Optic nerve head segmentation

Peripapillary atrophy detection by sparse biologically inspired feature manifold

Peripapillary atrophy (PPA) is an atrophy of pre-existing retina tissue. Because of its association with eye diseases such as myopia and glaucoma, PPA is an important indicator for diagnosis of these diseases. Experienced ophthalmologists are able to determine the presence of PPA using visual information from the retinal images. However, it is tedious, time consuming and subjective to examine all images especially in a screening program. This paper presents biologically inspired feature (BIF) for the automatic detection of PPA. BIF mimics the process of cortex for visual perception. In the proposed method, a focal region is segmented from the retinal image and the BIF is extracted. As BIF is an intrinsically low dimensional feature embedded in a high dimensional space, it is not suitable to measure the similarity between two BIFs directly based on the Euclidean distance. Therefore, it is necessary to obtain a suitable mapping to reduce the dimensionality. In this paper, we explore sparse transfer learning to transfer the label information from ophthalmologists to the sample distribution knowledge contained in all samples. Selective pair-wise discriminant analysis is used to define two strategies of sparse transfer learning: negative and positive sparse transfer learning. Experimental results show that negative sparse transfer learning is superior to the positive one for this task. The proposed BIF based approach achieves an accuracy of more than 90% in detecting PPA, much better than previous methods. It can be used to save the workload of ophthalmologists and thus reduce the diagnosis costs.

Variability between experts in defining the edge and area of the optic nerve head

OBJECTIVE

Estimation of the error rate in the subjective determination of the optic nerve head edge and area.

METHOD

1) 169 images of optic nerve disc were evaluated by five experts for the defining of the edges in 8 positions (every 45°). 2) The estimated areas of 26 cases were compared with the measurements of the Cirrus Optical Coherence Tomography (OCT-Cirrus).

RESULTS

1) The mean variation of the estimated radius was ±5.2%, with no significant differences between sectors. Specific differences were found between the 5 experts (P <.001), each one compared with the others. 2) The disc area measured by the OCT-Cirros was 1.78 mm² (SD =0.27). The results corresponding to the experts who detected smaller areas were better correlated to the area detected by the OCT-Cirrus (r=0.77-0.88) than the results corresponding to larger areas (r =0.61-0.69) (P <.05 in extreme cases).

CONCLUSIONS

There are specific patterns in each expert for defining the disc edges and involve 20% variation in the estimation of the optic nerve area. The experts who detected smaller areas have a higher agreement with the objective method used. A web tool is proposed for self-assessment and training in this task.

Automated diagnosis of referable maculopathy in diabetic retinopathy screening

This paper introduces an algorithm for the automated diagnosis of referable maculopathy in retinal images for diabetic retinopathy screening. Referable maculopathy is a potentially sight-threatening condition requiring immediate referral to an ophthalmologist from the screening service, and therefore accurate referral is extremely important. The algorithm uses a pipeline of detection and filtering of "peak points" with strong local contrast, segmentation of candidate lesions, extraction of features and classification by a multilayer perceptron. The optic nerve head and fovea are detected, so that the macula region can be identified and scanned. The algorithm is assessed against a reference standard database drawn from the Birmingham City Hospital (UK) diabetic retinopathy screening programme, against two possible modes of use: independent screening, and pre-filtering to reduce human screener workload.

Model-based optic nerve head segmentation on retinal fundus images

The optic nerve head (optic disc) plays an important role in the diagnosis of retinal diseases. Automatic localization and segmentation of the optic disc is critical towards a good computer-aided diagnosis (CAD) system. In this paper, we propose a method that combines edge detection, the Circular Hough Transform and a statistical deformable model to detect the optic disc from retinal fundus images. The algorithm was evaluated against a data set of 325 digital color fundus images, which includes both normal images and images with various pathologies. The result shows that the average error in area overlap is 11.3% and the average absolute area error is 10.8%, which outperforms existing methods. The result indicates a high correlation with ground truth segmentation and thus demonstrates a good potential for this system to be integrated with other retinal CAD systems.

An automated retinal image quality grading algorithm

This paper introduces an algorithm for the automated assessment of retinal fundus image quality grade. Retinal image quality grading assesses whether the quality of the image is sufficient to allow diagnostic procedures to be applied. Automated quality analysis is an important preprocessing step in algorithmic diagnosis, as it is necessary to ensure that images are sufficiently clear to allow pathologies to be visible. The algorithm is based on standard recommendations for quality analysis by human screeners, examining the clarity of retinal vessels within the macula region. An evaluation against a reference standard data-set is given; it is shown that the algorithm's performance correlates closely with that of clinicians manually grading image quality.

Fast localization and segmentation of optic disk in retinal images using directional matched filtering and level sets

The optic disk (OD) center and margin are typically requisite landmarks in establishing a frame of reference for classifying retinal and optic nerve pathology. Reliable and efficient OD localization and segmentation are important tasks in automatic eye disease screening. This paper presents a new, fast, and fully automatic OD localization and segmentation algorithm developed for retinal disease screening. First, OD location candidates are identified using template matching. The template is designed to adapt to different image resolutions. Then, vessel characteristics (patterns) on the OD are used to determine OD location. Initialized by the detected OD center and estimated OD radius, a fast, hybrid level-set model, which combines region and local gradient information, is applied to the segmentation of the disk boundary. Morphological filtering is used to remove blood vessels and bright regions other than the OD that affect segmentation in the peripapillary region. Optimization of the model parameters and their effect on the model performance are considered. Evaluation was based on 1200 images from the publicly available MESSIDOR database. The OD location methodology succeeded in 1189 out of 1200 images (99% success). The average mean absolute distance between the segmented boundary and the reference standard is 10% of the estimated OD radius for all image sizes. Its efficiency, robustness, and accuracy make the OD localization and segmentation scheme described herein suitable for automatic retinal disease screening in a variety of clinical settings.

RERBEE: robust efficient registration via bifurcations and elongated elements applied to retinal fluorescein angiogram sequences

We present RERBEE (robust efficient registration via bifurcations and elongated elements), a novel feature-based registration algorithm able to correct local deformations in high-resolution ultra-wide field-of-view (UWFV) fluorescein angiogram (FA) sequences of the retina. The algorithm is able to cope with peripheral blurring, severe occlusions, presence of retinal pathologies and the change of image content due to the perfusion of the fluorescein dye in time. We have used the computational power of a graphics processor to increase the performance of the most computationally expensive parts of the algorithm by a factor of over × 1300, enabling the algorithm to register a pair of 3900 × 3072 UWFV FA images in 5-10 min instead of the 5-7 h required using only the CPU. We demonstrate accurate results on real data with 267 image pairs from a total of 277 (96.4%) graded as correctly registered by a clinician and 10 (3.6%) graded as correctly registered with minor errors but usable for clinical purposes. Quantitative comparison with state-of-the-art intensity-based and feature-based registration methods using synthetic data is also reported. We also show some potential usage of a correctly aligned sequence for vein/artery discrimination and automatic lesion detection.

Telehealth practice recommendations for diabetic retinopathy, second edition

Ocular telemedicine and telehealth have the potential to decrease vision loss from DR. Planning, execution, and follow-up are key factors for success. Telemedicine is complex, requiring the services of expert teams working collaboratively to provide care matching the quality of conventional clinical settings. Improving access and outcomes, however, makes telemedicine a valuable tool for our diabetic patients. Programs that focus on patient needs, consider available resources, define clear goals, promote informed expectations, appropriately train personnel, and adhere to regulatory and statutory requirements have the highest chance of achieving success.

Accurate and efficient optic disc detection and segmentation by a circular transformation

Under the framework of computer-aided diagnosis, this paper presents an accurate and efficient optic disc (OD) detection and segmentation technique. A circular transformation is designed to capture both the circular shape of the OD and the image variation across the OD boundary simultaneously. For each retinal image pixel, it evaluates the image variation along multiple evenly-oriented radial line segments of specific length. The pixels with the maximum variation along all radial line segments are determined, which can be further exploited to locate both the OD center and the OD boundary accurately. Experiments show that OD detection accuracies of 99.75%, 97.5%, and 98.77% are obtained for the STARE dataset, the ARIA dataset, and the MESSIDOR dataset, respectively, and the OD center error lies around six pixels for the STARE dataset and the ARIA dataset which is much smaller than that of state-of-the-art methods ranging 14-29 pixels. In addition, the OD segmentation accuracies of 93.4% and 91.7% are obtained for STARE dataset and ARIA dataset, respectively, that consists of many severely degraded images of pathological retinas that state-of-the-art methods cannot segment properly. Furthermore, the algorithm runs in 5 s, which is substantially faster than many of the state-of-the-art methods.

Automated localization of retinal features

Retinal fundus images are widely used in the diagnosis and treatment of various eye diseases, such as diabetic retinopathy and glaucoma. A computer-aided retinal fundus image analysis could provide an immediate detection and characterization of retinal features prior to specialist inspection. This paper proposes an approach to automatically localize the main features in fundus images, such as blood vessels, optic disc, and fovea by exploiting the spatial and geometric relations that govern their distribution within the fundus image. The blood vessels are segmented by scale-space analysis. The average thickness of these blood vessels is then computed using the vessels centerlines and orientations from a Hessian matrix. The optic disc is localized using the circular Hough transform, the parabolic Hough transform fitting, and the localization of the fovea. The proposed method can be extended to establish a foveal coordinate system to facilitate grading lesions based on the spatial relationships between lesions and landmark features. The proposed method was evaluated on publicly available image databases, and the results have demonstrated a significant improvement over the current state-of-the-art methods.

Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment

Automatic retinal image analysis is emerging as an important screening tool for early detection of eye diseases. Glaucoma is one of the most common causes of blindness. The manual examination of optic disk (OD) is a standard procedure used for detecting glaucoma. In this paper, we present an automatic OD parameterization technique based on segmented OD and cup regions obtained from monocular retinal images. A novel OD segmentation method is proposed which integrates the local image information around each point of interest in multidimensional feature space to provide robustness against variations found in and around the OD region. We also propose a novel cup segmentation method which is based on anatomical evidence such as vessel bends at the cup boundary, considered relevant by glaucoma experts. Bends in a vessel are robustly detected using a region of support concept, which automatically selects the right scale for analysis. A multi-stage strategy is employed to derive a reliable subset of vessel bends called r-bends followed by a local spline fitting to derive the desired cup boundary. The method has been evaluated on 138 images comprising 33 normal and 105 glaucomatous images against three glaucoma experts. The obtained segmentation results show consistency in handling various geometric and photometric variations found across the dataset. The estimation error of the method for vertical cup-to-disk diameter ratio is 0.09/0.08 (mean/standard deviation) while for cup-to-disk area ratio it is 0.12/0.10. Overall, the obtained qualitative and quantitative results show effectiveness in both segmentation and subsequent OD parameterization for glaucoma assessment.

Automated segmentation of optic disc region on retinal fundus photographs: Comparison of contour modeling and pixel classification methods

The automatic determination of the optic disc area in retinal fundus images can be useful for calculation of the cup-to-disc (CD) ratio in the glaucoma screening. We compared three different methods that employed active contour model (ACM), fuzzy c-mean (FCM) clustering, and artificial neural network (ANN) for the segmentation of the optic disc regions. The results of these methods were evaluated using new databases that included the images captured by different camera systems. The average measures of overlap between the disc regions determined by an ophthalmologist and by using the ACM (0.88 and 0.87 for two test datasets) and ANN (0.88 and 0.89) methods were slightly higher than that by using FCM (0.86 and 0.86) method. These results on the unknown datasets were comparable with those of the resubstitution test; this indicates the generalizability of these methods. The differences in the vertical diameters, which are often used for CD ratio calculation, determined by the proposed methods and based on the ophthalmologist's outlines were even smaller than those in the case of the measure of overlap. The proposed methods can be useful for automatic determination of CD ratios.

Detecting the optic disc boundary in digital fundus images using morphological, edge detection, and feature extraction techniques

Optic disc (OD) detection is an important step in developing systems for automated diagnosis of various serious ophthalmic pathologies. This paper presents a new template-based methodology for segmenting the OD from digital retinal images. This methodology uses morphological and edge detection techniques followed by the Circular Hough Transform to obtain a circular OD boundary approximation. It requires a pixel located within the OD as initial information. For this purpose, a location methodology based on a voting-type algorithm is also proposed. The algorithms were evaluated on the 1200 images of the publicly available MESSIDOR database. The location procedure succeeded in 99% of cases, taking an average computational time of 1.67 s. with a standard deviation of 0.14 s. On the other hand, the segmentation algorithm rendered an average common area overlapping between automated segmentations and true OD regions of 86%. The average computational time was 5.69 s with a standard deviation of 0.54 s. Moreover, a discussion on advantages and disadvantages of the models more generally used for OD segmentation is also presented in this paper.

Segmentation of the optic disk in color eye fundus images using an adaptive morphological approach

The identification of some important retinal anatomical regions is a prerequisite for the computer aided diagnosis of several retinal diseases. In this paper, we propose a new adaptive method for the automatic segmentation of the optic disk in digital color fundus images, using mathematical morphology. The proposed method has been designed to be robust under varying illumination and image acquisition conditions, common in eye fundus imaging. Our experimental results based on two publicly available eye fundus image databases are encouraging, and indicate that our approach potentially can achieve a better performance than other known methods proposed in the literature. Using the DRIVE database (which consists of 40 retinal images), our method achieves a success rate of 100% in the correct location of the optic disk, with 41.47% of mean overlap. In the DIARETDB1 database (which consists of 89 retinal images), the optic disk is correctly located in 97.75% of the images, with a mean overlap of 43.65%.

An active contour model for segmenting and measuring retinal vessels

This paper presents an algorithm for segmenting and measuring retinal vessels, by growing a "Ribbon of Twins" active contour model, which uses two pairs of contours to capture each vessel edge, while maintaining width consistency. The algorithm is initialized using a generalized morphological order filter to identify approximate vessels centerlines. Once the vessel segments are identified the network topology is determined using an implicit neural cost function to resolve junction configurations. The algorithm is robust, and can accurately locate vessel edges under difficult conditions, including noisy blurred edges, closely parallel vessels, light reflex phenomena, and very fine vessels. It yields precise vessel width measurements, with subpixel average width errors. We compare the algorithm with several benchmarks from the literature, demonstrating higher segmentation sensitivity and more accurate width measurement.

Automated localization of the optic disc and the fovea

The detection of the position of the normal anatomy in color fundus photographs is an important step in the automated analysis of retinal images. An automatic system for the detection of the position of the optic disc and the fovea is presented. The method integrates the use of local vessel geometry and image intensity features to find the correct positions in the image. A kNN regressor is used to accomplish the integration. Evaluation was performed on a set of 250 digital color fundus photographs and the detection performance for the optic disc and the fovea were 99.2% and 96.4% respectively.

Quantitative depth analysis of optic nerve head using stereo retinal fundus image pair

Depth analysis of the optic nerve head (ONH) in the retinal fundus is important for the early detection of glaucoma. In this study, we investigate an automatic reconstruction method for the quantitative depth measurement of the ONH from a stereo retinal fundus image pair. We propose a technique to obtain the depth value from the stereo retinal fundus image pair, which mainly consists of five steps: 1. cutout of the ONH region from the stereo retinal fundus image pair, 2. registration of the stereo image pair, 3. disparity measurement, 4. noise reduction, and 5. quantitative depth calculation. Depth measurements of 12 normal eyes are performed using the stereo fundus camera and the Heidelberg Retina Tomograph (HRT), which is a confocal laser-scanning microscope. The depth values of the ONH obtained from the stereo retinal fundus image pair were in good accordance with the value obtained using HRT (r=0.80+/-0.15). These results indicate that our proposed method could be a useful and easy-to-handle tool for assessing the cup depth of the ONH in routine diagnosis as well as in glaucoma screening.

Segmentation of optic nerve head using warping and RANSAC

Glaucoma is the second leading cause of blindness, and the retinal nerve fiber layer (RNFL) defect is the early sign of the glaucomatous optic nerve damage. To evaluate the RNFL, segmentation of the optic nerve head on the RNFL photograph should be the first step. This paper presents segmentation of optic nerve head using warping and random sample consensus (RANSAC). Sensitivity and positive predictability of the proposed method were 91% and 78% respectively.

Automated assessment of the optic nerve head on stereo disc photographs

PURPOSE

To develop automated software for optic nerve head (ONH) quantitative assessment from stereoscopic disc photographs and to evaluate its performance in comparison with human expert assessment.

METHODS

A fully automated system, including three-dimensional ONH modeling, disc margin detection, cup margin detection, and calculation of stereometric ONH parameters, was developed and tested. One eye each from 54 subjects (23 healthy, 17 suspected glaucoma, and 14 glaucoma) was enrolled. The majority opinion of three experts defined disc and cup margins on the disc photographs was used for comparison. Seven ONH parameters, disc area, rim area, rim volume, cup area, cup volume, cup-to-disc (C/D) area ratio, and vertical C/D ratio, were computed based on both machine- and expert-defined margins and compared between the methods.

RESULTS

All automated ONH measurements showed good correlation with the expert defined margins (Pearson r = 0.90, disc area; 0.56, rim area; 0.78, rim volume; 0.88, cup area; 0.93, cup volume; 0.69, C/D area ratio; and 0.67, vertical C/D ratio; all P <or= 0.0001). No statistically significant difference was found in the glaucoma-discriminating ability of all seven ONH parameters (P >or= 0.21). The mean or median of automatically defined disc and cup areas was significantly higher than the subjective assessment (disc area P = 0.0001, t-test; cup area P = 0.036, Wilcoxon signed ranks test), although they had high correlation coefficients. The software failed to detect the disc margin for all the disc photographs with peripapillary atrophy.

CONCLUSIONS

The automated ONH analysis method provides an objective and quantitative ONH evaluation using widely available stereo disc photographs.

Optic disc detection from normalized digital fundus images by means of a vessels' direction matched filter

Optic disc (OD) detection is a main step while developing automated screening systems for diabetic retinopathy. We present in this paper a method to automatically detect the position of the OD in digital retinal fundus images. The method starts by normalizing luminosity and contrast through out the image using illumination equalization and adaptive histogram equalization methods respectively. The OD detection algorithm is based on matching the expected directional pattern of the retinal blood vessels. Hence, a simple matched filter is proposed to roughly match the direction of the vessels at the OD vicinity. The retinal vessels are segmented using a simple and standard 2-D Gaussian matched filter. Consequently, a vessels direction map of the segmented retinal vessels is obtained using the same segmentation algorithm. The segmented vessels are then thinned, and filtered using local intensity, to represent finally the OD-center candidates. The difference between the proposed matched filter resized into four different sizes, and the vessels' directions at the surrounding area of each of the OD-center candidates is measured. The minimum difference provides an estimate of the OD-center coordinates. The proposed method was evaluated using a subset of the STARE project's dataset, containing 81 fundus images of both normal and diseased retinas, and initially used by literature OD detection methods. The OD-center was detected correctly in 80 out of the 81 images (98.77%). In addition, the OD-center was detected correctly in all of the 40 images (100%) using the publicly available DRIVE dataset.

Automated optic disk boundary detection by modified active contour model

This paper presents a novel deformable-model-based algorithm for fully automated detection of optic disk boundary in fundus images. The proposed method improves and extends the original snake (deforming-only technique) in two aspects: clustering and smoothing update. The contour points are first self-separated into edge-point group or uncertain-point group by clustering after each deformation, and these contour points are then updated by different criteria based on different groups. The updating process combines both the local and global information of the contour to achieve the balance of contour stability and accuracy. The modifications make the proposed algorithm more accurate and robust to blood vessel occlusions, noises, ill-defined edges and fuzzy contour shapes. The comparative results show that the proposed method can estimate the disk boundaries of 100 test images closer to the groundtruth, as measured by mean distance to closest point (MDCP) <3 pixels, with the better success rate when compared to those obtained by gradient vector flow snake (GVF-snake) and modified active shape models (ASM).

Automated segmentation of the optic disc from stereo color photographs using physiologically plausible features

PURPOSE

To evaluate a novel automated segmentation algorithm for cup-to-disc segmentation from stereo color photographs of patients with glaucoma for the measurement of glaucoma progression.

METHODS

Stereo color photographs of the optic disc were obtained by using a fixed stereo-base fundus camera in 58 eyes of 58 patients with suspected or open-angle glaucoma. Manual planimetry was performed by three glaucoma faculty members to delineate a reference standard rim and cup segmentation of all stereo pairs and by three glaucoma fellows as well. Pixel feature classification was evaluated on the stereo pairs and corresponding reference standard, by using feature computation based on simulation of photoreceptor color opponency and visual cortex simple and complex cells. An optimal subset of 12 features was used to segment all pixels in all stereo pairs, and the percentage of pixels assigned the correct class and linear cup-to-disc ratio (LCDR) estimates of the glaucoma fellows and the algorithm were compared to the reference standard.

RESULTS

The algorithm was able to assign cup, rim, and background correctly to 88% of all pixels. Correlations of the LCDR estimates of glaucoma fellows with those of the reference standard were 0.73 (95% CI, 0.58-0.83), 0.81 (95% CI, 0.70-0.89), and 0.86 (95% CI, 0.78-0.91), respectively, whereas the correlation of the algorithm with the reference standard was 0.93 (95% CI, 0.89-0.96; n = 58).

CONCLUSIONS

The pixel feature classification algorithm allows objective segmentation of the optic disc from conventional color stereo photographs automatically without human input. The performance of the disc segmentation and LCDR calculation of the algorithm was comparable to that of glaucoma fellows in training and is promising for objective evaluation of optic disc cupping.

Texton-based segmentation of retinal vessels

With improvements in fundus imaging technology and the increasing use of digital images in screening and diagnosis, the issue of automated analysis of retinal images is gaining more serious attention. We consider the problem of retinal vessel segmentation, a key issue in automated analysis of digital fundus images. We propose a texture-based vessel segmentation algorithm based on the notion of textons. Using a weak statistical learning approach, we construct textons for retinal vasculature by designing filters that are specifically tuned to the structural and photometric properties of retinal vessels. We evaluate the performance of the proposed approach using a standard database of retinal images. On the DRIVE data set, the proposed method produced an average performance of 0.9568 specificity at 0.7346 sensitivity. This compares well with the best-published results on the data set 0.9773 specificity at 0.7194 sensitivity [Proc. SPIE5370, 648 (2004)].

Automated detection of optic disk boundary by a new deformable model technique

A new algorithm to detect the exact optic disk boundary, based on deformable model, is proposed in this paper. The energy function for deformation is defined as a combination of local energies. The proposed method modified the original snake technique in two aspects: clustering the contour points into edge-point group or uncertain-point group after each deformation, and updating the contour by variable updating-sample numbers. The modifications not only directly solve the blood vessel problem, but also make this algorithm more accurate and robust to noises, weak edges and fuzzy contour shapes. Based on 100 randomly-selected testing images, the success rates are 94% for the proposed method, as compared to 12% for the GVF-snake and 82% for the modified ASM algorithm, which show the effectiveness of the proposed method.

Automatic detection of retinal anatomy to assist diabetic retinopathy screening

Screening programmes for diabetic retinopathy are being introduced in the United Kingdom and elsewhere. These require large numbers of retinal images to be manually graded for the presence of disease. Automation of image grading would have a number of benefits. However, an important prerequisite for automation is the accurate location of the main anatomical features in the image, notably the optic disc and the fovea. The locations of these features are necessary so that lesion significance, image field of view and image clarity can be assessed. This paper describes methods for the robust location of the optic disc and fovea. The elliptical form of the major retinal blood vessels is used to obtain approximate locations, which are refined based on the circular edge of the optic disc and the local darkening at the fovea. The methods have been tested on 1056 sequential images from a retinal screening programme. Positional accuracy was better than 0.5 of a disc diameter in 98.4% of cases for optic disc location, and in 96.5% of cases for fovea location. The methods are sufficiently accurate to form an important and effective component of an automated image grading system for diabetic retinopathy screening.

Segmentation of trabeculated structures using an anisotropic Markov random field: application to the study of the optic nerve head in glaucoma

The study of the architecture of the optic nerve head (ONH) may provide valuable information about the development and progression of glaucoma. To this end, we have generated three-dimensional datasets from monkey eyes under controlled intraocular pressure (IOP). Segmentation of the connective tissues in this area is crucial to obtain an accurate measurement of geometrical parameters and to build mechanical models. However, this segmentation is made difficult by the complicated geometry and the artifacts introduced in the dataset building process. We present a novel segmentation algorithm, based on expectation-maximization, which incorporates an anisotropic Markov random field (MRF) to introduce prior knowledge about the geometry of the structure. The structure tensor is used to characterize the predominant structure direction and the spatial coherence at each point. The algorithm, which has been validated on an artificial validation dataset that mimics our ONH datasets, shows significant improvement over an isotropic MRF. Results on the real datasets demonstrate the ability of the new algorithm to obtain accurate, spatially consistent segmentations of this structure.