A new convolutional neural network based on combination of circlets and wavelets for macular OCT classification.

Artificial intelligence (AI) algorithms, encompassing machine learning and deep learning, can assist ophthalmologists in early detection of various ocular abnormalities through the analysis of retinal optical coherence tomography (OCT) images. Despite considerable progress in these algorithms, several limitations persist in medical imaging fields, where a lack of data is a common issue. Accordingly, specific image processing techniques, such as time-frequency transforms, can be employed in conjunction with AI algorithms to enhance diagnostic accuracy. This research investigates the influence of non-data-adaptive time-frequency transforms, specifically X-lets, on the classification of OCT B-scans. For this purpose, each B-scan was transformed using every considered X-let individually, and all the sub-bands were utilized as the input for a designed 2D Convolutional Neural Network (CNN) to extract optimal features, which were subsequently fed to the classifiers. Evaluating per-class accuracy shows that the use of the 2D Discrete Wavelet Transform (2D-DWT) yields superior outcomes for normal cases, whereas the circlet transform outperforms other X-lets for abnormal cases characterized by circles in their retinal structure (due to the accumulation of fluid). As a result, we propose a novel transform named CircWave by concatenating all sub-bands from the 2D-DWT and the circlet transform. The objective is to enhance the per-class accuracy of both normal and abnormal cases simultaneously. Our findings show that classification results based on the CircWave transform outperform those derived from original images or any individual transform. Furthermore, Grad-CAM class activation visualization for B-scans reconstructed from CircWave sub-bands highlights a greater emphasis on circular formations in abnormal cases and straight lines in normal cases, in contrast to the focus on irrelevant regions in original B-scans. To assess the generalizability of our method, we applied it to another dataset obtained from a different imaging system. We achieved promising accuracies of 94.5% and 90% for the first and second datasets, respectively, which are comparable with results from previous studies. The proposed CNN based on CircWave sub-bands (i.e. CircWaveNet) not only produces superior outcomes but also offers more interpretable results with a heightened focus on features crucial for ophthalmologists.

Application of ImageJ in Optical Coherence Tomography Angiography (OCT-A): A Literature Review.

Background: This study aimed to review the literature on the application of ImageJ in optical coherence tomography angiography (OCT-A) images. Methods: A general search was performed in PubMed, Google Scholar, and Scopus databases. The authors evaluated each of the selected articles in order to assess the implementation of ImageJ in OCT-A images. Results: ImageJ can aid in reducing artifacts, enhancing image quality to increase the accuracy of the process and analysis, processing and analyzing images, generating comparable parameters such as the parameters that assess perfusion of the layers (vessel density (VD), skeletonized density (SD), and vessel length density (VLD)) and the parameters that evaluate the structure of the layers (fractal dimension (FD), vessel density index (VDI), and lacunarity (LAC)), and the foveal avascular zone (FAZ) that are used widely in the retinal and choroidal studies), and establishing diagnostic criteria. It can help to save time when the dataset is huge with numerous plugins and options for image processing and analysis with reliable results. Diverse studies implemented distinct binarization and thresholding techniques, resulting in disparate outcomes and incomparable parameters. Uniformity in methodology is required to acquire comparable data from studies employing diverse processing and analysis techniques that yield varied outcomes. Conclusion: Researchers and professionals might benefit from using ImageJ because of how quickly and correctly it processes and analyzes images. It is highly adaptable and potent software, allowing users to evaluate images in a variety of ways. There exists a diverse range of methodologies for analyzing OCTA images through the utilization of ImageJ. However, it is imperative to establish a standardized strategy to ensure the reliability and consistency of the method for research purposes.

Biased Deep Learning Methods in Detection of COVID-19 Using CT Images: A Challenge Mounted by Subject-Wise-Split ISFCT Dataset.

Accurate detection of respiratory system damage including COVID-19 is considered one of the crucial applications of deep learning (DL) models using CT images. However, the main shortcoming of the published works has been unreliable reported accuracy and the lack of repeatability with new datasets, mainly due to slice-wise splits of the data, creating dependency between training and test sets due to shared data across the sets. We introduce a new dataset of CT images (ISFCT Dataset) with labels indicating the subject-wise split to train and test our DL algorithms in an unbiased manner. We also use this dataset to validate the real performance of the published works in a subject-wise data split. Another key feature provides more specific labels (eight characteristic lung features) rather than being limited to COVID-19 and healthy labels. We show that the reported high accuracy of the existing models on current slice-wise splits is not repeatable for subject-wise splits, and distribution differences between data splits are demonstrated using t-distribution stochastic neighbor embedding. We indicate that, by examining subject-wise data splitting, less complicated models show competitive results compared to the exiting complicated models, demonstrating that complex models do not necessarily generate accurate and repeatable results.

Discrimination of multiple sclerosis using OCT images from two different centers.

BACKGROUND: Multiple sclerosis (MS) is one of the most prevalent chronic inflammatory diseases caused by demyelination and axonal damage in the central nervous system. Structural retinal imaging via optical coherence tomography (OCT) shows promise as a noninvasive biomarker for monitoring of MS. There are successful reports regarding the application of Artificial Intelligence (AI) in the analysis of cross-sectional OCTs in ophthalmologic diseases. However, the alteration of thicknesses of various retinal layers in MS is noticeably subtle compared to other ophthalmologic diseases. Therefore, raw cross-sectional OCTs are replaced with multilayer segmented OCTs for discrimination of MS and healthy controls (HCs). METHODS: To conform to the principles of trustworthy AI, interpretability is provided by visualizing the regional layer contribution to classification performance with the proposed occlusion sensitivity approach. The robustness of the classification is also guaranteed by showing the effectiveness of the algorithm while being tested on the new independent dataset. The most discriminative features from different topologies of the multilayer segmented OCTs are selected by the dimension reduction method. Support vector machine (SVM), random forest (RF), and artificial neural network (ANN) are used for classification. Patient-wise cross-validation (CV) is utilized to evaluate the performance of the algorithm, where the training and test folds contain records from different subjects. RESULTS: The most discriminative topology is determined to square with a size of 40 pixels and the most influential layers are the ganglion cell and inner plexiform layer (GCIPL) and inner nuclear layer (INL). Linear SVM resulted in 88% Accuracy (with standard deviation (std) = 0.49 in 10 times of execution to indicate the repeatability), 78% precision (std=1.48), and 63% recall (std=1.35) in the discrimination of MS and HCs using macular multilayer segmented OCTs. CONCLUSION: The proposed classification algorithm is expected to help neurologists in the early diagnosis of MS. This paper distinguishes itself from other studies by employing two distinct datasets, which enhances the robustness of its findings in comparison with previous studies with lack of external validation. This study aims to circumvent the utilization of deep learning methods due to the limited quantity of the available data and convincingly demonstrates that favorable outcomes can be achieved without relying on deep learning techniques.

Optimal Deep Learning Architecture for Automated Segmentation of Cysts in OCT Images Using X-Let Transforms.

The retina is a thin, light-sensitive membrane with a multilayered structure found in the back of the eyeball. There are many types of retinal disorders. The two most prevalent retinal illnesses are Age-Related Macular Degeneration (AMD) and Diabetic Macular Edema (DME). Optical Coherence Tomography (OCT) is a vital retinal imaging technology. X-lets (such as curvelet, DTCWT, contourlet, etc.) have several benefits in image processing and analysis. They can capture both local and non-local features of an image simultaneously. The aim of this paper is to propose an optimal deep learning architecture based on sparse basis functions for the automated segmentation of cystic areas in OCT images. Different X-let transforms were used to produce different network inputs, including curvelet, Dual-Tree Complex Wavelet Transform (DTCWT), circlet, and contourlet. Additionally, three different combinations of these transforms are suggested to achieve more accurate segmentation results. Various metrics, including Dice coefficient, sensitivity, false positive ratio, Jaccard index, and qualitative results, were evaluated to find the optimal networks and combinations of the X-let's sub-bands. The proposed network was tested on both original and noisy datasets. The results show the following facts: (1) contourlet achieves the optimal results between different combinations; (2) the five-channel decomposition using high-pass sub-bands of contourlet transform achieves the best performance; and (3) the five-channel decomposition using high-pass sub-bands formations out-performs the state-of-the-art methods, especially in the noisy dataset. The proposed method has the potential to improve the accuracy and speed of the segmentation process in clinical settings, facilitating the diagnosis and treatment of retinal diseases.

CNV-Net: Segmentation, Classification and Activity Score Measurement of Choroidal Neovascularization (CNV) Using Optical Coherence Tomography Angiography (OCTA).

This paper aims to present an artificial intelligence-based algorithm for the automated segmentation of Choroidal Neovascularization (CNV) areas and to identify the presence or absence of CNV activity criteria (branching, peripheral arcade, dark halo, shape, loop and anastomoses) in OCTA images. Methods: This retrospective and cross-sectional study includes 130 OCTA images from 101 patients with treatment-naïve CNV. At baseline, OCTA volumes of 6 × 6 mm2 were obtained to develop an AI-based algorithm to evaluate the CNV activity based on five activity criteria, including tiny branching vessels, anastomoses and loops, peripheral arcades, and perilesional hypointense halos. The proposed algorithm comprises two steps. The first block includes the pre-processing and segmentation of CNVs in OCTA images using a modified U-Net network. The second block consists of five binary classification networks, each implemented with various models from scratch, and using transfer learning from pre-trained networks. Results: The proposed segmentation network yielded an averaged Dice coefficient of 0.86. The individual classifiers corresponding to the five activity criteria (branch, peripheral arcade, dark halo, shape, loop, and anastomoses) showed accuracies of 0.84, 0.81, 0.86, 0.85, and 0.82, respectively. The AI-based algorithm potentially allows the reliable detection and segmentation of CNV from OCTA alone, without the need for imaging with contrast agents. The evaluation of the activity criteria in CNV lesions obtains acceptable results, and this algorithm could enable the objective, repeatable assessment of CNV features.

Differentiating Glaucomatous Optic Neuropathy From Non-glaucomatous Optic Neuropathies Using Deep Learning Algorithms.

PURPOSE: A deep learning framework to differentiate glaucomatous optic disc changes due to glaucomatous optic neuropathy (GON) from non-glaucomatous optic disc changes due to non-glaucomatous optic neuropathies (NGONs). DESIGN: Cross-sectional study. METHOD: A deep-learning system was trained, validated, and externally tested to classify optic discs as normal, GON, or NGON, using 2183 digital color fundus photographs. A Single-Center data set of 1822 images (660 images of NGON, 676 images of GON, and 486 images of normal optic discs) was used for training and validation, whereas 361 photographs from 4 different data sets were used for external testing. Our algorithm removed the redundant information from the images using an optic disc segmentation (OD-SEG) network, after which we performed transfer learning with various pre-trained networks. Finally, we calculated sensitivity, specificity, F1-score, and precision to show the performance of the discrimination network in the validation and independent external data set. RESULTS: For classification, the algorithm with the best performance for the Single-Center data set was DenseNet121, with a sensitivity of 95.36%, precision of 95.35%, specificity of 92.19%, and F1 score of 95.40%. For the external validation data, the sensitivity and specificity of our network for differentiating GON from NGON were 85.53% and 89.02%, respectively. The glaucoma specialist who diagnosed those cases in masked fashion had a sensitivity of 71.05% and a specificity of 82.21%. CONCLUSIONS: The proposed algorithm for the differentiation of GON from NGON yields results that have a higher sensitivity than those of a glaucoma specialist, and its application for unseen data thus is extremely promising.

Diagnostic value of intereye difference metrics for optic neuritis in aquaporin-4 antibody seropositive neuromyelitis optica spectrum disorders.

BACKGROUND: The novel optic neuritis (ON) diagnostic criteria include intereye differences (IED) of optical coherence tomography (OCT) parameters. IED has proven valuable for ON diagnosis in multiple sclerosis but has not been evaluated in aquaporin-4 antibody seropositive neuromyelitis optica spectrum disorders (AQP4+NMOSD). We evaluated the diagnostic accuracy of intereye absolute (IEAD) and percentage difference (IEPD) in AQP4+NMOSD after unilateral ON >6 months before OCT as compared with healthy controls (HC). METHODS: Twenty-eight AQP4+NMOSD after unilateral ON (NMOSD-ON), 62 HC and 45 AQP4+NMOSD without ON history (NMOSD-NON) were recruited by 13 centres as part of the international Collaborative Retrospective Study on retinal OCT in Neuromyelitis Optica study. Mean thickness of peripapillary retinal nerve fibre layer (pRNFL) and macular ganglion cell and inner plexiform layer (GCIPL) were quantified by Spectralis spectral domain OCT. Threshold values of the ON diagnostic criteria (pRNFL: IEAD 5 µm, IEPD 5%; GCIPL: IEAD: 4 µm, IEPD: 4%) were evaluated using receiver operating characteristics and area under the curve (AUC) metrics. RESULTS: The discriminative power was high for NMOSD-ON versus HC for IEAD (pRNFL: AUC 0.95, specificity 82%, sensitivity 86%; GCIPL: AUC 0.93, specificity 98%, sensitivity 75%) and IEPD (pRNFL: AUC 0.96, specificity 87%, sensitivity 89%; GCIPL: AUC 0.94, specificity 96%, sensitivity 82%). The discriminative power was high/moderate for NMOSD-ON versus NMOSD-NON for IEAD (pRNFL: AUC 0.92, specificity 77%, sensitivity 86%; GCIP: AUC 0.87, specificity 85%, sensitivity 75%) and for IEPD (pRNFL: AUC 0.94, specificity 82%, sensitivity 89%; GCIP: AUC 0.88, specificity 82%, sensitivity 82%). CONCLUSIONS: Results support the validation of the IED metrics as OCT parameters of the novel diagnostic ON criteria in AQP4+NMOSD.

Parapapillary choroidal microvascular density in acute primary angle-closure and primary open-angle glaucoma: an optical coherence tomography angiography study.

BACK GROUND/AIMS: To determine whether parapapillary choroidal microvasculature (PPCMv) density, measured by optical coherence tomography angiography, differed between acute primary angle-closure (APAC), primary open-angle glaucoma (POAG) and controls. METHODS: This is a prospective, cross-sectional, observational study. Data from 149 eyes from two academic referral centres were analysed. Automated PPCMv density was calculated in inner and outer annuli around the optic nerve region in addition to the peripapillary superficial vasculature, using customised software. A generalised estimating equation was used to compare vessel densities among groups, adjusted for confounders. RESULTS: Data from 40 eyes with APAC, 65 eyes with POAG and 44 eyes in healthy controls were gathered and analysed. Global radial peripapillary capillary densities were reduced in eyes with APAC and POAG compared with controls (p=0.027 and 0.136, respectively). Mean outer annular PPCMv density in the POAG group was lower vs the APAC group by 3.6% (95% CI 0.6% to 6.5%) (p=0.018) in the multivariable model adjusted for confounders. The mean difference in inner and outer superior PPCMv between the POAG and APAC groups was 5.9% and 4.4% (95% CI 1.9% to 9.9% and 1.0% to 7.7%, respectively; both p<0.010). Furthermore, POAG and APAC groups both had significantly lower PPCMv compared with controls (both, p<0.001). CONCLUSIONS: While superficial peripapillary vessels were affected to similar degrees in POAG and APAC, PPCMv drop-out was greater with POAG versus APAC, suggesting that choroidal vessel density may be affected to a lesser extent following an acute increase in intraocular pressure before glaucoma develops.

Measurement of retinal nerve fiber layer thickness with a deep learning algorithm in ischemic optic neuropathy and optic neuritis.

This work aims at determining the ability of a deep learning (DL) algorithm to measure retinal nerve fiber layer (RNFL) thickness from optical coherence tomography (OCT) scans in anterior ischemic optic neuropathy (NAION) and demyelinating optic neuritis (ON). The training/validation dataset included 750 RNFL OCT B-scans. Performance of our algorithm was evaluated on 194 OCT B-scans from 70 healthy eyes, 82 scans from 28 NAION eyes, and 84 scans of 29 ON eyes. Results were compared to manual segmentation as a ground-truth and to RNFL calculations from the built-in instrument software. The Dice coefficient for the test images was 0.87. The mean average RNFL thickness using our U-Net was not different from the manually segmented best estimate and OCT machine data in control and ON eyes. In NAION eyes, while the mean average RNFL thickness using our U-Net algorithm was not different from the manual segmented value, the OCT machine data were different from the manual segmented values. In NAION eyes, the MAE of the average RNFL thickness was 1.18 ± 0.69 µm and 6.65 ± 5.37 µm in the U-Net algorithm segmentation and the conventional OCT machine data, respectively (P = 0.0001).

Synthetic OCT Data Generation to Enhance the Performance of Diagnostic Models for Neurodegenerative Diseases.

Purpose: Optical coherence tomography (OCT) has recently emerged as a source for powerful biomarkers in neurodegenerative diseases such as multiple sclerosis (MS) and neuromyelitis optica (NMO). The application of machine learning techniques to the analysis of OCT data has enabled automatic extraction of information with potential to aid the timely diagnosis of neurodegenerative diseases. These algorithms require large amounts of labeled data, but few such OCT data sets are available now. Methods: To address this challenge, here we propose a synthetic data generation method yielding a tailored augmentation of three-dimensional (3D) OCT data and preserving differences between control and disease data. A 3D active shape model is used to produce synthetic retinal layer boundaries, simulating data from healthy controls (HCs) as well as from patients with MS or NMO. Results: To evaluate the generated data, retinal thickness maps are extracted and evaluated under a broad range of quality metrics. The results show that the proposed model can generate realistic-appearing synthetic maps. Quantitatively, the image histograms of the synthetic thickness maps agree with the real thickness maps, and the cross-correlations between synthetic and real maps are also high. Finally, we use the generated data as an augmentation technique to train stronger diagnostic models than those using only the real data. Conclusions: This approach provides valuable data augmentation, which can help overcome key bottlenecks of limited data. Translational Relevance: By addressing the challenge posed by limited data, the proposed method helps apply machine learning methods to diagnose neurodegenerative diseases from retinal imaging.

Dynamic Brain Connectivity in Resting-State FMRI Using Spectral ICA and Graph Approach: Application to Healthy Controls and Multiple Sclerosis.

Multiple sclerosis (MS) is a neuroinflammatory disease that involves structural and functional damage to the brain. It changes the functional connectivity of the brain between and within networks. Resting-state functional magnetic resonance imaging (fMRI) enables us to measure functional correlation and independence between different brain regions. In recent years, statistical methods, including independent component analysis (ICA) and graph-based analysis, have been widely used in fMRI studies. Furthermore, topological properties of the brain have been appeared as significant features of neuroscience studies. Most studies are focused on graph analysis and ICA methods, rather than considering spectral approaches. Here, we developed a new framework to measure brain connectivity (in static and dynamic formats) and incorporate it to study fMRI data from MS patients and healthy controls (HCs). For this purpose, a spectral ICA method is proposed to extract the nodes of the brain graph. Spectral ICA extracts more reliable components and decreases the processing time in calculation of the static brain connectivity. Compared to Infomax ICA, dynamic range and low-frequency to high-frequency power ratio (fALFF) show better results using the proposed ICA. It is also helpful in selection of the states for dynamic connectivity. Furthermore, the dynamic connectivity-based extracted components from spectral ICA are estimated using a mutual information method and based on correlation of sliding time-windowed on selected IC time courses. First-level and second-level connectivity states are calculated using correlations of connectivity strength between graph nodes (spectral ICA components). Finally, static and dynamic connectivity are analyzed based on correlation nodes percolated by an anatomical automatic labeling (AAL) atlas. Despite static and dynamic connectivity results of AAL correlations not showing any significant changes between MS and HC, our results based on spectral ICA in static and dynamic connectivity showed significantly decreased connectivity in MS patients in the anterior cingulate cortex, whereas it was significantly weaker in the core but stronger at the periphery of the posterior cingulate cortex.

Glioma segmentation with DWI weighted images, conventional anatomical images, and post-contrast enhancement magnetic resonance imaging images by U-Net.

Glioma segmentation is believed to be one of the most important stages of treatment management. Recent developments in magnetic resonance imaging (MRI) protocols have led to a renewed interest in using automatic glioma segmentation with different MRI image weights. U-Net is a major area of interest within the field of automatic glioma segmentation. This paper examines the impact of different input MRI image-weight on the U-Net output performance for glioma segmentation. One hundred forty-nine glioma patients were scanned with a 1.5T MRI scanner. The main MRI image-weights acquired are diffusion-weighted imaging (DWI) weighted images (b50, b500, b1000, Apparent diffusion coefficient (ADC) map, Exponential apparent diffusion coefficient (eADC) map), anatomical image-weights (T2, T1, T2-FLAIR), and post enhancement image-weights (T1Gd). The U-Net and data augmentation are used to segment the glioma tumors. Having the Dice coefficient and accuracy enabled us to compare our results with the previous study. The first set of analyses examined the impact of epoch number on the accuracy of U-Net, and n_epoch = 20 was selected for U-Net training. The mean Dice coefficient for b50, b500, b1000, ADC map, eADC map, T2, T1, T2-FLAIR, and T1Gd image weights for glioma segmentation with U-Net were calculated 0.892, 0.872, 0.752, 0.931, 0.944, 0.762, 0.721, 0.896, 0.694 respectively. This study has found that, DWI image-weights have a higher diagnostic value for glioma segmentation with U-Net in comparison with anatomical image-weights and post enhancement image-weights. The results of this investigation show that ADC and eADC maps have higher performance for glioma segmentation with U-Net.

Statistical Inference of COVID-19 Outbreak: Delay Distribution Effect in EQIR Modeling of Epidemic.

Background: The world is experiencing another pandemic called COVID-19. Several mathematical models have been proposed to examine the impact of health interventions in controlling pandemic growth. Method: In this study, we propose a fractional order distributed delay dynamic system, namely, EQIR model. In order to predict the outbreak, the proposed model incorporates changes in transmission rate, isolation rate, and identification of infected people through time varying deterministic and stochastic parameters. Furthermore, proposed stochastic model considers fluctuations in population behavior and simulates different scenarios of outbreak at the same time. Main novelty of this model is its ability to incorporate changes in transmission rate, latent periods, and rate of quarantine through time varying deterministic and stochastic assumptions. This model can exactly follow the disease trend from its beginning to current situation and predict outbreak future for various situations. Results: Parameters of this model were identified during fitting process to real data of Iran, USA, and South Korea. We calculated the reproduction number using a Laplace transform-based method. Results of numerical simulation verify the effectiveness and accuracy of proposed deterministic and stochastic models in current outbreak. Conclusion: Justifying of parameters of the model emphasizes that, although stricter deterrent interventions can prevent another peak and control the current outbreak, the consecutive screening schemes of COVID-19 plays more important role. This means that the more diagnostic tests performed on people, the faster the disease will be controlled.

Intraretinal Layer Segmentation Using Cascaded Compressed U-Nets.

Reliable biomarkers quantifying neurodegeneration and neuroinflammation in central nervous system disorders such as Multiple Sclerosis, Alzheimer's dementia or Parkinson's disease are an unmet clinical need. Intraretinal layer thicknesses on macular optical coherence tomography (OCT) images are promising noninvasive biomarkers querying neuroretinal structures with near cellular resolution. However, changes are typically subtle, while tissue gradients can be weak, making intraretinal segmentation a challenging task. A robust and efficient method that requires no or minimal manual correction is an unmet need to foster reliable and reproducible research as well as clinical application. Here, we propose and validate a cascaded two-stage network for intraretinal layer segmentation, with both networks being compressed versions of U-Net (CCU-INSEG). The first network is responsible for retinal tissue segmentation from OCT B-scans. The second network segments eight intraretinal layers with high fidelity. At the post-processing stage, we introduce Laplacian-based outlier detection with layer surface hole filling by adaptive non-linear interpolation. Additionally, we propose a weighted version of focal loss to minimize the foreground-background pixel imbalance in the training data. We train our method using 17,458 B-scans from patients with autoimmune optic neuropathies, i.e., multiple sclerosis, and healthy controls. Voxel-wise comparison against manual segmentation produces a mean absolute error of 2.3 µm, outperforming current state-of-the-art methods on the same data set. Voxel-wise comparison against external glaucoma data leads to a mean absolute error of 2.6 µm when using the same gold standard segmentation approach, and 3.7 µm mean absolute error in an externally segmented data set. In scans from patients with severe optic atrophy, 3.5% of B-scan segmentation results were rejected by an experienced grader, whereas this was the case in 41.4% of B-scans segmented with a graph-based reference method. The validation results suggest that the proposed method can robustly segment macular scans from eyes with even severe neuroretinal changes.

Astrocytic outer retinal layer thinning is not a feature in AQP4-IgG seropositive neuromyelitis optica spectrum disorders.

BACKGROUND: Patients with anti-aquaporin-4 antibody seropositive (AQP4-IgG+) neuromyelitis optica spectrum disorders (NMOSDs) frequently suffer from optic neuritis (ON) leading to severe retinal neuroaxonal damage. Further, the relationship of this retinal damage to a primary astrocytopathy in NMOSD is uncertain. Primary astrocytopathy has been suggested to cause ON-independent retinal damage and contribute to changes particularly in the outer plexiform layer (OPL) and outer nuclear layer (ONL), as reported in some earlier studies. However, these were limited in their sample size and contradictory as to the localisation. This study assesses outer retinal layer changes using optical coherence tomography (OCT) in a multicentre cross-sectional cohort. METHOD: 197 patients who were AQP4-IgG+ and 32 myelin-oligodendrocyte-glycoprotein antibody seropositive (MOG-IgG+) patients were enrolled in this study along with 75 healthy controls. Participants underwent neurological examination and OCT with central postprocessing conducted at a single site. RESULTS: No significant thinning of OPL (25.02±2.03 µm) or ONL (61.63±7.04 µm) were observed in patients who were AQP4-IgG+ compared with patients who were MOG-IgG+ with comparable neuroaxonal damage (OPL: 25.10±2.00 µm; ONL: 64.71±7.87 µm) or healthy controls (OPL: 24.58±1.64 µm; ONL: 63.59±5.78 µm). Eyes of patients who were AQP4-IgG+ (19.84±5.09 µm, p=0.027) and MOG-IgG+ (19.82±4.78 µm, p=0.004) with a history of ON showed parafoveal OPL thinning compared with healthy controls (20.99±5.14 µm); this was not observed elsewhere. CONCLUSION: The results suggest that outer retinal layer loss is not a consistent component of retinal astrocytic damage in AQP4-IgG+ NMOSD. Longitudinal studies are necessary to determine if OPL and ONL are damaged in late disease due to retrograde trans-synaptic axonal degeneration and whether outer retinal dysfunction occurs despite any measurable structural correlates.

Synthetic OCT data in challenging conditions: three-dimensional OCT and presence of abnormalities.

Nowadays, retinal optical coherence tomography (OCT) plays an important role in ophthalmology and automatic analysis of the OCT is of real importance: image denoising facilitates a better diagnosis and image segmentation and classification are undeniably critical in treatment evaluation. Synthetic OCT was recently considered to provide a benchmark for quantitative comparison of automatic algorithms and to be utilized in the training stage of novel solutions based on deep learning. Due to complicated data structure in retinal OCTs, a limited number of delineated OCT datasets are already available in presence of abnormalities; furthermore, the intrinsic three-dimensional (3D) structure of OCT is ignored in many public 2D datasets. We propose a new synthetic method, applicable to 3D data and feasible in presence of abnormalities like diabetic macular edema (DME). In this method, a limited number of OCT data is used during the training step and the Active Shape Model is used to produce synthetic OCTs plus delineation of retinal boundaries and location of abnormalities. Statistical comparison of thickness maps showed that synthetic dataset can be used as a statistically acceptable representative of the original dataset (p > 0.05). Visual inspection of the synthesized vessels was also promising. Regarding the texture features of the synthesized datasets, Q-Q plots were used, and even in cases that the points have slightly digressed from the straight line, the p-values of the Kolmogorov-Smirnov test rejected the null hypothesis and showed the same distribution in texture features of the real and the synthetic data. The proposed algorithm provides a unique benchmark for comparison of OCT enhancement methods and a tailored augmentation method to overcome the limited number of OCTs in deep learning algorithms.

Retinal Optical Coherence Tomography in Neuromyelitis Optica.

BACKGROUND AND OBJECTIVES: To determine optic nerve and retinal damage in aquaporin-4 antibody (AQP4-IgG)-seropositive neuromyelitis optica spectrum disorders (NMOSD) in a large international cohort after previous studies have been limited by small and heterogeneous cohorts. METHODS: The cross-sectional Collaborative Retrospective Study on retinal optical coherence tomography (OCT) in neuromyelitis optica collected retrospective data from 22 centers. Of 653 screened participants, we included 283 AQP4-IgG-seropositive patients with NMOSD and 72 healthy controls (HCs). Participants underwent OCT with central reading including quality control and intraretinal segmentation. The primary outcome was thickness of combined ganglion cell and inner plexiform (GCIP) layer; secondary outcomes were thickness of peripapillary retinal nerve fiber layer (pRNFL) and visual acuity (VA). RESULTS: Eyes with ON (NMOSD-ON, N = 260) or without ON (NMOSD-NON, N = 241) were assessed compared with HCs (N = 136). In NMOSD-ON, GCIP layer (57.4 ± 12.2 µm) was reduced compared with HC (GCIP layer: 81.4 ± 5.7 µm, p < 0.001). GCIP layer loss (-22.7 µm) after the first ON was higher than after the next (-3.5 µm) and subsequent episodes. pRNFL observations were similar. NMOSD-NON exhibited reduced GCIP layer but not pRNFL compared with HC. VA was greatly reduced in NMOSD-ON compared with HC eyes, but did not differ between NMOSD-NON and HC. DISCUSSION: Our results emphasize that attack prevention is key to avoid severe neuroaxonal damage and vision loss caused by ON in NMOSD. Therapies ameliorating attack-related damage, especially during a first attack, are an unmet clinical need. Mild signs of neuroaxonal changes without apparent vision loss in ON-unaffected eyes might be solely due to contralateral ON attacks and do not suggest clinically relevant progression but need further investigation.

Retinal OCT Texture Analysis for Differentiating Healthy Controls from Multiple Sclerosis (MS) with/without Optic Neuritis.

Multiple sclerosis (MS) is an inflammatory disease damaging the myelin sheath in the central and peripheral nervous system in the brain and spinal cord. Optic Neuritis (ON) is one of the most prevalent ocular demonstrations of MS. The current diagnosis protocol for MS is MRI, but newer modalities like Optical Coherence Tomography (OCT) are already of interest in early detection and progression analysis. OCT reveals the symptoms of MS in the Central Nervous System (CNS) through cross-sectional images from neural retinal layers. Previous works on OCT were mostly focused on the thickness of retinal layers; however, texture features seem also to have information in this regard. In this research, we introduce a new pipeline that constructs layer-stacked (LS) images containing data from each specific layer. A variety of texture features are then extracted from LS images to differentiate between healthy controls and ON/None-ON MS cases. Furthermore, the definition of texture extraction methods is tailored for this application. After performing a vast survey on available texture analysis methods, a treasury of powerful features is collected in this paper. As a primary work, this paper shows the ability of such features in the diagnosis of HC and MS (ON and None-ON) cases. Our findings show that the texture features are powerful to diagnose MS cases. Furthermore, adding information of conventional thickness values to texture features improves considerably the discrimination between most of the target groups including HC vs. MS, HC vs. MS-None-ON, and HC vs. MS-ON.

COVID TV-Unet: Segmenting COVID-19 chest CT images using connectivity imposed Unet.

The novel corona-virus disease (COVID-19) pandemic has caused a major outbreak in more than 200 countries around the world, leading to a severe impact on the health and life of many people globally. By October 2020, more than 44 million people were infected, and more than 1,000,000 deaths were reported. Computed Tomography (CT) images can be used as an alternative to the time-consuming RT-PCR test, to detect COVID-19. In this work we propose a segmentation framework to detect chest regions in CT images, which are infected by COVID-19. An architecture similar to a Unet model was employed to detect ground glass regions on a voxel level. As the infected regions tend to form connected components (rather than randomly distributed voxels), a suitable regularization term based on 2D-anisotropic total-variation was developed and added to the loss function. The proposed model is therefore called "TV-Unet". Experimental results obtained on a relatively large-scale CT segmentation dataset of around 900 images, incorporating this new regularization term leads to a 2% gain on overall segmentation performance compared to the Unet trained from scratch. Our experimental analysis, ranging from visual evaluation of the predicted segmentation results to quantitative assessment of segmentation performance (precision, recall, Dice score, and mIoU) demonstrated great ability to identify COVID-19 associated regions of the lungs, achieving a mIoU rate of over 99%, and a Dice score of around 86%.