Segment Optical Coherence Tomography Images Research Articles

Inter-rater Reliability and Repeatability of Manual Anterior Segment Optical Coherence Tomography Image Grading in Keratoconus.

To determine the repeatability of corneal measurements from anterior segment optical coherence tomography (AS-OCT) images using ImageJ software in healthy eyes compared with eyes with keratoconus. Anterior segment OCT images of 25 eyes from 14 healthy subjects and 25 eyes from 15 subjects with keratoconus between the ages of 20 and 80 years were evaluated. Two trained observers used ImageJ to measure the central corneal cross-sectional area and anterior and posterior corneal arc lengths. MedCalc statistical software was used to generate the intraclass correlation coefficient (ICC) and Bland-Altman plots (BAPs) for observer measurements. Observer measurements of the central corneal cross-sectional area and anterior and posterior corneal arc lengths yielded an ICC >0.7. The ICC comparing the 3 parameters ranged from 0.75 to 0.84 for the control and 0.96 to 0.98 for the keratoconus group. No systematic proportional bias was detected by the BAPs. There were minimal differences between the 2 observer's measurements, with a mean of the difference of 0.3 mm2, 0 mm, and 0 mm, for the 3 measurements, respectively. This study suggests that ImageJ software is a repeatable and reliable tool in the analysis of corneal parameters from AS-OCT images among patients with keratoconus and may be applicable to AS-OCT imaging protocol development, an area of active keratoconus research.

Weakly supervised anomaly segmentation in retinal OCT images using an adversarial learning approach.

Lesion detection is a critical component of disease diagnosis, but the manual segmentation of lesions in medical images is time-consuming and experience-demanding. These issues have recently been addressed through deep learning models. However, most of the existing algorithms were developed using supervised training, which requires time-intensive manual labeling and prevents the model from detecting unaware lesions. As such, this study proposes a weakly supervised learning network based on CycleGAN for lesions segmentation in full-width optical coherence tomography (OCT) images. The model was trained to reconstruct underlying normal anatomic structures from abnormal input images, then the lesions can be detected by calculating the difference between the input and output images. A customized network architecture and a multi-scale similarity perceptual reconstruction loss were used to extend the CycleGAN model to transfer between objects exhibiting shape deformations. The proposed technique was validated using an open-source retinal OCT image dataset. Image-level anomaly detection and pixel-level lesion detection results were assessed using area-under-curve (AUC) and the Dice similarity coefficient, producing results of 96.94% and 0.8239, respectively, higher than all comparative methods. The average test time required to generate a single full-width image was 0.039 s, which is shorter than that reported in recent studies. These results indicate that our model can accurately detect and segment retinopathy lesions in real-time, without the need for supervised labeling. And we hope this method will be helpful to accelerate the clinical diagnosis process and reduce the misdiagnosis rate.

Livelayer: a semi-automatic software program for segmentation of layers and diabetic macular edema in optical coherence tomography images

Given the capacity of Optical Coherence Tomography (OCT) imaging to display structural changes in a wide variety of eye diseases and neurological disorders, the need for OCT image segmentation and the corresponding data interpretation is latterly felt more than ever before. In this paper, we wish to address this need by designing a semi-automatic software program for applying reliable segmentation of 8 different macular layers as well as outlining retinal pathologies such as diabetic macular edema. The software accommodates a novel graph-based semi-automatic method, called “Livelayer” which is designed for straightforward segmentation of retinal layers and fluids. This method is chiefly based on Dijkstra’s Shortest Path First (SPF) algorithm and the Live-wire function together with some preprocessing operations on the to-be-segmented images. The software is indeed suitable for obtaining detailed segmentation of layers, exact localization of clear or unclear fluid objects and the ground truth, demanding far less endeavor in comparison to a common manual segmentation method. It is also valuable as a tool for calculating the irregularity index in deformed OCT images. The amount of time (seconds) that Livelayer required for segmentation of Inner Limiting Membrane, Inner Plexiform Layer–Inner Nuclear Layer, Outer Plexiform Layer–Outer Nuclear Layer was much less than that for the manual segmentation, 5 s for the ILM (minimum) and 15.57 s for the OPL–ONL (maximum). The unsigned errors (pixels) between the semi-automatically labeled and gold standard data was on average 2.7, 1.9, 2.1 for ILM, IPL–INL, OPL–ONL, respectively. The Bland–Altman plots indicated perfect concordance between the Livelayer and the manual algorithm and that they could be used interchangeably. The repeatability error was around one pixel for the OPL–ONL and < 1 for the other two. The unsigned errors between the Livelayer and the manual algorithm was 1.33 for ILM and 1.53 for Nerve Fiber Layer–Ganglion Cell Layer in peripapillary B-Scans. The Dice scores for comparing the two algorithms and for obtaining the repeatability on segmentation of fluid objects were at acceptable levels.

Semi-supervised generative adversarial networks for closed-angle detection on anterior segment optical coherence tomography images: an empirical study with a small training dataset.

BackgroundSemi-supervised learning algorithms can leverage an unlabeled dataset when labeling is limited or expensive to obtain. In the current study, we developed and evaluated a semi-supervised generative adversarial networks (GANs) model that detects closed-angle on anterior segment optical coherence tomography (AS-OCT) images using a small labeled dataset.MethodsIn this cross-sectional study, a semi-supervised GANs model was developed for automatic closed-angle detection training on a small labeled and large unsupervised training dataset collected from the Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong (JSIEC). The closed-angle was defined as iris-trabecular contact beyond the scleral spur in AS-OCT images. We further developed two supervised deep learning (DL) models training on the same supervised dataset and the whole dataset separately. The semi-supervised GANs model and supervised DL models’ performance were compared on two independent testing datasets from JSIEC (515 images) and the Department of Ophthalmology (84 images), National University Health System, respectively. The diagnostic performance was assessed by evaluation matrices, including the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).ResultsFor closed-angle detection using clinician grading of AS-OCT imaging as the reference standard, the semi-supervised GANs model showed comparable performance, with AUCs of 0.97 (95% CI, 0.96–0.99) and 0.98 (95% CI, 0.94–1.00), compared with the supervised DL model (using the whole dataset) [AUCs of 0.97 (95% CI, 0.96–0.99), and 0.97 (95% CI, 0.94–1.00)]. When training on the same small supervised dataset, the semi-supervised GANs achieved performance at least as well as, if not better than, the supervised DL model [AUCs of 0.90 (95% CI: 0.84–0.96), and 0.92 (95% CI, 0.86–0.97)].ConclusionsThe semi-supervised GANs method achieves diagnostic performance at least as good as a supervised DL model when trained on small labeled datasets. Further development of semi-supervised learning methods could be useful within clinical and research settings.Trial registration numberChiCTR2000037892.

Confocal Microscopy and Anterior Segment Optical Coherence Tomography Imaging of the Ocular Surface and Bleb Morphology in Medically and Surgically Treated Glaucoma Patients: A Review.

Glaucoma patients often suffer from ocular surface disease (OSD) caused by the chronic administration of topical anti-glaucoma medications, especially in cases of long-term therapy with preserved or multiple drugs. Additionally, glaucoma surgery may determine ocular surface changes related to the formation and location of the filtering bleb, the application of anti-mitotic agents, and the post-operative wound-healing processes within the conjunctiva. Recently, several studies have evaluated the role of advanced diagnostic imaging technologies such as in vivo confocal microscopy (IVCM) and anterior segment-optical coherence tomography (AS-OCT) in detecting microscopic and macroscopic features of glaucoma therapy-related OSD. Their clinical applications are still being explored, with recent particular attention paid to analyzing the effects of new drug formulations and of minimally invasive surgical procedures on the ocular surface status. In this review, we summarize the current knowledge about the main changes of the ocular surface identified at IVCM and AS-OCT in glaucoma patients under medical therapy, or after surgical treatment.

Deep learning based lesion detection from anterior segment optical coherence tomography images and its application in the diagnosis of keratoconus

Objective: To developed an image analysis system of anterior segment optical coherence tomography (AS-OCT) examination results based on deep learning technology, and to evaluate its effect in identifying various types of corneal pathologies and quantified indices. Methods: A total of 4 026 patients (5 617 eyes), including 1 977 males and 2 049 females, aged (45±23) years, were enrolled in Qingdao Eye Hospital from January 2011 to August 2019. The AS-OCT images were used as a training dataset, which were labeled with location information of 16 corneal pathologies (including corneal epithelial defect, corneal epithelial thickening, corneal thinning and so on) by clinical experts, as well as the tissue stratification of the corneal epithelium and stroma. The labeled AS-OCT images were used to train the corneal pathology detection model and corneal stratification model based on deep convolutional neural network algorithm. Then 1 709 AS-OCT images of the affected eyes were collected as a validation dataset. Compared with the artificial labeling results, the accuracy, sensitivity and specificity were evaluated in the corneal pathology detection model, and the overlapping rate (Dice coefficient) between the labeled area of the model and the artificial labeling area was used to evaluate the corneal stratification model. Results: The results of 5 617 training sets showed that there were 1 472 cases of corneal epithelial defect, 2 416 cases of corneal epithelial thickening, 2 001 cases of corneal thinning, 780 cases of corneal lordosis, 2 064 cases of corneal thickening, 358 cases of subepithelial blisters, 486 cases of subepithelial opacity, 1 010 cases of corneal ulcer, 3 635 cases of stromal opacity, 1 060 cases of posterior elastic layer fold, 137 cases of posterior elastic layer detachment, 665 cases of keratic precipitate, 176 cases of corneal perforation, 127 cases of corneal foreign body, 299 cases of after lamellar keratoplasty (LKP) and 234 cases of after penetrating keratoplasty (PKP). Among 1 709 images, 1 596 were manually labeled. The average sensitivity and specificity of the corneal pathology detection model were 96.5% and 96.1% compared with the results of manual labeling. Fifteen samples were missed for detection, and the rate was 0.93%. The average Dice coefficients of the corneal stratification model for the corneal epithelium and stroma were 0.985 and 0.917, respectively. Conclusions: Our artificial intelligence-based diagnosis system with AS-OCT is able to give quantified information and location information of corneal lesions with high accuracy, which can help ophthalmologists improve the efficiency and accuracy of diagnosis. (Chin J Ophthalmol, 2021, 57: 447-453).

Segmentation of anterior segment boundaries in swept source OCT images

Quantification of the eye’s anterior segment morphology from optical coherence tomography (OCT) images is crucial for research and clinical decision-making, including the diagnosis and monitoring of many ocular diseases. Structural parameters, such as tissue thickness and area are the most common metrics used to quantify these medical images, and tissue segmentation is required before these metrics can be extracted. Currently, swept source OCT allows the capture of cross-sectional images that encompass the entire anterior segment with a high level of detail. However, the manual annotation of tissue boundaries is time-consuming. In this work, an algorithm based on graph-search theory combined with boundary-specific image transformation is applied for the segmentation of anterior segment OCT images. We demonstrate that the method can reliably segment 5 different tissue boundaries in healthy eyes with low boundary error (mean error below 1 pixel across all boundaries). The technique can be used to extract clinically relevant parameters such as central corneal and crystalline lens thickness as well as anterior chamber depth and area, with a high level of agreement with manual segmentation (normalized errors below 1.6%). The proposed method provides a tool that can support clinical and research OCT data analysis.

The Heritability of Primary Angle Closure Anatomic Traits and Predictors of Angle Closure in South Indian Siblings

To estimate the heritability of ocular biometric and anterior chamber morphologic parameters and to determine predictors of angle closure concordance in South Indian probands with angle closure and their siblings DESIGN: Prospective observational cohort study METHODS: Subjects received a standardized ophthalmic examination, A-scan ultrasonography, pachymetry, and anterior segment optical coherence tomography (ASOCT) imaging. Heritability was calculated using residual correlation coefficients adjusted for age, sex, and home setting. Concordant sibling pairs were defined as both proband and sibling with angle closure. Predictors of angle closure concordance among siblings were calculated using multivariable logistic regression models. A total of 345 sibling pairs participated. All anterior chamber parameters were highly heritable (P < .001 for all). Similarly, all iris parameters, axial length, lens thickness (LT), central corneal thickness, anterior lens curvature, lens vault (LV), spherical equivalent, and intraocular pressure were moderately to highly heritable (P < .004 for all). LV and LT were more heritable among concordant siblings (P < .05 for both). In contrast, ASOCT angle parameters had statistically insignificant heritability estimates. In multivariable analyses, siblings older than their probands were more likely to be concordant for angle closure (OR 1.05, 95% CI 1.01, 1.09; P=.02) and siblings with deeper anterior chamber depths (ACDs) compared to their proband were less likely to be concordant for angle closure (OR 0.74, 95% CI 0.64, 0.86; P < .001). Iris, anterior chamber, and lens parameters may be heritable whereas angle parameters were not. LT and LV may play important roles in the pathogenesis of angle closure. Siblings who are older or have a shallower ACD may need more careful disease monitoring.

Perspectives for preclinical mouse models of glaucoma after Boston keratoprosthesis type 1

Animal models of the Boston keratoprosthesis type 1 (KPro) are needed to study glaucoma damage after KPro implantation to control for confounding comorbidities common in human KPro recipients. The purpose of this study was to determine the feasibility of establishing a reproducible mouse model of glaucoma after KPro surgery, specifically that of a miniaturized mouse model of KPro (mKPro). In the present study, a total of 20 corneas of donor C57BL/6 mice (n = 10) were implanted in one eye of each recipient BALB/C mouse (n = 20), assembled as part of the mKPro, either with or without intraoperative lensectomy. Main feasibility outcomes consisted in incidence rates of loss of tone, capsule nicking, and lens extrusion, as well as acquisition of posterior segment optical coherence tomography (OCT) images. With lensectomy (n = 10), loss of ocular tone and retinal detachment occurred in 100% of mice. Without lensectomy (n = 10), capsule nicking and opening, as well as lens extrusion, occurred in 80% of mice. Causes of these complications included the large proportion of intraocular volume occupied by the lens, the shallow anterior chamber, and thus the lack of available intraocular volume to implant the KPro if the lens remains present. Successful mouse KPro surgery may require a great deal of practice to be useful as a reproducible model. Animal KPro models ought to be pursued further by research teams in future studies.

Assessment of Generative Adversarial Networks for Synthetic Anterior Segment Optical Coherence Tomography Images in Closed-Angle Detection

PurposeTo develop generative adversarial networks (GANs) that synthesize realistic anterior segment optical coherence tomography (AS-OCT) images and evaluate deep learning (DL) models that are trained on real and synthetic datasets for detecting angle closure.MethodsThe GAN architecture was adopted and trained on the dataset with AS-OCT images collected from the Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, synthesizing open- and closed-angle AS-OCT images. A visual Turing test with two glaucoma specialists was performed to assess the image quality of real and synthetic images. DL models, trained on either real or synthetic datasets, were developed. Using the clinicians’ grading of the AS-OCT images as the reference standard, we compared the diagnostic performance of open-angle vs. closed-angle detection of DL models and the AS-OCT parameter, defined as a trabecular-iris space area 750 µm anterior to the scleral spur (TISA750), in a small independent validation dataset.ResultsThe GAN training included 28,643 AS-OCT anterior chamber angle (ACA) images. The real and synthetic datasets for DL model training have an equal distribution of open- and closed-angle images (all with 10,000 images each). The independent validation dataset included 238 open-angle and 243 closed-angle AS-OCT ACA images. The image quality of real versus synthetic AS-OCT images was similar, as assessed by the two glaucoma specialists, except for the scleral spur visibility. For the independent validation dataset, both DL models achieved higher areas under the curve compared with TISA750. Two DL models had areas under the curve of 0.97 (95% confidence interval, 0.96–0.99) and 0.94 (95% confidence interval, 0.92–0.96).ConclusionsThe GAN synthetic AS-OCT images appeared to be of good quality, according to the glaucoma specialists. The DL models, trained on all-synthetic AS-OCT images, can achieve high diagnostic performance.Translational RelevanceThe GANs can generate realistic AS-OCT images, which can also be used to train DL models.

Anterior Chamber Characteristics, Endothelial Parameters, and Corneal Densitometry After Descemet Stripping Automated Endothelial Keratoplasty in Patients With Fuchs Dystrophy.

PurposeTo compare anterior segment parameters in patients with Fuchs endothelial dystrophy (FED) who underwent Descemet stripping automated endothelial keratoplasty (DSAEK) in one eye and no corneal surgery in the fellow eye.MethodsThis prospective study was conducted on 28 eyes of 14 patients with FED who underwent DSAEK in one eye at least one year prior (DSAEK group) and no corneal surgery in the fellow eye (control group). Each eye was analyzed with the anterior segment optical coherence tomography, specular microscopy, and Scheimpflug imaging systems. Data were compared between the two groups.ResultsThe mean age of the patients was 76.9 7.0 years. There were no statistically significant differences in the mean central corneal thickness (CCT), central anterior chamber depth, anterior chamber angle parameters, cylinder and keratometry values between two groups (all P-values 0.05). The paracentral corneal thickness, corneal volume, endothelial cell density, and hexagonal cell ratio measurements were statistically significantly higher in the DSAEK group than the control (all P-values < 0.05), and anterior chamber volume in the DSAEK group was significantly less than the control (P = 0.046). While posterior and total corneal densitometry values in the DSAEK group were statistically significantly lower than the control (P < 0.001 and P = 0.011, respectively), there were no statistically significant differences in the anterior or middle corneal densities (P = 0.108 and P = 0.134, respectively).ConclusionWe found that total corneal densitometry value decreased in DSAEK group. Although DSAEK surgery did not affect the anterior chamber angle parameters, it reduced the anterior chamber volume and increased the corneal volume and paracentral corneal thickness due to the addition of the DSAEK graft.

Corneal thickness changes in myopic children during and after short-term orthokeratology lens wear.

To evaluate thickness changes in the central and mid-peripheral cornea (CCT and mPCT), corneal epithelium (CET and mPET) and stroma (CST and mPST) of myopic children during and after short-term orthokeratology (ortho-k) lens wear, with conventional (CCF, 0.75D) and increased compression factors (ICF, 1.75D). This was a self-controlled case series study. Subjects wore a CCF lens in one eye and an ICF lens in the other. Anterior segment optical coherence tomography images were captured weekly for 1month during lens wear and for 2weeks after discontinuing lens wear. CCT and CET (central 3-mm cornea) and mPCT and mPET (within a 4-6mm diameter annulus) were measured. Stromal thickness (ST) was determined by subtracting epithelium thickness (ET) from corneal thickness (CT). The repeatability of the analytical software was also investigated on age-matched spectacle-wearing subjects (n=98). Excluding three outliers (>3S.D.s), the coefficient of repeatability and intraclass correlation coefficients of 98 spectacle-wearing subjects ranged from 2.63 to 4.64μm and from 0.90 to 0.99, respectively. For the weekly-change study, CCT and CET in both eyes were significantly thinner after lens wear (p<0.001) and CET thinning in the ICF eyes were significantly higher (p<0.02). CCT changes were mainly contributed by CET. CST, mPCT, mPET and mPST changes were not significant (p>0.20) in either eye. CT (all sublayers) rebounded to baseline values 2weeks after discontinuing lens wear (0.99>p>0.12). Significant reductions in CT and ET, but not ST, were observed within 1month of ortho-k lens wear. Wearing ICF lenses resulted in a higher reduction in CET. Corneal thickness changes were reversible after discontinuing lens wear.

Deep Learning for Detecting Corneal Pathologies From Anterior Segment Optical Coherence Tomography

Background: The corneal disease accounts for a mass of cases of visual impairment and blindness. Developing an automatic corneal pathologies detection system is critical in early management and vision preservation. Methods: A deep learning model, CorNet, was developed to identify 9 categories of corneal pathologies from anterior segment optical coherence tomography (AS-OCT) images. To develop the CorNet, 48644 AS-OCT images were collected and labeled by professional ophthalmologists. We evaluated the performance of CorNet by comparing the clinical readings of 6 ophthalmologists with different seniority who analyzed two independent testing datasets from different hospitals. Findings: By classifying 9 corneal pathologies, our CorNet achieved the area under receiver operating characteristics curve (AUC) of 0.972 (95% CI, 0.961-0.980) on the QDEH testing set (1,203 images) and the AUC of 0.972 ( 0.953-0.983 ) on the SDEH testing set (483 images). The average accuracy, sensitivity, and specificity values of CorNet were 0.947, 0.917, 0.956 on the QDEH testing set and 0.949, 0.932, 0.955 on the SDEH testing set, respectively. Compared to ophthalmologists, the statistical analysis revealed that CorNet was significantly higher than residents in sensitivity and achieved comparable performance in accuracy and specificity between attending ophthalmologists and residents. Interpretation: We constructed a large-scale AS-OCT dataset and developed a deep learning model for corneal pathologies detection. The CorNet achieved high accuracy and good generalization in multicenter clinical validation. Thus, it is a promising strategy for timely screening and treatment of corneal pathologies. Funding Information: Qingdao Science and Technology Demonstration and Guidance Project, under Fund No. 20-3-4-45-nsh. Declaration of Interests: All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest (such as honoraria; educational grants; participation in speakers' bureaus; membership, employment, consultancies, stock ownership, or other equity interest; and expert testimony or patent-licensing arrangements), or non-financial interest (such as personal or professional relationships, affiliations, knowledge or beliefs) in the subject matter or materials discussed in this manuscript. Ethics Approval Statement: This study adhered to the tenets of the Declaration of Helsinki, whereas approval was issued by the institutional review board of Qingdao Eye Hospital of Shandong First Medical University (No. QYLS 2020-07).

Quantitative characterization of human breast tissue based on deep learning segmentation of 3D optical coherence tomography images.

In this study, we performed dual-modality optical coherence tomography (OCT) characterization (volumetric OCT imaging and quantitative optical coherence elastography) on human breast tissue specimens. We trained and validated a U-Net for automatic image segmentation. Our results demonstrated that U-Net segmentation can be used to assist clinical diagnosis for breast cancer, and is a powerful enabling tool to advance our understanding of the characteristics for breast tissue. Based on the results obtained from U-Net segmentation of 3D OCT images, we demonstrated significant morphological heterogeneity in small breast specimens acquired through diagnostic biopsy. We also found that breast specimens affected by different pathologies had different structural characteristics. By correlating U-Net analysis of structural OCT images with mechanical measurement provided by quantitative optical coherence elastography, we showed that the change of mechanical properties in breast tissue is not directly due to the change in the amount of dense or porous tissue.

Tissue self-attention network for the segmentation of optical coherence tomography images on the esophagus.

Automatic segmentation of layered tissue is the key to esophageal optical coherence tomography (OCT) image processing. With the advent of deep learning techniques, frameworks based on a fully convolutional network are proved to be effective in classifying pixels on images. However, due to speckle noise and unfavorable imaging conditions, the esophageal tissue relevant to the diagnosis is not always easy to identify. An effective approach to address this problem is extracting more powerful feature maps, which have similar expressions for pixels in the same tissue and show discriminability from those from different tissues. In this study, we proposed a novel framework, called the tissue self-attention network (TSA-Net), which introduces the self-attention mechanism for esophageal OCT image segmentation. The self-attention module in the network is able to capture long-range context dependencies from the image and analyzes the input image in a global view, which helps to cluster pixels in the same tissue and reveal differences of different layers, thus achieving more powerful feature maps for segmentation. Experiments have visually illustrated the effectiveness of the self-attention map, and its advantages over other deep networks were also discussed.

Automated segmentation for whole human eye OCT image using RM multistage Mask R-CNN

Accurate segmentation of structures in whole human eye optical coherence tomography (OCT) images can improve the accuracy of disease diagnosis and ophthalmic biological parameter measurement. However, due to the complex features of the cornea, lens, and retina in the whole human eye OCT image and external interference, it is difficult to precisely extract the object features, which restricts the segmentation accuracy of whole human eye OCT images. A relation module (RM) multistage Mask Region-based Convolutional Neural Network (R-CNN) method for whole human eye OCT image segmentation is established. Based on Mask R-CNN, modulated deformable convolution is employed to produce an irregular receptive field and improve the adaptability of the network to the whole human eye OCT image’s object deformation. In the feature map extraction, the RM is combined to learn the position relation feature map of the human eye structures, which is utilized to enhance feature maps. A multistage mask is constructed in the segmentation branch, and the error is corrected through iterations of the mask to improve the segmentation accuracy of the whole human eye OCT image. Combined with the above structures, the RM multistage Mask R-CNN method is constructed for whole human eye OCT image segmentation. The model is trained by whole human eye OCT images and is applied to realize highly accurate whole human eye OCT image segmentation. Comparison experiments with K-means, U-net, and Feature Pyramid Networks (FPN)-deformable-mask R-CNN are performed to verify the segmentation accuracy and robustness of the proposed method to complex deformation and external interference.

Anterior segment optical coherence tomography imaging and ocular biometry in cataract patients with open angle glaucoma comorbidity

BackgroundAnterior chamber angle anatomy in perspective of ocular biometry may be the key element to intraocular pressure (IOP) reduction, especially in glaucoma patients. We aim to investigate anterior chamber angle and biometrical data prior to cataract surgery in patients with and without glaucoma comorbidity.Materials and methodsThis prospective comparative case-control study included 62 subjects (38 with cataract only and 24 with cataract and glaucoma). A full ophthalmic examination including, Goldmann applanation tonometry, anterior chamber swept source optical coherence tomography (DRI OCT Triton plus (Ver.10.13)) and swept source optical biometry (IOL Master 700 v1.7) was performed on all participants.ResultsWe found that ocular biometry parameters and anterior chamber parameters were not significantly different among groups. However, when we added cut-off values for narrow angles, we found that glaucoma group tended to have more narrow angles than control group. IOP was higher in glaucoma group despite all glaucoma patients having medically controlled IOP. In all subjects, anterior chamber parameters correlated well with lens position (LP), but less with relative lens position, while LP cut-off value of 5.1 mm could be used for predicting narrow anterior chamber angle parameters.ConclusionsCataract patients tend to develop narrow anterior chamber angles. Anterior chamber angle parameters have a positive moderate to strong relationship with lens position. LP may be used predicting narrow angles.

Automatic screening of tear meniscus from lacrimal duct obstructions using anterior segment optical coherence tomography images by deep learning.

We assessed the ability of deep learning (DL) models to distinguish between tear meniscus of lacrimal duct obstruction (LDO) patients and normal subjects using anterior segment optical coherence tomography (ASOCT) images. The study included 117 ASOCT images (19 men and 98 women; mean age, 66.6 ± 13.6 years) from 101 LDO patients and 113 ASOCT images (29 men and 84 women; mean age, 38.3 ± 19.9 years) from 71 normal subjects. We trained to construct 9 single and 502 ensemble DL models with 9 different network structures, and calculated the area under the curve (AUC), sensitivity, and specificity to compare the distinguishing abilities of these single and ensemble DL models. For the highest single DL model (DenseNet169), the AUC, sensitivity, and specificity for distinguishing LDO were 0.778, 64.6%, and 72.1%, respectively. For the highest ensemble DL model (VGG16, ResNet50, DenseNet121, DenseNet169, InceptionResNetV2, InceptionV3, and Xception), the AUC, sensitivity, and specificity for distinguishing LDO were 0.824, 84.8%, and 58.8%, respectively. The heat maps indicated that these DL models placed their focus on the tear meniscus region of the ASOCT images. The combination of DL and ASOCT images could distinguish between tear meniscus of LDO patients and normal subjects with a high level of accuracy. These results suggest that DL might be useful for automatic screening of patients for LDO.

Dielectric property measurements of corneal tissues for computational dosimetry of the eye in terahertz band in vivo and in vitro.

The dielectric constant of the normal corneal tissue of a rabbit eye was obtained in vitro in the range from approximately 0.1 to 1 THz, and the drying process on the eye surface exposed to high-power terahertz waves was investigated by in vivo reflectance measurement using terahertz time-domain spectroscopy. When the rabbit eye was exposed to terahertz waves at 162 GHz for 6 min with an irradiation power of 360 or 480 mW/cm2, the reflectance temporally increased and then decreased with a temperature increase. Based on multiple-reflection calculation using the dielectric constant and anterior segment optical coherence tomography images, those changes in reflectance were attributed to drying of the tear and epithelium of the cornea, respectively. Furthermore, the drying progressed over a temperature increase of around 5°C under our exposure conditions. These findings suggest that the possibility of eye damage increases with the progress of drying and that the setting of the eye surface conditions can be a cause of disagreement between computational and experimental data of absorbed energy under high-level irradiation because reflectance is related to terahertz wave penetration in the eye tissue. The time-domain spectroscopic measurements were useful for the acquisition of the dielectric constant as well as for the real-time monitoring of the eye conditions during exposure measurement.

A Novel Approach for Assessing Visual Impairment Caused by Intraocular Lens Opacification: High-Resolution Optical Coherence Tomography

To quantify in vitro straylight induced by intraocular lens (IOL) localized opacification using an anterior segment optical coherence tomography (OCT) device. Laboratory investigation. We obtained high-resolution OCT cross-section images of 44 explanted IOLs using a new in vitro application for an anterior segment OCT device, the Anterion (Heidelberg Engineering, Heidelberg, Germany). In 24 cases, the reason for IOL explantation was a centrally localized opacification, the sequela of a secondary ocular surgery. As a control, we used 20 IOLs removed after an IOL (sub-)luxation. Using image analysis, we found a threshold area value representing a metric for the amount of opacification in a region of interest in the IOL's central optic. We used a modified C-Quant straylight meter (Oculus, Wetzlar, Germany) to quantify light scattering. We derived a linear regression from calculating the correlation between the amount of opacification and straylight. We visualized different amounts of IOL opacification using the OCT device. The opacified lenses showed a mean threshold area of 6.7% ± 3.3% and mean straylight was 95.1 ± 75.6 deg2/sr. The clear group's mean threshold area was 2.0% ± 0.8% and 5.0 ± 3.4 deg2/sr mean straylight. Straylight correlated statistically significantly with the threshold area, with a correlation coefficient of R2=0.80, P < .001. This high-resolution OCT imaging technique can be used to visualize IOL opacities. The amount of opacification correlated well with the straylight induced by the lens. Anterior segment OCT imaging might be used in the future as a tool for predicting the extent of visual impairment and aid clinicians to quantify patients' complaints.