Optical Coherence Tomography Data Research Articles

Deep semi-supervised multiple instance learning with self-correction for DME classification from OCT images.

Supervised deep learning has achieved prominent success in various diabetic macular edema (DME) recognition tasks from optical coherence tomography (OCT) volumetric images. A common problematic issue that frequently occurs in this field is the shortage of labeled data due to the expensive fine-grained annotations, which increases substantial difficulty in accurate analysis by supervised learning. The morphological changes in the retina caused by DME might be distributed sparsely in B-scan images of the OCT volume, and OCT data is often coarsely labeled at the volume level. Hence, the DME identification task can be formulated as a multiple instance classification problem that could be addressed by multiple instance learning (MIL) techniques. Nevertheless, none of previous studies utilize unlabeled data simultaneously to promote the classification accuracy, which is particularly significant for a high quality of analysis at the minimum annotation cost. To this end, we present a novel deep semi-supervised multiple instance learning framework to explore the feasibility of leveraging a small amount of coarsely labeled data and a large amount of unlabeled data to tackle this problem. Specifically, we come up with several modules to further improve the performance according to the availability and granularity of their labels. To warm up the training, we propagate the bag labels to the corresponding instances as the supervision of training, and propose a self-correction strategy to handle the label noise in the positive bags. This strategy is based on confidence-based pseudo-labeling with consistency regularization. The model uses its prediction to generate the pseudo-label for each weakly augmented input only if it is highly confident about the prediction, which is subsequently used to supervise the same input in a strongly augmented version. This learning scheme is also applicable to unlabeled data. To enhance the discrimination capability of the model, we introduce the Student-Teacher architecture and impose consistency constraints between two models. For demonstration, the proposed approach was evaluated on two large-scale DME OCT image datasets. Extensive results indicate that the proposed method improves DME classification with the incorporation of unlabeled data and outperforms competing MIL methods significantly, which confirm the feasibility of deep semi-supervised multiple instance learning at a low annotation cost.

Ocular complications of diabetes mellitus in a pediatric population and proposals for screening and follow-up programs.

Diabetes mellitus (DM) is one of the world's greatest health emergencies of the 21st century. Ocular complications of DM are commonly chronic and progressive, but vision loss can be effectively prevented or delayed with early detection and timely treatment. Therefore, regular comprehensive ophthalmologic examinations are mandatory. Ophthalmic screening and dedicated follow-up for adults with DM are well established, whereas, there is no consensus on optimal recommendations for the pediatric population, reflecting the lack of clarity about the current burden of disease in this age group. To determine the epidemiology of ocular complications of diabetes and to assess optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) macular features in a pediatric population with DM. To review ophthalmological screening and follow-up plans for the diabetic pediatric population. Observational study. Retrospective consecutive cohort study of all 165 diabetic patients (330 eyes) aged 0-18 years, examined between January 2006 and September 2018 at the Pediatric Department of 'S. Maria della Misericordia' Udine Hospital who underwent at least one complete ophthalmologic examination at the Ophthalmology University Clinic at the Udine Hospital. OCT and OCTA data were available for 37 patients (72 eyes, 2 excluded). The associations between ocular complications and selected potential risk factors were evaluated by univariate analyses. No patient had signs of ocular diabetic complications or any macular morphological or micro-vascular impairment, regardless of any potential risk factor. The prevalence of strabismus and refractive errors in the study group, was found to be similar to non-diabetic pediatric populations. Screening and follow-up of ocular diabetic complications in children and adolescents could be performed less frequently than in adults with diabetes. There is no need to screen potentially treatable visual disorders in diabetic children earlier or more frequently than in the healthy children thus reducing time spent in hospital and permitting a better tolerance to medical examinations in diabetic pediatric patients. We described the OCT and OCTA patterns in a pediatric population with DM.

A Deep Ensemble Learning-Based CNN Architecture for Multiclass Retinal Fluid Segmentation in OCT Images

Retinal Fluids (fluid collections) develop because of the accumulation of fluid in the retina, which may be caused by several retinal disorders, and can lead to loss of vision. Optical coherence tomography (OCT) provides non-invasive cross-sectional images of the retina and enables the visualization of different retinal abnormalities. The identification and segmentation of retinal cysts from OCT scans is gaining immense attention since the manual analysis of OCT data is time consuming and requires an experienced ophthalmologist. Identification and categorization of the retinal cysts aids in establishing the pathophysiology of various retinal diseases, such as macular edema, diabetic macular edema, and age-related macular degeneration. Hence, an automatic algorithm for the segmentation and detection of retinal cysts would be of great value to the ophthalmologists. In this study, we have proposed a convolutional neural network-based deep ensemble architecture that can segment the three different types of retinal cysts from the retinal OCT images. The quantitative and qualitative performance of the model was evaluated using the publicly available RETOUCH challenge dataset. The proposed model outperformed the state-of-the-art methods, with an overall improvement of 1.8%.

The Incidence and the Clinical Course of Retinal Complications of Intracameral Cefuroxime in Cataract Surgery

Aim. To determine the incidence and the clinical course of retinal complications of intracameral administration of cefuroxime in minimally invasive cataract surgery.Methods. From 2016 to 2021, a prospective clinical study was conducted at the Volga District Medical Center of the Federal Medical and Biological Agency of Russia, which included patients with cataract in one or two eyes to be surgically treated. All patients received 1 mg of cefuroxime injected into the anterior chamber at the end of surgery. All patients underwent ophthalmological examination including evaluation of best corrected visual acuity with determination of logarithm of minimum angle of resolution (logMAR), tonometry, biomicroscopy, and ophthalmoscopy. Each patient before and the day after surgery underwent optical coherence tomography of the retina on a spectral optical tomograph RTVue-100 (Optovue). The dynamics of the condition was evaluated on days 3 and 7 after surgery.Results. Five cases of retinal complications of intracameral cefuroxime injection were identified during the 5-year study period. According to data of optical coherence tomography, retinal edema was localized in the internal nuclear layer of the retina, and the height of serous retinal detachment in the fovea area on the next day after surgery was 315.0 ± 11.0 µm and reduced statistically significantly to 59.8 ± 42.3 µm on the 3rd day after the intervention (p = 0.043). One week later, all patients had complete retinal adherence and recovery of visual function. Retinal edema did not recur in the long term after surgery.Conclusion. Serous retinal detachment with macular edema is the most common clinically relevant complication of intracameral antibiotic prophylaxis, which develops both in compliance with the dilution protocol and in overdose, and has a favourable prognosis.

ИЗМЕНЕНИЯ АУТОФЛЮОРЕСЦЕНЦИИ ГЛАЗНОГО ДНАУ МОЛОДЫХ ЛИЦ С РАЗНЫМИ ВИДАМИ РЕФРАКЦИИ. СООБЩЕНИЕ 1

Purpose:to assess the state of the macular region of the retina using the study of autofluorescence (AF) of theeye fundus in young subjects with high visual acuity and different types of clinical refraction.Material and methods.104 healthy volunteers (208 eyes), 70 females and 34 males, aged 20 to 30 years, average age (24,5± 0,4) годаy.о., were examined. All patients had high visual acuity (1,0 and higher) and there were no signs of pathology in the macular region, which was established ophthalmoscopically and confirmed by optical coherence tomography (OCT) data. Such methods of the examination were performed in all subjects as visometry with correction, refractometry, ophthalmobiomi-ocroscopy with Goldmann's lens, OCT in the 3D mode of the macular region of the fundus and the study of fundus-AF with typing on known patterns: normal pattern, minimal changes, focal changes and reticular pattern. The analysis was carried outin10 subgroups depending on the type, the degree of clinical refraction and the presence of astigmatism.Results.4 main patterns of AF were identified in the examined subjects: normal, minimal changes, focal changes and reticular. The most common pattern in all refractive groups was the reticular pattern, the frequency of which ranged from 41,7 to 88,9%. The least common pattern was normal, the frequency of which ranged from 4,2 to 33,3%. A significant differencebetween the values of the thickness of the retina in the foveal zone with the reticular pattern and its average group value in different refractive groups was not found.Conclusion.In young subjects with high visual acuity without clinical manifestation of pathology of the macular zone, AF-patterns other than the normal picture may be present. The reticular pattern is noted as the most common in all analyzed groups with various types of refraction. Further studies of early changes in fundus AF may make it possible to determine thepredictors of the development of dystrophic pathology of the macular zone.

Refractive Effect of Epithelial Remodelling in Myopia after Transepithelial Photorefractive Keratectomy.

(1) Introduction: We analysed epithelial changes after the treatment of moderate myopia with transepithelial photorefractive keratectomy. (2) Materials and Methods: We used optical coherence tomography data and analysed changes in the stroma and epithelium after ablation. We aimed to ascertain how much epithelium hyperplasia occurred after TransPRK; for this, we used data from 50 eyes treated with TransPRK with the AMARIS 1050 Hz, with a minimum follow-up of 4 months. (3) Results: The measured epithelial changes corresponded to a less than 0.1 ± 0.2D of spherical effect, less than 0.2 ± 0.2D of astigmatic effect, and less than 0.5 ± 0.2D of comatic effect. (4) Conclusions: The changes in epithelial thickness after aberration-neutral transepithelial photorefractive keratectomy for moderate myopia were very small, indicating a low level of epithelial hyperplasia without resembling a regression-inducing lentoid.

Longitudinal OCT texture analysis to assess the retinal changes in the triple‐transgenic mouse model of Alzheimer's disease

AbstractPurpose: This study aimed to investigate whether texture from optical coherence tomography (OCT) can address Alzheimer's disease (AD)‐related changes in the retina by evaluating differences to the wild‐type (WT) control group over time.Methods: The study included OCT data of WT mice and its age‐matched transgenic mice of AD (3xTg‐AD). Animals were imaged monthly from 1 month old up to 4 months old and at the ages of 8‐, 12‐, and 16 months old. Neuro‐retinal layers were analysed using various texture metrics, assuming that these could convey different views of unfolding changes. Two hundred forty texture metrics were computed from local binary patterns and some variants, local phase quantisation, wavelet features, and Gabor filters. The discriminative potential of the texture metrics was evaluated using the non‐parametric Mann–Whitney test with a 5% significance level at each age to determine the consistency in the texture difference between groups over time. The trajectories of the texture measurements of the WT and AD mice were compared to analyse the trends over time.Results: Texture metrics showing differences between the WT and AD groups from a time‐point onwards were found for all neuro‐retinal layers, with the retinal nerve fibre layer (RNFL) presenting the most significant number of metrics in these conditions. The most relevant differences between groups were found at 2 months old, while few metrics presented differences from 8 months old onwards. Consequently, this study demonstrated that texture metrics discriminate retinas of AD mice from the WT group based on OCT data. Furthermore, this study also demonstrated the parallel path of changes over time in both groups, with the vast majority of the metrics presenting the same type of variation with time.Conclusions: This study emphasizes the potential of the texture information in the OCT images to address AD‐related changes in the retina. We presented longitudinal texture analysis of WT and transgenic mice, where the texture differences were found at the youngest age of the study (1 month) and preserved the differences over the 16‐months study period. Those differences showed the same evolutionary trend for both groups.

Volumetric Characterization of Microvasculature in Ex Vivo Human Brain Samples By Serial Sectioning Optical Coherence Tomography.

Serial sectioning optical coherence tomography (OCT) enables accurate volumetric reconstruction of several cubic centimeters of human brain samples. We aimed to identify anatomical features of the ex vivo human brain, such as intraparenchymal blood vessels and axonal fiber bundles, from the OCT data in 3D, using intrinsic optical contrast. We developed an automatic processing pipeline to enable characterization of the intraparenchymal microvascular network in human brain samples. We demonstrated the automatic extraction of the vessels down to a 20 μm in diameter using a filtering strategy followed by a graphing representation and characterization of the geometrical properties of microvascular network in 3D. We also showed the ability to extend this processing strategy to extract axonal fiber bundles from the volumetric OCT image. This method provides a viable tool for quantitative characterization of volumetric microvascular network as well as the axonal bundle properties in normal and pathological tissues of the ex vivo human brain.

Space-variant image reconstruction via Cauchy regularisation: Application to Optical Coherence Tomography

We propose a smooth, non-convex and content-adaptive regularisation model for single-image super-resolution of murine Optical Coherence Tomography (OCT) data. We follow a sparse-representation approach where sparsity is modelled with respect to a suitable dictionary generated from high-resolution OCT data. To do so, we employ a pre-learned dictionary tailored to model α-stable statistics in the non-Gaussian case, i.e. α<2. The image reconstruction problem renders here particularly challenging due to the high level of noise degradation and to the heterogeneity of the data at hand. As a regulariser, we employ a separable Cauchy-type penalty. To favour adaptivity to image contents, we propose a space-variant modelling by which the local degree of non-convexity given by the local Cauchy shape parameter is estimated via maximum likelihood. For the solution of the reconstruction problem, we consider an extension of the cautious Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm where the descent direction is suitably updated depending on the local convexity of the functional. Our numerical results show that the combination of a space-variant modelling with a tailored optimisation strategy improves reconstruction results and allows for an effective segmentation with standard approaches.

Влияние интравитреального введения эпидермального фактора роста на морфофункциональное состояние глаза кролика

Purpose. To study the morphofunctional state of the rabbit eye after intravitreal injection of epidermal growth factor. Material and methods. In an experiment on rabbits, intravitreal course administration of Eberprot-P containing recombinant epidermal growth factor (EGF) at a dose of 100 ng was carried out. 7 and 30 days after each injection, biomicroscopy and ophthalmoscopy of the eye, optical coherence tomography (OCT) of the fundus in vivo were performed. Morphological studies were performed according to the generally accepted method with staining of histological preparations with hematoxylin and eosin. The cell density of the ganglionic layer, the inner and outer nuclear layers of the retina was assessed. SPSS software for Windows was used for statistical analysis. Results. Biomicroscopic and ophthalmoscopic studies of the intraocular structures of the experimental eyes did not reveal signs of edema or intraocular inflammation, toxic or irritant effects of intravitreal injection. There were no pathological changes in the form of cataracts, Tyndall's phenomenon in the anterior chamber moisture, vitreous opacities, retinal infiltrates. According to OCT data, the retinal thickness remained unchanged: 158 ± 5µm versus the control 158 ± 3µm (p = 1.0), no retinal wrinkling effects were detected. The morphological picture of the intraocular tissues of the eye after intravitreal injection was characterized by the absence of any pathological changes in the architectonics of the layers and cellular structures of the retina. Histomorphometric analysis showed no difference in the cell density of the ganglion layer, inner and outer nuclear layers of the retina of the experimental and control eyes of animals. Conclusion. Intravitreal application of EGF in rabbits does not cause intraocular specific inflammation or any destructive effects in the retina, which indicates the potential for its clinical use in the treatment of dystrophic retinal diseases. Keywords: epidermal growth factor, retina, intravitreal injection, morphology, histomorphometry

Retinal layer segmentation in a cohort of healthy children via optical coherence tomography.

High-resolution optical coherence tomography (OCT) allows the detection of macular pathology and involvement of the optic nerve in a wide spectrum of diseases. For the differentiation of diseased and healthy status, normal values of retinal layer segmentation are critical. Yet, normative values mostly cover adult populations with only sparse data for paediatric cohorts. We present data of retinal layer characteristics via OCT in a healthy paediatric cohort. This prospective cross-sectional study screened 75 healthy children (male = 42, female = 33, range 4-17 years) without visual problems. OCT was performed with a peripapillary ring and macula scan protocol to determine paediatric normative values for routine parameters (peripapillary retinal nerve fibre layer thickness (pRNFL), total macular volume (TMV), macular retinal thickness (RT)). The macula scan (6mm grid) was segmented using the device-inherent automated segmentation software (Heidelberg Eye Explorer) for retinal layers: RNFL, ganglion cell layer (GCL), inner plexiform layer (IPL), inner nuclear layer (INL), outer plexiform layer (OPL), outer nuclear layer (ONL) in 9 segments each and mean of the 9 segments. We obtained OCT data of 72 children with mean age 12.49 years (standard deviation, SD, 2.18; minimum 3.93). Mean global pRNFL was 102.20 μm (SD 8.24), mean TMV 8.81 mm3 (0.30) and mean RT (all segments) 318.22 μm (10.19). Segmented macular retinal layer thicknesses (mean of all segments) were: RNFL 27.67 μm (2.14), GCL 41.94 μm (2.50), IPL 34.97 μm (2.10), INL 35.18 μm (2.15), OPL 29.06 μm (2.24), ONL 68.35 μm (6.20). The OCT is a useful non-invasive imaging technique for the examination of the retina in children with short duration, high imaging resolution and no known adverse effects. Normative values may serve as a comparator for different neuropaediatric disorders and are first presented with this study using an up-to-date and standardized OCT imaging technique.

Human Coronary Plaque Optical Coherence Tomography Image Repairing, Multilayer Segmentation and Impact on Plaque Stress/Strain Calculations.

Coronary vessel layer structure may have a considerable impact on plaque stress/strain calculations. Most current plaque models use single-layer vessel structures due to the lack of available multilayer segmentation techniques. In this paper, an automatic multilayer segmentation and repair method was developed to segment coronary optical coherence tomography (OCT) images to obtain multilayer vessel geometries for biomechanical model construction. Intravascular OCT data were acquired from six patients (one male; mean age: 70.0) using a protocol approved by the local institutional review board with informed consent obtained. A total of 436 OCT slices were selected in this study. Manually segmented data were used as the gold standard for method development and validation. The edge detection method and cubic spline surface fitting were applied to detect and repair the internal elastic membrane (IEM), external elastic membrane (EEM) and adventitia-periadventitia interface (ADV). The mean errors of automatic contours compared to manually segmented contours were 1.40%, 4.34% and 6.97%, respectively. The single-layer mean plaque stress value from lumen was 117.91 kPa, 10.79% lower than that from three-layer models (132.33 kPa). On the adventitia, the single-layer mean plaque stress value was 50.46 kPa, 156.28% higher than that from three-layer models (19.74 kPa). The proposed segmentation technique may have wide applications in vulnerable plaque research.

Combining Optical Coherence Tomography and Optical Coherence Tomography Angiography Longitudinal Data for the Detection of Visual Field Progression in Glaucoma

To use longitudinal optical coherence tomography (OCT) and OCT angiography (OCTA) data to detect glaucomatous visual field (VF) progression with a supervised machine learning approach. Prospective cohort study. One hundred ten eyes of patients with suspected glaucoma (33.6%) and patients with glaucoma (66.4%) with a minimum of 5 24-2 VF tests and 3 optic nerve head and macula images over an average follow-up duration of 4.1 years were included. VF progression was defined using a composite measure including either a "likely progression event" on Guided Progression Analysis, a statistically significant negative slope of VF mean deviation or VF index, or a positive pointwise linear regression event. Feature-based gradient boosting classifiers were developed using different subsets of baseline and longitudinal OCT and OCTA summary parameters. The area under the receiver operating characteristic curve (AUROC) was used to compare the classification performance of different models. VF progression was detected in 28 eyes (25.5%). The model with combined baseline and longitudinal OCT and OCTA parameters at the global and hemifield levels had the best classification accuracy to detect VF progression (AUROC=0.89). Models including combined OCT and OCTA parameters had higher classification accuracy compared with those with individual subsets of OCT or OCTA features alone. Including hemifield measurements significantly improved the models' classification accuracy compared with using global measurements alone. Including longitudinal rates of change of OCT and OCTA parameters (AUROCs=0.80-0.89) considerably increased the classification accuracy of the models with baseline measurements alone (AUROCs=0.60-0.63). Longitudinal OCTA measurements complement OCT-derived structural metrics for the evaluation of functional VF loss in patients with glaucoma.

Triplet Cross-Fusion Learning for Unpaired Image Denoising in Optical Coherence Tomography.

Optical coherence tomography (OCT) is a widely-used modality in clinical imaging, which suffers from the speckle noise inevitably. Deep learning has proven its superior capability in OCT image denoising, while the difficulty of acquiring a large number of well-registered OCT image pairs limits the developments of paired learning methods. To solve this problem, some unpaired learning methods have been proposed, where the denoising networks can be trained with unpaired OCT data. However, majority of them are modified from the cycleGAN framework. These cycleGAN-based methods train at least two generators and two discriminators, while only one generator is needed for the inference. The dual-generator and dual-discriminator structures of cycleGAN-based methods demand a large amount of computing resource, which may be redundant for OCT denoising tasks. In this work, we propose a novel triplet cross-fusion learning (TCFL) strategy for unpaired OCT image denoising. The model complexity of our strategy is much lower than those of the cycleGAN-based methods. During training, the clean components and the noise components from the triplet of three unpaired images are cross-fused, helping the network extract more speckle noise information to improve the denoising accuracy. Furthermore, the TCFL-based network which is trained with triplets can deal with limited training data scenarios. The results demonstrate that the TCFL strategy outperforms state-of-the-art unpaired methods both qualitatively and quantitatively, and even achieves denoising performance comparable with paired methods. Code is available at: https://github.com/gengmufeng/TCFL-OCT.

Lipoprotein (a) is related to In-Stent neoatherosclerosis incidence rate and plaque vulnerability: Optical Coherence Tomography Study

BackgroundIn-stent neoatherosclerosis (ISNA) is an important reason for stent failure. High lipoprotein (a) [Lp (a)] level is an independent predictor of in-stent restenosis (ISR). To date, the relationship between the level of serum Lp (a) and the incidence rate and vulnerability of ISNA has never been verified.MethodsA total of 119 patients with 125 drug-eluting stent ISR lesions who underwent percutaneous coronary intervention guided by optical coherence tomography were enrolled in this study. According to their Lp (a) level, the patients were divided into two groups [high Lp (a) group ≥ 30 mg/dL, n = 47; or low Lp (a) group < 30 mg/dL, n = 72]. The clinical baseline, angiographic characteristics, and optical coherence tomography data of both groups were recorded and analyzed.ResultsNo significant differences in clinical and angiographic characteristics were found between the two groups (P > 0.05). The incidence rate of ISNA in the high Lp (a) group was significantly higher than that in the low Lp (a) group (94.0% [n = 47] vs. 52.0% [n = 39], P < 0.001). The incidence rate of thin-cap fibroatheroma in ISR lesions was significantly higher in the high Lp (a) group than in the low Lp (a) group (42% [n = 21] vs. 5.3% [n = 4], P < 0.001).ConclusionA high Lp (a) level is associated with the high incidence rate and plaque vulnerability of ISNA.

Robust Identification and Segmentation of the Outer Skin Layers in Volumetric Fingerprint Data.

Despite the long history of fingerprint biometrics and its use to authenticate individuals, there are still some unsolved challenges with fingerprint acquisition and presentation attack detection (PAD). Currently available commercial fingerprint capture devices struggle with non-ideal skin conditions, including soft skin in infants. They are also susceptible to presentation attacks, which limits their applicability in unsupervised scenarios such as border control. Optical coherence tomography (OCT) could be a promising solution to these problems. In this work, we propose a digital signal processing chain for segmenting two complementary fingerprints from the same OCT fingertip scan: One fingerprint is captured as usual from the epidermis ("outer fingerprint"), whereas the other is taken from inside the skin, at the junction between the epidermis and the underlying dermis ("inner fingerprint"). The resulting 3D fingerprints are then converted to a conventional 2D grayscale representation from which minutiae points can be extracted using existing methods. Our approach is device-independent and has been proven to work with two different time domain OCT scanners. Using efficient GPGPU computing, it took less than a second to process an entire gigabyte of OCT data. To validate the results, we captured OCT fingerprints of 130 individual fingers and compared them with conventional 2D fingerprints of the same fingers. We found that both the outer and inner OCT fingerprints were backward compatible with conventional 2D fingerprints, with the inner fingerprint generally being less damaged and, therefore, more reliable.

A Note on Macroscopic Optical Coherence Tomography Imaging Enabled 3D Scanning for Museum and Cultural Heritage Applications

ABSTRACT Optical coherence tomography (OCT) is a non-invasive imaging method that can be used to study the surface features and subsurface structures of delicate cultural heritage objects. However, the field of view of OCT severely limits the system’s scanning area. Previously, we have presented a hybrid scanning platform combined with an imaging stitching algorithm to achieve macroscopic OCT (macro-OCT) imaging. This paper further demonstrates the potential applications of the OCT data by rendering 3D volumetric data into standard virtual reality (VR), augmented reality (AR), and 3D printing formats. The 3D model can be 3D printed or interactively displayed through various platforms such as VR and AR headsets, smartphones, and web pages. The high-resolution 3D models obtained from the macro-OCT system can potentially improve the experience of accessing artworks online and assist individuals with visual impairments to study art through tactile feedback.

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

PurposeOptical 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.MethodsTo 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.ResultsTo 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.ConclusionsThis approach provides valuable data augmentation, which can help overcome key bottlenecks of limited data.Translational RelevanceBy addressing the challenge posed by limited data, the proposed method helps apply machine learning methods to diagnose neurodegenerative diseases from retinal imaging.

Послеоперационная деформация ИОЛ, методика выявления и влияние на послеоперационную рефракцию

Purpose. To determine IOL deformation in patients after phacoemulsification using optical coherence tomography (OCT) and to identify associated shift of postoperative refraction. Results. A "deflection" along the axis was detected during the OCT data analysis. In 38 cases (17.27 %) the center of the optical part of the lens was shifted toward the retina. The amplitude of this shift was 8.41 ± 8.28 mkm (from 0.00 to 30.00 mkm). At the same time patients with the "deflection" of the optical part of the IOL have large values of axial length (AL) accompanied with a great corneal segment diameter size, a deeper anterior chamber of the pseudophakic eye and its larger volume after IOL implantation. The obtained subjective refraction and the autorefractometry data in the form of a spherical equivalent were compared with the expected value of the calculated refraction using standard formulas. The average amplitude of the refraction shift was 0.25 diopters towards hypermetropia. Mathematical models based of logistic regression were constructed to predict the probability of the lens "deflection". The model based on only IOL power value (AUROC = 0.89 ± 0.07) stood out with good predictive quality and the possibility of interpretation. A high probability of IOL "deflection" was revealed when its power was not greater than ≥ 18.5 diopters. Another models was built based on sets of biometry data measured with Lenstar LS900: the axial length and anterior chamber depth of of the phakic eye, the diameter of the corneal segment and the average keratometry data calculated within the main meridians. This one have also high predictive quality: AUROC = 0.93 ± 0.06. Conclusion. Based on the data of optical coherence tomography, it is possible to detect the axial "deflection" of the optical part of the intraocular lens. The deflection of the IOL is reflected in the hypermetropia refractive shift relative to that calculated by the formulas of Hoffer Q, Holladay I and Haigis, which requires correction. To calculate the probability of displacement of the implanted IOL towards the retina, 2 logistic regression models with good predictive quality and the possibility of interpretation for the have been developed. Keywords: cataract, "deflection" along the axis, phacoemulsification, IOL deformation, optical coherence tomography

Прогнозирование рефракционного сдвига при выполнении фототерапевтической кератэктомии на примере пациента с субэпителиальной муциновой дистрофией роговицы (клинический случай)

Purpose. To present the treatment results of a patient with subepithelial mucinous corneal dystrophy by phototherapeutic keratectomy (PTK) using the excimer-laser system WaveLight EX500 (Alcon, USA) taking into account the induced myopic refractive shift. Material and methods. Patient S., 67 years old, with subepithelial mucinous corneal dystrophy and compound hyperopic astigmatism of both eyes. To determine the possibility of surgical treatment, in addition to the general ophthalmological examination, there were performed: optical coherence tomography (OCT) of the cornea to evaluate the total corneal thickness and the opacity depth; Corneal topography to evaluate total corneal refractive power and maximal anterior refractive power. FTK calculations were made basing on OCT data considering clinical refraction. The follow-up period was 3 months. Results. As a result of treatment, the corneal transparency of both eyes was restored. The ablation of the left eye corneal stroma with the standard PTK protocol to a 90-micron depth caused an increase in the patient’s refractive power by 3.87 D in spherical equivalent, which led to excessive myopic refraction. When performing PTK on the right eye, decrease of the ablation depth to 80-micron, as well as the two-stage formation of the anterior corneal profile with the formation of its wider «base» and a smaller optical zone diameter led to less refractive power increase of 2.62 D in spherical equivalent, which caused an emmetropic refraction in this case. Conclusion. The presented clinical case shows that various protocols for PTK implementation in patients with superficial corneal opacities can make it possible to not only achieve corneal transparency, but also to control the refractive shift and to define the final clinical refraction. Keywords: corneal dystrophy, phototherapeutic keratectomy (PTK), refractive surgery.