Multi-granularity learning of explicit geometric constraint and contrast for label-efficient medical image segmentation and differentiable clinical function assessment.

Automated segmentation is a challenging task in medical image analysis that usually requires a large amount of manually labeled data. However, most current supervised learning based algorithms suffer from insufficient manual annotations, posing a significant difficulty for accurate and robust segmentation. In addition, most current semi-supervised methods lack explicit representations of geometric structure and semantic information, restricting segmentation accuracy. In this work, we propose a hybrid framework to learn polygon vertices, region masks, and their boundaries in a weakly/semi-supervised manner that significantly advances geometric and semantic representations. Firstly, we propose multi-granularity learning of explicit geometric structure constraints via polygon vertices (PolyV) and pixel-wise region (PixelR) segmentation masks in a semi-supervised manner. Secondly, we propose eliminating boundary ambiguity by using an explicit contrastive objective to learn a discriminative feature space of boundary contours at the pixel level with limited annotations. Thirdly, we exploit the task-specific clinical domain knowledge to differentiate the clinical function assessment end-to-end. The ground truth of clinical function assessment, on the other hand, can serve as auxiliary weak supervision for PolyV and PixelR learning. We evaluate the proposed framework on two tasks, including optic disc (OD) and cup (OC) segmentation along with vertical cup-to-disc ratio (vCDR) estimation in fundus images; left ventricle (LV) segmentation at end-diastolic and end-systolic frames along with ejection fraction (LVEF) estimation in two-dimensional echocardiography images. Experiments on nine large-scale datasets of the two tasks under different label settings demonstrate our model's superior performance on segmentation and clinical function assessment.

Using Deep Learning to Segment Retinal Vascular Leakage and Occlusion in Retinal Vasculitis.

PURPOSE: Retinal vasculitis (RV) is characterised by retinal vascular leakage, occlusion or both on fluorescein angiography (FA). There is no standard scheme available to segment RV features. We aimed to develop a deep learning model to segment both vascular leakage and occlusion in RV. METHODS: Four hundred and sixty-three FA images from 82 patients with retinal vasculitis were used to develop a deep learning model, in 60:20:20 ratio for training:validation:testing. Parameters, including deep learning architectures (DeeplabV3+, UNet++ and UNet), were altered to find the best binary segmentation model separately for retinal vascular leakage and occlusion, using a Dice score to determine the reliability of each model. RESULTS: Our best model for vascular leakage had a Dice score of 0.6279 (95% confidence interval (CI) 0.5584-0.6974). For occlusion, the best model achieved a Dice score of 0.6992 (95% CI 0.6109-0.7874). CONCLUSION: Our RV segmentation models could perform reliable segmentation for retinal vascular leakage and occlusion in FAs of RV patients.

Deep segmentation of OCTA for evaluation and association of changes of retinal microvasculature with Alzheimer's disease and mild cognitive impairment.

BACKGROUND: Optical coherence tomography angiography (OCTA) enables fast and non-invasive high-resolution imaging of retinal microvasculature and is suggested as a potential tool in the early detection of retinal microvascular changes in Alzheimer's Disease (AD). We developed a standardised OCTA analysis framework and compared their extracted parameters among controls and AD/mild cognitive impairment (MCI) in a cross-section study. METHODS: We defined and extracted geometrical parameters of retinal microvasculature at different retinal layers and in the foveal avascular zone (FAZ) from segmented OCTA images obtained using well-validated state-of-the-art deep learning models. We studied these parameters in 158 subjects (62 healthy control, 55 AD and 41 MCI) using logistic regression to determine their potential in predicting the status of our subjects. RESULTS: In the AD group, there was a significant decrease in vessel area and length densities in the inner vascular complexes (IVC) compared with controls. The number of vascular bifurcations in AD is also significantly lower than that of healthy people. The MCI group demonstrated a decrease in vascular area, length densities, vascular fractal dimension and the number of bifurcations in both the superficial vascular complexes (SVC) and the IVC compared with controls. A larger vascular tortuosity in the IVC, and a larger roundness of FAZ in the SVC, can also be observed in MCI compared with controls. CONCLUSION: Our study demonstrates the applicability of OCTA for the diagnosis of AD and MCI, and provides a standard tool for future clinical service and research. Biomarkers from retinal OCTA images can provide useful information for clinical decision-making and diagnosis of AD and MCI.

A Systematic Review on Retinal Biomarkers to Diagnose Dementia from OCT/OCTA Images.

Background: Traditional methods for diagnosing dementia are costly, time-consuming, and somewhat invasive. Since the retina shares significant anatomical similarities with the brain, retinal abnormalities detected via optical coherence tomography (OCT) and OCT angiography (OCTA) have been studied as a potential non-invasive diagnostic tool for neurodegenerative disorders; however, the most effective retinal changes remain a mystery to be unraveled in this review. Objective: This study aims to explore the relationship between retinal abnormalities in OCT/OCTA images and cognitive decline as well as evaluating biomarkers' effectiveness in detecting neurodegenerative diseases. Methods: A systematic search was conducted on PubMed, Web of Science, and Scopus until December 2022, resulted in 64 papers using agreed search keywords, and inclusion/exclusion criteria. Results: The superior peripapillary retinal nerve fiber layer (pRNFL) is a trustworthy biomarker to identify most Alzheimer's disease (AD) cases; however, it is inefficient when dealing with mild AD and mild cognitive impairment (MCI). The global pRNFL (pRNFL-G) is another reliable biomarker to discriminate frontotemporal dementia from mild AD and healthy controls (HCs), moderate AD and MCI from HCs, as well as identifing pathological Aß42/tau in cognitively healthy individuals. Conversely, pRNFL-G fails to realize mild AD and the progression of AD. The average pRNFL thickness variation is considered a viable biomarker to monitor the progression of AD. Finally, the superior and average pRNFL thicknesses are considered consistent for advanced AD but not for early/mild AD. Conclusions: Retinal changes may indicate dementia, but further research is needed to confirm the most effective biomarkers for early and mild AD.

Prospective clinical study of retinal microvascular alteration after ICL implantation.

Purpose: To evaluate the retinal microvascular alteration after implantable collamer lens (ICL) implantation in moderate to high myopia patients using quantitative optical coherence tomography angiography (OCTA). Methods: This prospective cohort study included 50 eyes of 25 patients with preoperative spherical equivalent ≥ -3.00 D. Patients underwent bilateral ICL implantation at the Department of Ophthalmology, Peking University Third Hospital, from November 2018 to July 2019. OCTA was used to image the superficial and deep retinal capillary plexuses before ICL implantation surgery and at 3 months follow-up. Results: There was no significant difference in the microvascular density within each annular zone and all quadrantal zones of the superficial and deep layers found in myopia patients before and after ICL surgery. Conclusion: Levels of microvascular density in retinal capillary plexuses were stable, as detected by the OCTA, showing the high security of ICL implantation, which would not leave adverse effects on retinal microvasculature in myopia patients.

Serum Uric Acid Levels Are Associated With Macula Microvasculature Changes In Hypertensive White Matter Hyperintensity Patients.

PURPOSE: To characterize the macula microvasculature using fractal dimension (FD) in hypertensive white matter hyperintensity (WMH) participants and explore the association between the microvascular changes and serum uric acid levels. METHODS: Thirty-eight WMH participants were dementia and stroke-free, and 37 healthy controls were enrolled. Optical coherence tomographic angiography (OCTA) was used to image the superficial vascular complex (SVC), deep vascular complex (DVC), and inner vascular complex (IVC) in a 2.5-mm diameter concentric circle (excluding the foveal avascular zone FAZ). A commercial algorithm was used to quantify the complexity and density of the three capillary layers by fractal analysis. RESULTS: WMH participants showed significantly lower FD value in the SVC (P = 0.002), DVC (P < 0.001) and IVC (P = 0.012) macula microvasculature compared with control group. After adjusting for risk factors (hypertension, diabetes, age and gender) SVC (P = 0.035) and IVC (P = 0.030) significantly correlated with serum uric acid. CONCLUSION: Serum uric acid levels are associated with microvascular changes in WMH. Fractal dimension based on OCTA imaging could help quantitatively characterize the macula microvasculature changes in WMH and may be a potential screening tool to detect serum uric acid level changes.

Characterization of the Retinal Microvasculature and FAZ Changes in Ischemic Stroke and Its Different Types.

Purpose: This study aimed to assess morphological changes in the retinal microvasculature and foveal avascular zone (FAZ) in patients with ischemic stroke and its different subtypes. Methods: Thirty-three patients with ischemic stroke (14 with nonlacunar infarction and 19 with lacunar infarction) and 27 control participants were enrolled in this study. Based on optical coherence tomography angiography (OCTA), three vascular parameters, including vascular area density, vascular fractal dimension (VFD), and vascular orientation distribution (VOD), and four FAZ-related parameters, including FAZ area, FAZ axis ratio (FAR), FAZ circularity (FC), and FAZ roundness, in the superficial capillary plexus (SCP) and deep capillary plexus (DCP) were extracted and analyzed. Results: Logistic regression results showed that worse best-corrected visual acuity (odds ratio [OR], 0.21), higher FAR (OR, 2.77) and lower FC (OR, 0.36) of the DCP were associated with ischemic stroke. Furthermore, lower VOD of the SCP was significantly associated with lacunar infarction compared with nonlacunar infarction. Conclusions: Our study shows that the FAR and FC of the DCP may be potential biomarkers of ischemic stroke. Moreover, we demonstrated that OCT showed specific damage patterns in retinal microvascular and macular morphology in different subtypes of ischemic stroke. Translational Relevance: This work lays the foundation for the pathophysiological characteristics of cerebrovascular diseases assisted by retinal imaging and artificial intelligence.

Retinal microvasculature and imaging markers of brain frailty in normal aging adults.

Background: The retina and brain share a similar embryologic origin, blood barriers, and microvasculature features. Thus, retinal imaging has been of interest in the aging population to help in the early detection of brain disorders. Imaging evaluation of brain frailty, including brain atrophy and markers of cerebral small vessel disease (CSVD), could reflect brain health in normal aging, but is costly and time-consuming. In this study, we aimed to evaluate the retinal microvasculature and its association with radiological indicators of brain frailty in normal aging adults. Methods: Swept-source optical coherence tomography angiography (SS-OCTA) and 3T-MRI brain scanning were performed on normal aging adults (aged ≥ 50 years). Using a deep learning algorithm, microvascular tortuosity (VT) and fractal dimension parameter (Dbox) were used to evaluate the superficial vascular complex (SVC) and deep vascular complex (DVC) of the retina. MRI markers of brain frailty include brain volumetric measures and CSVD markers that were assessed. Results: Of the 139 normal aging individuals included, the mean age was 59.43 ± 7.31 years, and 64.0% (n = 89) of the participants were females. After adjustment of age, sex, and vascular risk factors, Dbox in the DVC showed a significant association with the presence of lacunes (ß = 0.58, p = 0.007), while VT in the SVC significantly correlated with the score of cerebral deep white matter hyperintensity (ß = 0.31, p = 0.027). No correlations were found between brain volumes and retinal microvasculature changes (P > 0.05). Conclusion: Our report suggests that imaging of the retinal microvasculature may give clues to brain frailty in the aging population.

Evaluation of Ocular Surface Characteristics in Dry Eye Disease With and Without Soft Contact Lens Wear: A Comparative Study.

OBJECTIVES: To investigate ocular surface alterations and in vivo confocal microscopic characteristics of the cornea in dry eye disease (DED) with contact lens wear (CLW). METHODS: Sixty participants were divided into three groups: DED with CLW (n=20), DED without CLW (n=20), and normal control (n=20). Ocular surface parameters were evaluated. Basal tears and in vivo confocal microscopy images of the cornea were collected. Multiplex bead analysis was used to assess interleukin (IL)-6, IL-1ß, tumor necrosis factor (TNF)-α, nerve growth factor (NGF), and substance P (SP) in tears. Nerve morphology and dendritic cell density in corneal subbasal nerve images were calculated. RESULTS: The DED with CLW group showed significantly higher ocular surface staining scores ( P =0.022) and higher levels of IL-1ß, NGF, and SP in tears ( P =0.014, P =0.004 and P =0.025) than the DED without CLW group. Corneal dendritic cell density in the DED with CLW group was significantly higher than that in the normal controls ( P =0.001) and DED without CLW group ( P =0.043). Tear cytokine levels of IL-1ß, NGF, and SP were correlated with ocular surface parameters in the DED with CLW group. Moreover, the years of CLW were positively correlated with corneal dendritic cell density (r=0.527, P =0.017) and negatively correlated with corneal nerve density (r=-0.511, P =0.021). CONCLUSIONS: Patients with DED with CLW showed greater epithelial damage, elevated inflammatory cytokines and neuromediators in tears, and higher corneal dendritic cell density than patients with DED without CLW. The immune and nervous systems may be involved in contact lens-related DED.

Differences in retinal microvasculature between large artery atherosclerosis and small artery disease: an optical coherence tomography angiography study.

Purpose: Recent reports suggest retinal microvasculature mirror cerebral microcirculation. Using optical coherence tomography angiography (OCTA), we investigated the retinal microvasculature differences between ischemic stroke patients with large artery atherosclerosis (LAA) and small artery disease (SAD). Methods: All patients underwent MR imaging and were classified as SAD and LAA; LAA was subdivided into anterior LAS and posterior LAS depending on the location. Swept-source OCTA (SS-OCTA) was used to image and segment the retina into the superficial vascular complex (SVC) and deep vascular complex (DVC) in a 6 × 6 mm area around the fovea. A deep learning algorithm was used to assess the vessel area density (VAD, %) in the retinal microvasculature. Results: Fifty-eight (mean age = 60.26 ± 10.88 years; 81.03% males) were LAA while 64 (mean age = 55.58 ± 10.34 years; 85.94% males) were SAD. LAS patients had significantly reduced VAD in the DVC (P = 0.022) compared to SAD patients; the VAD in the SVC did not show any significant difference between the two groups (P = 0.580). Anterior LAA ischemic stroke showed significantly lower VAD (P = 0.002) in the SVC compared with posterior LAS patients. There was no significant difference in the DVC between the two groups (P = 0.376). Conclusions: We found LAA patients had significantly reduced DVC density compared with SAD; we also showed anterior LAA patients had significantly reduced SVC density compared with posterior LAA. These findings suggest retinal imaging has the potential to be used to detect microvasculature changes in subtypes of ischemic stroke.

Automatic Sequence-Based Network for Lung Diseases Detection in Chest CT.

OBJECTIVE: To develop an accurate and rapid computed tomography (CT)-based interpretable AI system for the diagnosis of lung diseases. BACKGROUND: Most existing AI systems only focus on viral pneumonia (e.g., COVID-19), specifically, ignoring other similar lung diseases: e.g., bacterial pneumonia (BP), which should also be detected during CT screening. In this paper, we propose a unified sequence-based pneumonia classification network, called SLP-Net, which utilizes consecutiveness information for the differential diagnosis of viral pneumonia (VP), BP, and normal control cases from chest CT volumes. METHODS: Considering consecutive images of a CT volume as a time sequence input, compared with previous 2D slice-based or 3D volume-based methods, our SLP-Net can effectively use the spatial information and does not need a large amount of training data to avoid overfitting. Specifically, sequential convolutional neural networks (CNNs) with multi-scale receptive fields are first utilized to extract a set of higher-level representations, which are then fed into a convolutional long short-term memory (ConvLSTM) module to construct axial dimensional feature maps. A novel adaptive-weighted cross-entropy loss (ACE) is introduced to optimize the output of the SLP-Net with a view to ensuring that as many valid features from the previous images as possible are encoded into the later CT image. In addition, we employ sequence attention maps for auxiliary classification to enhance the confidence level of the results and produce a case-level prediction. RESULTS: For evaluation, we constructed a dataset of 258 chest CT volumes with 153 VP, 42 BP, and 63 normal control cases, for a total of 43,421 slices. We implemented a comprehensive comparison between our SLP-Net and several state-of-the-art methods across the dataset. Our proposed method obtained significant performance without a large amount of data, outperformed other slice-based and volume-based approaches. The superior evaluation performance achieved in the classification experiments demonstrated the ability of our model in the differential diagnosis of VP, BP and normal cases.

Superficial Macula Capillary Complexity Changes Are Associated With Disability in Neuromyelitis Optica Spectrum Disorders.

Purpose: We examined the macular microvascular changes of the macula in neuromyelitis optica spectrum disorder (NMOSD) patients and its association with their disability and other clinical variables. Methods: Thirty-four NMOSD (13 patients without optic neuritis, NMOSD-NON, and 21 patients with a history of optic neuritis, NMOSD-ON) and 44 healthy controls (HCs) were included in the study. Optical coherence tomographic angiography (OCTA) was used to image the superficial (SCP), deep (DCP), and whole capillary plexus (WCP) in a 2.5-mm-diameter concentric circle [excluding the foveal avascular zone (FAZ)]. An algorithm (Dbox) was used to quantify the complexity of the three capillary layers by fractal analysis. We also evaluated the expanded disability scale status (EDSS). Results: Dbox values were significantly reduced in SCP (p < 0.001), DCP (p < 0.001), and WCP (p = 0.003) of NMOSD when compared with HCs. Dbox values were significantly reduced in NMOSD eyes with optic neuritis when compared with healthy controls (p < 0.001) and eyes without optic neuritis (p = 0.004) in the SCP. In the DCP, eyes with optic neuritis showed significantly reduced Dbox values when compared with eyes without optic neuritis (p = 0.016) and healthy controls (p < 0.001); eyes without optic neuritis showed significantly reduced Dbox values (p = 0.007) in the DCP when compared with healthy controls. A significant negative correlation (Rho = -0.475, p = 0.005) was shown between the superficial macula Dbox values and the EDSS in NMOSD patients. Additionally, a negative correlation (Rho = -0.715, p = 0.006) was seen in the superficial Dbox values in [e]eyes without optic neuritis and EDSS. Conclusions: Macular microvascular damage in the superficial plexus is associated with disability in NMOSD. Macular microvascular alterations arise independently of the occurrence of ON in NMOSD.

Outer Retinal Layer Thickness Changes in White Matter Hyperintensity and Parkinson's Disease.

Purpose: To investigate the thickness changes of outer retinal layers in subjects with white matter hyperintensities (WMH) and Parkinson's Disease (PD). Methods: 56 eyes from 31 patients with WMH, 11 eyes from 6 PD patients, and 58 eyes from 32 healthy controls (HC) were enrolled in this study. A macular-centered scan was conducted on each participant using a spectral-domain optical coherence tomography (SD-OCT) device. After speckle noise reduction, a state-of-the-art deep learning method (i.e., a context encoder network) was employed to segment the outer retinal layers from OCT B-scans. Thickness quantification of the outer retinal layers was conducted on the basis of the segmentation results. Results: WMH patients had significantly thinner Henle fiber layers, outer nuclear layers (HFL+ONL) and photoreceptor outer segments (OS) than HC (p = 0.031, and p = 0.005), while PD patients showed a significant increase of mean thickness in the interdigitation zone and the retinal pigment epithelium/Bruch complex (IZ+RPE) (19.619 ± 4.626) compared to HC (17.434 ± 1.664). There were no significant differences in the thickness of the outer plexiform layer (OPL), the myoid and ellipsoid zone (MEZ), and the IZ+RPE layer between WMH and HC subjects. Similarly, there were also no obvious differences in the thickness of the OPL, HFL+ONL, MEZ and the OS layer between PD and HC subjects. Conclusion: Thickness changes in HFL+ONL, OS, and IZ+RPE layers may correlate with brain-related diseases such as WMH and PD. Further longitudinal study is needed to confirm HFL+ONL/OS/IZ+RPE layer thickness as potential biomarkers for detecting certain brain-related diseases.

Quantification of Increased Corneal Subbasal Nerve Tortuosity in Dry Eye Disease and Its Correlation With Clinical Parameters.

Purpose: This study quantified corneal subbasal nerve tortuosity in dry eye disease (DED) and investigated its correlation with clinical parameters by proposing an aggregated measure of tortuosity (Tagg). Methods: The sample consisted of 26 eyes of patients with DED and 23 eyes of healthy volunteers, which represented separately the dry eye group and the control group. Clinical evaluation of DED and in vivo confocal microscopy analysis of the central cornea were performed. Tagg incorporated six metrics of tortuosity. Corneal subbasal nerve images of subjects and a validation data set were analyzed using Tagg. Spearman's rank correlation was performed on Tagg and clinical parameters. Results: Tagg was validated using 1501 corneal nerve images. Tagg was higher in patients with DED than in healthy volunteers (P < 0.001). Tagg was positively correlated with the ocular surface disease index (r = 0.418, P = 0.003) and negatively correlated with tear breakup time (r = -0.398, P = 0.007). There was no correlation between Tagg and visual analog scale scores, corneal fluorescein staining scores, or the Schirmer I test. Conclusions: Tagg was validated for quantification of corneal subbasal nerve tortuosity and was higher in patients with DED than in healthy volunteers. A higher Tagg may be linked to ocular discomfort, visual function disturbance, and tear film instability. Translational Relevance: Corneal subbasal nerve tortuosity is a potential biomarker for corneal neurobiology in DED.

ROSE: A Retinal OCT-Angiography Vessel Segmentation Dataset and New Model.

Optical Coherence Tomography Angiography (OCTA) is a non-invasive imaging technique that has been increasingly used to image the retinal vasculature at capillary level resolution. However, automated segmentation of retinal vessels in OCTA has been under-studied due to various challenges such as low capillary visibility and high vessel complexity, despite its significance in understanding many vision-related diseases. In addition, there is no publicly available OCTA dataset with manually graded vessels for training and validation of segmentation algorithms. To address these issues, for the first time in the field of retinal image analysis we construct a dedicated Retinal OCTA SEgmentation dataset (ROSE), which consists of 229 OCTA images with vessel annotations at either centerline-level or pixel level. This dataset with the source code has been released for public access to assist researchers in the community in undertaking research in related topics. Secondly, we introduce a novel split-based coarse-to-fine vessel segmentation network for OCTA images (OCTA-Net), with the ability to detect thick and thin vessels separately. In the OCTA-Net, a split-based coarse segmentation module is first utilized to produce a preliminary confidence map of vessels, and a split-based refined segmentation module is then used to optimize the shape/contour of the retinal microvasculature. We perform a thorough evaluation of the state-of-the-art vessel segmentation models and our OCTA-Net on the constructed ROSE dataset. The experimental results demonstrate that our OCTA-Net yields better vessel segmentation performance in OCTA than both traditional and other deep learning methods. In addition, we provide a fractal dimension analysis on the segmented microvasculature, and the statistical analysis demonstrates significant differences between the healthy control and Alzheimer's Disease group. This consolidates that the analysis of retinal microvasculature may offer a new scheme to study various neurodegenerative diseases.

Corneal nerve tortuosity grading via ordered weighted averaging-based feature extraction.

PURPOSE: Tortuosity of corneal nerve fibers acquired by in vivo Confocal Microscopy (IVCM) are closely correlated to numerous diseases. While tortuosity assessment has conventionally been conducted through labor-intensive manual evaluation, this warrants an automated and objective tortuosity assessment of curvilinear structures. This paper proposes a method that extracts the image-level features for corneal nerve tortuosity grading. METHODS: For an IVCM image, all corneal nerve fibers are first segmented and then, their tortuosity are calculated by morphological measures. The ordered weighted averaging (OWA) approach, and the k-Nearest-Neighbor guided dependent ordered weighted averaging (kNNDOWA) approach are proposed to aggregate the tortuosity values and form a set of extracted features. This is followed by running the Wrapper method, a supervised feature selection, with an aim to identify the most informative attributes for tortuosity grading. RESULTS: Validated on a public and an in-house benchmark data sets, experimental results demonstrate superiority of the proposed method over the conventional averaging and length-weighted averaging methods with performance gain in accuracy (15.44% and 14.34%, respectively). CONCLUSIONS: The simultaneous use of multiple aggregation operators could extract the image-level features that lead to more stable and robust results compared with that using average and length-weighted average. The OWA method could facilitate the explanation of derived aggregation behavior through stress functions. The kNNDOWA method could mitigate the effects of outliers in the image-level feature extraction.

Automated Tortuosity Analysis of Nerve Fibers in Corneal Confocal Microscopy.

Precise characterization and analysis of corneal nerve fiber tortuosity are of great importance in facilitating examination and diagnosis of many eye-related diseases. In this paper we propose a fully automated method for image-level tortuosity estimation, comprising image enhancement, exponential curvature estimation, and tortuosity level classification. The image enhancement component is based on an extended Retinex model, which not only corrects imbalanced illumination and improves image contrast in an image, but also models noise explicitly to aid removal of imaging noise. Afterwards, we take advantage of exponential curvature estimation in the 3D space of positions and orientations to directly measure curvature based on the enhanced images, rather than relying on the explicit segmentation and skeletonization steps in a conventional pipeline usually with accumulated pre-processing errors. The proposed method has been applied over two corneal nerve microscopy datasets for the estimation of a tortuosity level for each image. The experimental results show that it performs better than several selected state-of-the-art methods. Furthermore, we have performed manual gradings at tortuosity level of four hundred and three corneal nerve microscopic images, and this dataset has been released for public access to facilitate other researchers in the community in carrying out further research on the same and related topics.

Retinal Vascular Network Topology Reconstruction and Artery/Vein Classification via Dominant Set Clustering.

The estimation of vascular network topology in complex networks is important in understanding the relationship between vascular changes and a wide spectrum of diseases. Automatic classification of the retinal vascular trees into arteries and veins is of direct assistance to the ophthalmologist in terms of diagnosis and treatment of eye disease. However, it is challenging due to their projective ambiguity and subtle changes in appearance, contrast, and geometry in the imaging process. In this paper, we propose a novel method that is capable of making the artery/vein (A/V) distinction in retinal color fundus images based on vascular network topological properties. To this end, we adapt the concept of dominant set clustering and formalize the retinal blood vessel topology estimation and the A/V classification as a pairwise clustering problem. The graph is constructed through image segmentation, skeletonization, and identification of significant nodes. The edge weight is defined as the inverse Euclidean distance between its two end points in the feature space of intensity, orientation, curvature, diameter, and entropy. The reconstructed vascular network is classified into arteries and veins based on their intensity and morphology. The proposed approach has been applied to five public databases, namely INSPIRE, IOSTAR, VICAVR, DRIVE, and WIDE, and achieved high accuracies of 95.1%, 94.2%, 93.8%, 91.1%, and 91.0%, respectively. Furthermore, we have made manual annotations of the blood vessel topologies for INSPIRE, IOSTAR, VICAVR, and DRIVE datasets, and these annotations are released for public access so as to facilitate researchers in the community.

Retinal vascular segmentation using superpixel-based line operator and its application to vascular topology estimation.

PURPOSE: Automatic methods of analyzing of retinal vascular networks, such as retinal blood vessel detection, vascular network topology estimation, and arteries/veins classification are of great assistance to the ophthalmologist in terms of diagnosis and treatment of a wide spectrum of diseases. METHODS: We propose a new framework for precisely segmenting retinal vasculatures, constructing retinal vascular network topology, and separating the arteries and veins. A nonlocal total variation inspired Retinex model is employed to remove the image intensity inhomogeneities and relatively poor contrast. For better generalizability and segmentation performance, a superpixel-based line operator is proposed as to distinguish between lines and the edges, thus allowing more tolerance in the position of the respective contours. The concept of dominant sets clustering is adopted to estimate retinal vessel topology and classify the vessel network into arteries and veins. RESULTS: The proposed segmentation method yields competitive results on three public data sets (STARE, DRIVE, and IOSTAR), and it has superior performance when compared with unsupervised segmentation methods, with accuracy of 0.954, 0.957, and 0.964, respectively. The topology estimation approach has been applied to five public databases (DRIVE,STARE, INSPIRE, IOSTAR, and VICAVR) and achieved high accuracy of 0.830, 0.910, 0.915, 0.928, and 0.889, respectively. The accuracies of arteries/veins classification based on the estimated vascular topology on three public databases (INSPIRE, DRIVE and VICAVR) are 0.90.9, 0.910, and 0.907, respectively. CONCLUSIONS: The experimental results show that the proposed framework has effectively addressed crossover problem, a bottleneck issue in segmentation and vascular topology reconstruction. The vascular topology information significantly improves the accuracy on arteries/veins classification.