose a method that automatically locates biological markers to the Early Treatment Diabetic Retinopathy Study (ETDRS) rings, only requiring B-scan-level presence annotations. We trained a neural network using 22,723 OCT B-Scans of 460 eyes (433 patients) with AMD and DR, annotated with slice-level labels for Intraretinal Fluid (IRF) and Subretinal Fluid (SRF). The neural network outputs were mapped into the corresponding ETDRS rings. We incorporated the class annotations and domain knowledge into a loss function to constrain the output with biologically plausible solutions. The method was tested on a set of OCT volumes with 322 eyes (189 patients) with Diabetic Macular Edema, with slice-level SRF and IRF presence annotations for the ETDRS rings. Our method accurately predicted the presence of IRF and SRF in each ETDRS ring, outperforming previous baselines even in the most challenging scenarios. Our model was also successfully applied to en-face marker segmentation and showed consistency within C-scans, despite not incorporating volume information in the training process. We achieved a correlation coefficient of 0.946 for the prediction of the IRF area.

Abnormal functional connectivity strength in age-related macular degeneration patients: a fMRI study.

OBJECTIVE: Age-related macular degeneration (AMD) is a serious blinding eye disease. Previous neuroimaging studies reported that AMD were accompanied by abnormalities of the brain. However, whether AMD patients were associated with functional connectivity strength (FCS) or not remains unknown. In our study, the purpose of the study was to assess FCS changes in AMD patients. METHODS: In our study, 20 AMD patients and 20 healthy controls (HCs), matched closely by sex, age, and educational level were underwent MRI scanning. FCS method and seed-based functional connectivity (FC) method were applied to investigate the functional network changes between two groups. Moreover, support vector machine (SVM) method was applied to assess the FCS maps as a feature to classification of AMD diseases. RESULTS: Our study reported that AMD patients showed decreased FCS values in the bilateral calcarine, left supplementary motor area, left superior parietal lobule and left paracentral lobule (ParaL) relative to the HC group. Meanwhile, our study found that the AMD patients showed abnormal FC within visual network, sensorimotor network and default mode network. Moreover, the SVM method showed that FCS maps as machine learning features shows good classification efficiency (area under curve = 0.82) in the study. CONCLUSION: Our study demonstrated that AMD patients showed abnormal FCS with the visual network, sensorimotor network and default mode network, which might reflect the impaired vision, cognition and motor function in AMD patients. In addition, FCS indicator can be used as an effective biological marker to assist the clinical diagnosis of AMD.

Automated deep learning-based AMD detection and staging in real-world OCT datasets (PINNACLE study report 5).

Real-world retinal optical coherence tomography (OCT) scans are available in abundance in primary and secondary eye care centres. They contain a wealth of information to be analyzed in retrospective studies. The associated electronic health records alone are often not enough to generate a high-quality dataset for clinical, statistical, and machine learning analysis. We have developed a deep learning-based age-related macular degeneration (AMD) stage classifier, to efficiently identify the first onset of early/intermediate (iAMD), atrophic (GA), and neovascular (nAMD) stage of AMD in retrospective data. We trained a two-stage convolutional neural network to classify macula-centered 3D volumes from Topcon OCT images into 4 classes: Normal, iAMD, GA and nAMD. In the first stage, a 2D ResNet50 is trained to identify the disease categories on the individual OCT B-scans while in the second stage, four smaller models (ResNets) use the concatenated B-scan-wise output from the first stage to classify the entire OCT volume. Classification uncertainty estimates are generated with Monte-Carlo dropout at inference time. The model was trained on a real-world OCT dataset, 3765 scans of 1849 eyes, and extensively evaluated, where it reached an average ROC-AUC of 0.94 in a real-world test set.

Pachychoroid neovasculopathy versus macular neovascularization in age-related macular degeneration with and without shallow irregular pigment epithelial detachment.

To compare the choroidal neovascular features of individuals with pachychoroid neovasculopathy (PNV) and neovascular age-related macular degeneration (nAMD) with and without shallow irregular pigment epithelial detachment (SIPED). Using optical coherence tomography angiography, the choroidal neovascular complexes of 27 patients with PNV, 34 patients with nAMD and SIPED, and 15 patients with nAMD without SIPED were analyzed with FIJI and AngioTool software. PNV compared to nAMD with SIPED had a greater vessel percentage area (P = 0.034), junction density (P = 0.045), average vessel length (P < 0.001), and fractal dimension (P < 0.001). PNV, compared to nAMD without SIPED, had a greater total vessel length (P = 0.002), total number of junctions (P < 0.001), junction density (P = 0.034), and fractal dimension (P = 0.005). nAMD with SIPED, compared to nAMD without SIPED, had greater vessel area, total number of junctions, total vessel length, and average vessel length (all P values < 0.001). Patients with nAMD plus SIPED and individuals with nAMD without SIPED have similar fractal dimension values (P = 0.703). Biomarkers of choroidal neovascular complexity, such as fractal dimension, can be used to differentiate PNV from nAMD with or without SIPED.

Automatic detection and differential diagnosis of age-related macular degeneration from color fundus photographs using deep learning with hierarchical vision transformer.

Age-related macular degeneration (AMD) is a leading cause of vision loss in the elderly, highlighting the need for early and accurate detection. In this study, we proposed DeepDrAMD, a hierarchical vision transformer-based deep learning model that integrates data augmentation techniques and SwinTransformer, to detect AMD and distinguish between different subtypes using color fundus photographs (CFPs). The DeepDrAMD was trained on the in-house WMUEH training set and achieved high performance in AMD detection with an AUC of 98.76% in the WMUEH testing set and 96.47% in the independent external Ichallenge-AMD cohort. Furthermore, the DeepDrAMD effectively classified dryAMD and wetAMD, achieving AUCs of 93.46% and 91.55%, respectively, in the WMUEH cohort and another independent external ODIR cohort. Notably, DeepDrAMD excelled at distinguishing between wetAMD subtypes, achieving an AUC of 99.36% in the WMUEH cohort. Comparative analysis revealed that the DeepDrAMD outperformed conventional deep-learning models and expert-level diagnosis. The cost-benefit analysis demonstrated that the DeepDrAMD offers substantial cost savings and efficiency improvements compared to manual reading approaches. Overall, the DeepDrAMD represents a significant advancement in AMD detection and differential diagnosis using CFPs, and has the potential to assist healthcare professionals in informed decision-making, early intervention, and treatment optimization.

Wavelet scattering transform application in classification of retinal abnormalities using OCT images.

To assist ophthalmologists in diagnosing retinal abnormalities, Computer Aided Diagnosis has played a significant role. In this paper, a particular Convolutional Neural Network based on Wavelet Scattering Transform (WST) is used to detect one to four retinal abnormalities from Optical Coherence Tomography (OCT) images. Predefined wavelet filters in this network decrease the computation complexity and processing time compared to deep learning methods. We use two layers of the WST network to obtain a direct and efficient model. WST generates a sparse representation of the images which is translation-invariant and stable concerning local deformations. Next, a Principal Component Analysis classifies the extracted features. We evaluate the model using four publicly available datasets to have a comprehensive comparison with the literature. The accuracies of classifying the OCT images of the OCTID dataset into two and five classes were [Formula: see text] and [Formula: see text], respectively. We achieved an accuracy of [Formula: see text] in detecting Diabetic Macular Edema from Normal ones using the TOPCON device-based dataset. Heidelberg and Duke datasets contain DME, Age-related Macular Degeneration, and Normal classes, in which we achieved accuracy of [Formula: see text] and [Formula: see text], respectively. A comparison of our results with the state-of-the-art models shows that our model outperforms these models for some assessments or achieves nearly the best results reported so far while having a much smaller computational complexity.

Deep learning model for automatic differentiation of EMAP from AMD in macular atrophy.

To create a deep learning (DL) classifier pre-trained on fundus autofluorescence (FAF) images that can assist the clinician in distinguishing age-related geographic atrophy from extensive macular atrophy and pseudodrusen-like appearance (EMAP). Patients with complete outer retinal and retinal pigment epithelium atrophy secondary to either EMAP (EMAP Group) or to dry age related macular degeneration (AMD group) were retrospectively selected. Fovea-centered posterior pole (30° × 30°) and 55° × 55° degree-field-of-view FAF images of sufficiently high quality were collected and used to train two different deep learning (DL) classifiers based on ResNet-101 design. Testing was performed on a set of images coming from a different center. A total of 300 patients were recruited, 135 belonging to EMAP group and 165 belonging to AMD group. The 30° × 30° FAF based DL classifier showed a sensitivity of 84.6% and a specificity of 85.3% for the diagnosis of EMAP. The 55° × 55° FAF based DL classifier showed a sensitivity of 90% and a specificity of 84.6%, a performance that was significantly higher than that of the 30° × 30° classifer (p = 0.037). Artificial intelligence can accurately distinguish between atrophy caused by AMD or by EMAP on FAF images. Its performance are improved using wide field acquisitions.