Optimal multiple surface segmentation with shape and context priors

Boundary-Repairing Dual-Path Network for Retinal Layer Segmentation in OCT Image with Pigment Epithelial Detachment

Automatic retinal layer segmentation in optical coherence tomography (OCT) images is crucial for the diagnosis of ocular diseases. Currently, automatic retinal layer segmentation works well with normal OCT images. However, pigment epithelial detachment (PED) dramatically alters the retinal structure, causing blurred boundaries and partial disappearance of the Bruch's Membrane (BM), thus posing challenges to the segmentation. To tackle these problems, we propose a novel dual-path U-shaped network for simultaneous layer segmentation and boundary regression. This network first designs a feature interaction fusion (FIF) module to strengthen the boundary shape constraints in the layer path. To address the challenge posed by partial BM disappearance and boundary-blurring, we propose a layer boundary repair (LBR) module. This module aims to use contrastive loss to enhance the confidence of blurred boundary regions and refine the segmentation of layer boundaries through the re-prediction head. In addition, we introduce a novel bilateral threshold distance map (BTDM) designed for the boundary path. The BTDM serves to emphasize information within boundary regions. This map, combined with the updated probability map, culminates in topology-guaranteed segmentation results achieved through a topology correction (TC) module. We investigated the proposed network on two severely deformed datasets (i.e., OCTA-500 and Aier-PED) and one slightly deformed dataset (i.e., DUKE). The proposed method achieves an average Dice score of 94.26% on the OCTA-500 dataset, which was 1.5% higher than BAU-Net and outperformed other methods. In the DUKE and Aier-PED datasets, the proposed method achieved average Dice scores of 91.65% and 95.75%, respectively.

Advancing Ocular Imaging: A Hybrid Attention Mechanism-Based U-Net Model for Precise Segmentation of Sub-Retinal Layers in OCT Images

This paper presents a novel U-Net model incorporating a hybrid attention mechanism for automating the segmentation of sub-retinal layers in Optical Coherence Tomography (OCT) images. OCT is an ophthalmology tool that provides detailed insights into retinal structures. Manual segmentation of these layers is time-consuming and subjective, calling for automated solutions. Our proposed model combines edge and spatial attention mechanisms with the U-Net architecture to improve segmentation accuracy. By leveraging attention mechanisms, the U-Net focuses selectively on image features. Extensive evaluations using datasets demonstrate that our model outperforms existing approaches, making it a valuable tool for medical professionals. The study also highlights the model's robustness through performance metrics such as an average Dice score of 94.99%, Adjusted Rand Index (ARI) of 97.00%, and Strength of Agreement (SOA) classifications like "Almost Perfect", "Excellent", and "Very Strong". This advanced predictive model shows promise in expediting processes and enhancing the precision of ocular imaging in real-world applications.

Graph Attention U-Net for Retinal Layer Surface Detection and Choroid Neovascularization Segmentation in OCT Images

Choroidal neovascularization (CNV) is a typical symptom of age-related macular degeneration (AMD) and is one of the leading causes for blindness. Accurate segmentation of CNV and detection of retinal layers are critical for eye disease diagnosis and monitoring. In this paper, we propose a novel graph attention U-Net (GA-UNet) for retinal layer surface detection and CNV segmentation in optical coherence tomography (OCT) images. Due to retinal layer deformation caused by CNV, it is challenging for existing models to segment CNV and detect retinal layer surfaces with the correct topological order. We propose two novel modules to address the challenge. The first module is a graph attention encoder (GAE) in a U-Net model that automatically integrates topological and pathological knowledge of retinal layers into the U-Net structure to achieve effective feature embedding. The second module is a graph decorrelation module (GDM) that takes reconstructed features by the decoder of the U-Net as inputs, it then decorrelates and removes information unrelated to retinal layer for improved retinal layer surface detection. In addition, we propose a new loss function to maintain the correct topological order of retinal layers and the continuity of their boundaries. The proposed model learns graph attention maps automatically during training and performs retinal layer surface detection and CNV segmentation simultaneously with the attention maps during inference. We evaluated the proposed model on our private AMD dataset and another public dataset. Experiment results show that the proposed model outperformed the competing methods for retinal layer surface detection and CNV segmentation and achieved new state of the arts on the datasets.

Deep learning network with differentiable dynamic programming for retina OCT surface segmentation

Multiple-surface segmentation in optical coherence tomography (OCT) images is a challenging problem, further complicated by the frequent presence of weak image boundaries. Recently, many deep learning-based methods have been developed for this task and yield remarkable performance. Unfortunately, due to the scarcity of training data in medical imaging, it is challenging for deep learning networks to learn the global structure of the target surfaces, including surface smoothness. To bridge this gap, this study proposes to seamlessly unify a U-Net for feature learning with a constrained differentiable dynamic programming module to achieve end-to-end learning for retina OCT surface segmentation to explicitly enforce surface smoothness. It effectively utilizes the feedback from the downstream model optimization module to guide feature learning, yielding better enforcement of global structures of the target surfaces. Experiments on Duke AMD (age-related macular degeneration) and JHU MS (multiple sclerosis) OCT data sets for retinal layer segmentation demonstrated that the proposed method was able to achieve subvoxel accuracy on both datasets, with the mean absolute surface distance (MASD) errors of 1.88 ± 1.96μm and 2.75 ± 0.94μm, respectively, over all the segmented surfaces.

Multiscale joint segmentation method for retinal optical coherence tomography images using a bidirectional wave algorithm and improved graph theory

Morphology and functional metrics of retinal layers are important biomarkers for many human ophthalmic diseases. Automatic and accurate segmentation of retinal layers is crucial for disease diagnosis and research. To improve the performance of retinal layer segmentation, a multiscale joint segmentation framework for retinal optical coherence tomography (OCT) images based on bidirectional wave algorithm and improved graph theory is proposed. In this framework, the bidirectional wave algorithm was used to segment edge information in multiscale images, and the improved graph theory was used to modify edge information globally, to realize automatic and accurate segmentation of eight retinal layer boundaries. This framework was tested on two public datasets and two OCT imaging systems. The test results show that, compared with other state-of-the-art methods, this framework does not need data pre-training and parameter pre-adjustment on different datasets, and can achieve sub-pixel retinal layer segmentation on a low-configuration computer.

Self-Supervised Sequence Recovery for Semi-Supervised Retinal Layer Segmentation

Automated layer segmentation plays an important role for retinal disease diagnosis in optical coherence tomography (OCT) images. However, the severe retinal diseases result in the performance degeneration of automated layer segmentation approaches. In this paper, we present a robust semi-supervised retinal layer segmentation network to relieve the model failures on abnormal retinas, in which we obtain the lesion features from the labeled images with disease-balanced distribution, and utilize the unlabeled images to supplement the layer structure information. Specifically, in our proposed method, the cross-consistency training is utilized over the predictions of the different decoders, and we enforce a consistency between different decoder predictions to improve the encoders representation. Then, we proposed a sequence prediction branch based on self-supervised manner, which is designed to predict the position of each jigsaw puzzle to obtain sensory perception of the retinal layer structure. To this task, a layer spatial pyramid pooling (LSPP) module is designed to extract multi-scale layer spatial features. Furthermore, we use the optical coherence tomography angiography (OCTA) to supplement the information damaged by diseases. The experimental results validate that our method achieves more robust results compared with current supervised segmentation methods. Meanwhile, advanced segmentation performance can be obtained compared with state-of-the-art semi-supervised segmentation methods.

Globally optimal OCT surface segmentation using a constrained IPM optimization

Segmentation of multiple surfaces in optical coherence tomography (OCT) images is a challenging problem, further complicated by the frequent presence of weak boundaries, varying layer thicknesses, and mutual influence between adjacent surfaces. The traditional graph-based optimal surface segmentation method has proven its effectiveness with its ability to capture various surface priors in a uniform graph model. However, its efficacy heavily relies on handcrafted features that are used to define the surface cost for the "goodness" of a surface. Recently, deep learning (DL) is emerging as a powerful tool for medical image segmentation thanks to its superior feature learning capability. Unfortunately, due to the scarcity of training data in medical imaging, it is nontrivial for DL networks to implicitly learn the global structure of the target surfaces, including surface interactions. This study proposes to parameterize the surface cost functions in the graph model and leverage DL to learn those parameters. The multiple optimal surfaces are then simultaneously detected by minimizing the total surface cost while explicitly enforcing the mutual surface interaction constraints. The optimization problem is solved by the primal-dual interior-point method (IPM), which can be implemented by a layer of neural networks, enabling efficient end-to-end training of the whole network. Experiments on spectral-domain optical coherence tomography (SD-OCT) retinal layer segmentation demonstrated promising segmentation results with sub-pixel accuracy.

DW-Net: Dynamic Multi-Hierarchical Weighting Segmentation Network for Joint Segmentation of Retina Layers With Choroid Neovascularization

Choroid neovascularization (CNV) is one of the blinding factors. The early detection and quantitative measurement of CNV are crucial for the establishment of subsequent treatment. Recently, many deep learning-based methods have been proposed for CNV segmentation. However, CNV is difficult to be segmented due to the complex structure of the surrounding retina. In this paper, we propose a novel dynamic multi-hierarchical weighting segmentation network (DW-Net) for the simultaneous segmentation of retinal layers and CNV. Specifically, the proposed network is composed of a residual aggregation encoder path for the selection of informative feature, a multi-hierarchical weighting connection for the fusion of detailed information and abstract information, and a dynamic decoder path. Comprehensive experimental results show that our proposed DW-Net achieves better performance than other state-of-the-art methods.

Robust region encoding and layer attribute protection for the segmentation of retina with multifarious abnormalities

PURPOSE

To robustly segment retinal layers that are affected by complex variety of retinal diseases for optical coherence tomography angiography (OCTA) en face projection generation.

METHODS

In this paper, we propose a robust retinal layer segmentation model to reduce the impact of multifarious abnormalities on model performance. OCTA vascular distribution that is regarded as the supplements of spectral domain optical coherence tomography (SD-OCT) structural information is introduced to improve the robustness of layer region encoding. To further reduce the sensitivity of region encoding to retinal abnormalities, we propose a multitask layer-wise refinement (MLR) module that can refine the initial layer region segmentation results layer-by-layer. Finally, we design a region-to-surface transformation (RtST) module without additional training parameters to convert the encoding layer regions to their corresponding layer surfaces. This transformation from layer regions to layer surfaces can remove the inaccurate segmentation regions, and the layer surfaces are easier to be used to protect the retinal layer natures than layer regions.

RESULTS

Experimental data includes 273 eyes, where 95 eyes are normal and 178 eyes contain complex retinal diseases, including age-related macular degeneration (AMD), diabetic retinopathy (DR), central serous chorioretinopathy (CSC), choroidal neovascularization (CNV), and so forth. The dice similarity coefficient (DSC: %) of superficial, deep and outer retina achieves 98.92, 97.48, and 98.87 on normal eyes and 98.35, 95.33, and 98.17 on abnormal eyes. Compared with other commonly used layer segmentation models, our model achieves the state-of-the-art layer segmentation performance.

CONCLUSIONS

The final results prove that our proposed model obtains outstanding performance and has enough ability to resist retinal abnormalities. Besides, OCTA modality is helpful for retinal layer segmentation.

Assignment Flow for Order-Constrained OCT Segmentation

At the present time optical coherence tomography (OCT) is among the most commonly used non-invasive imaging methods for the acquisition of large volumetric scans of human retinal tissues and vasculature. The substantial increase of accessible highly resolved 3D samples at the optic nerve head and the macula is directly linked to medical advancements in early detection of eye diseases. To resolve decisive information from extracted OCT volumes and to make it applicable for further diagnostic analysis, the exact measurement of retinal layer thicknesses serves as an essential task be done for each patient separately. However, manual examination of OCT scans is a demanding and time consuming task, which is typically made difficult by the presence of tissue-dependent speckle noise. Therefore, the elaboration of automated segmentation models has become an important task in the field of medical image processing. We propose a novel, purely data driven geometric approach to order-constrained 3D OCT retinal cell layer segmentation which takes as input data in any metric space and can be implemented using only simple, highly parallelizable operations. As opposed to many established retinal layer segmentation methods, we use only locally extracted features as input and do not employ any global shape prior. The physiological order of retinal cell layers and membranes is achieved through the introduction of a smoothed energy term. This is combined with additional regularization of local smoothness to yield highly accurate 3D segmentations. The approach thereby systematically avoid bias pertaining to global shape and is hence suited for the detection of anatomical changes of retinal tissue structure. To demonstrate its robustness, we compare two different choices of features on a data set of manually annotated 3D OCT volumes of healthy human retina. The quality of computed segmentations is compared to the state of the art in automatic retinal layer segmention as well as to manually annotated ground truth data in terms of mean absolute error and Dice similarity coefficient. Visualizations of segmented volumes are also provided.

OCTRexpert:A Feature-based 3D Registration Method for Retinal OCT Images

Medical image registration can be used for studying longitudinal and cross-sectional data, quantitatively monitoring disease progression and guiding computer assisted diagnosis and treatments. However, deformable registration which enables more precise and quantitative comparison has not been well developed for retinal optical coherence tomography (OCT) images. This paper proposes a new 3D registration approach for retinal OCT data called OCTRexpert. To the best of our knowledge, the proposed algorithm is the first full 3D registration approach for retinal OCT images which can be applied to longitudinal OCT images for both normal and serious pathological subjects. In this approach, a pre-processing method is first performed to remove eye motion artifact and then a novel design-detection-deformation strategy is applied for the registration. In the design step, a couple of features are designed for each voxel in the image. In the detection step, active voxels are selected and the point-to-point correspondences between the subject and template images are established. In the deformation step, the image is hierarchically deformed according to the detected correspondences in multi-resolution. The proposed method is evaluated on a dataset with longitudinal OCT images from 20 healthy subjects and 4 subjects diagnosed with serious Choroidal Neovascularization (CNV). Experimental results show that the proposed registration algorithm consistently yields statistically significant improvements in both Dice similarity coefficient and the average unsigned surface error compared with the other registration methods.

Accurate tissue interface segmentation via adversarial pre-segmentation of anterior segment OCT images

Optical Coherence Tomography (OCT) is an imaging modality that has been widely adopted for visualizing corneal, retinal and limbal tissue structure with micron resolution. It can be used to diagnose pathological conditions of the eye, and for developing pre-operative surgical plans. In contrast to the posterior retina, imaging the anterior tissue structures, such as the limbus and cornea, results in B-scans that exhibit increased speckle noise patterns and imaging artifacts. These artifacts, such as shadowing and specularity, pose a challenge during the analysis of the acquired volumes as they substantially obfuscate the location of tissue interfaces. To deal with the artifacts and speckle noise patterns and accurately segment the shallowest tissue interface, we propose a cascaded neural network framework, which comprises of a conditional Generative Adversarial Network (cGAN) and a Tissue Interface Segmentation Network (TISN). The cGAN pre-segments OCT B-scans by removing undesired specular artifacts and speckle noise patterns just above the shallowest tissue interface, and the TISN combines the original OCT image with the pre-segmentation to segment the shallowest interface. We show the applicability of the cascaded framework to corneal datasets, demonstrate that it precisely segments the shallowest corneal interface, and also show its generalization capacity to limbal datasets. We also propose a hybrid framework, wherein the cGAN pre-segmentation is passed to a traditional image analysis-based segmentation algorithm, and describe the improved segmentation performance. To the best of our knowledge, this is the first approach to remove severe specular artifacts and speckle noise patterns (prior to the shallowest interface) that affects the interpretation of anterior segment OCT datasets, thereby resulting in the accurate segmentation of the shallowest tissue interface. To the best of our knowledge, this is the first work to show the potential of incorporating a cGAN into larger deep learning frameworks for improved corneal and limbal OCT image segmentation. Our cGAN design directly improves the visualization of corneal and limbal OCT images from OCT scanners, and improves the performance of current OCT segmentation algorithms.

Optimal surface segmentation with convex priors in irregularly sampled space

Optimal surface segmentation is a state-of-the-art method used for segmentation of multiple globally optimal surfaces in volumetric datasets. The method is widely used in numerous medical image segmentation applications. However, nodes in the graph based optimal surface segmentation method typically encode uniformly distributed orthogonal voxels of the volume. Thus the segmentation cannot attain an accuracy greater than a single unit voxel, i.e. the distance between two adjoining nodes in graph space. Segmentation accuracy higher than a unit voxel is achievable by exploiting partial volume information in the voxels which shall result in non-equidistant spacing between adjoining graph nodes. This paper reports a generalized graph based multiple surface segmentation method with convex priors which can optimally segment the target surfaces in an irregularly sampled space. The proposed method allows non-equidistant spacing between the adjoining graph nodes to achieve subvoxel segmentation accuracy by utilizing the partial volume information in the voxels. The partial volume information in the voxels is exploited by computing a displacement field from the original volume data to identify the subvoxel-accurate centers within each voxel resulting in non-equidistant spacing between the adjoining graph nodes. The smoothness of each surface modeled as a convex constraint governs the connectivity and regularity of the surface. We employ an edge-based graph representation to incorporate the necessary constraints and the globally optimal solution is obtained by computing a minimum s-t cut. The proposed method was validated on 10 intravascular multi-frame ultrasound image datasets for subvoxel segmentation accuracy. In all cases, the approach yielded highly accurate results. Our approach can be readily extended to higher-dimensional segmentations.

Automatic three-dimensional segmentation of endoscopic airway OCT images

Automatic delineation and segmentation of airway structures from endoscopic optical coherence tomography (OCT) images improve image analysis efficiency and thus has been of particular interest. Conventional two-dimensional automatic segmentation methods, such as the dynamic programming approach, ensures the edge-continuity in the xz-direction (intra-B-scan), but fails to preserve the surface-continuity when concerning the y-direction (inter-B-scan). To solve this, we present a novel automatic three-dimensional (3D) airway segmentation strategy. Our segmentation scheme includes an artifact-oriented pre-processing pipeline and a modified 3D optimal graph search algorithm incorporating adaptive tissue-curvature adjustment. The proposed algorithm is tested on endoscopic airway OCT image data sets acquired by different swept-source OCT platforms, and on different animal and human models. With our method, the results show continuous surface segmentation performance, which is both robust and accurate.

Automatic Segmentation of Retinal Layer in OCT Images With Choroidal Neovascularization

Age-related macular degeneration is one of the main causes of blindness. However, the internal structures of retinas are complex and difficult to be recognized due to the occurrence of neovascularization. Traditional surface detection methods may fail in the layer segmentation. In this paper, a supervised method is reported for simultaneously segmenting layers and neovascularization. Three spatial features, seven gray-level-based features, and 14 layer-like features are extracted for the neural network classifier. The coarse surfaces of different optical coherence tomography (OCT) images can thus be found. To describe and enhance retinal layers with different thicknesses and abnormalities, multi-scale bright and dark layer detection filters are introduced. A constrained graph search algorithm is also proposed to accurately detect retinal surfaces. The weights of nodes in the graph are computed based on these layer-like responses. The proposed method was evaluated on 42 spectral-domain OCT images with age-related macular degeneration. The experimental results show that the proposed method outperforms state-of-the-art methods.

Fully Automated Delineation of Gross Tumor Volume for Head and Neck Cancer on PET-CT Using Deep Learning: A Dual-Center Study

Purpose

In this study, we proposed an automated deep learning (DL) method for head and neck cancer (HNC) gross tumor volume (GTV) contouring on positron emission tomography-computed tomography (PET-CT) images.

Materials and Methods

PET-CT images were collected from 22 newly diagnosed HNC patients, of whom 17 (Database 1) and 5 (Database 2) were from two centers, respectively. An oncologist and a radiologist decided the gold standard of GTV manually by consensus. We developed a deep convolutional neural network (DCNN) and trained the network based on the two-dimensional PET-CT images and the gold standard of GTV in the training dataset. We did two experiments: Experiment 1, with Database 1 only, and Experiment 2, with both Databases 1 and 2. In both Experiment 1 and Experiment 2, we evaluated the proposed method using a leave-one-out cross-validation strategy. We compared the median results in Experiment 2 (GTVa) with the performance of other methods in the literature and with the gold standard (GTVm).

Results

A tumor segmentation task for a patient on coregistered PET-CT images took less than one minute. The dice similarity coefficient (DSC) of the proposed method in Experiment 1 and Experiment 2 was 0.481∼0.872 and 0.482∼0.868, respectively. The DSC of GTVa was better than that in previous studies. A high correlation was found between GTVa and GTVm (R = 0.99, P < 0.001). The median volume difference (%) between GTVm and GTVa was 10.9%. The median values of DSC, sensitivity, and precision of GTVa were 0.785, 0.764, and 0.789, respectively.

Conclusion

A fully automatic GTV contouring method for HNC based on DCNN and PET-CT from dual centers has been successfully proposed with high accuracy and efficiency. Our proposed method is of help to the clinicians in HNC management.

Multiple surface segmentation using convolution neural nets: application to retinal layer segmentation in OCT images

Automated segmentation of object boundaries or surfaces is crucial for quantitative image analysis in numerous biomedical applications. For example, retinal surfaces in optical coherence tomography (OCT) images play a vital role in the diagnosis and management of retinal diseases. Recently, graph based surface segmentation and contour modeling have been developed and optimized for various surface segmentation tasks. These methods require expertly designed, application specific transforms, including cost functions, constraints and model parameters. However, deep learning based methods are able to directly learn the model and features from training data. In this paper, we propose a convolutional neural network (CNN) based framework to segment multiple surfaces simultaneously. We demonstrate the application of the proposed method by training a single CNN to segment three retinal surfaces in two types of OCT images - normal retinas and retinas affected by intermediate age-related macular degeneration (AMD). The trained network directly infers the segmentations for each B-scan in one pass. The proposed method was validated on 50 retinal OCT volumes (3000 B-scans) including 25 normal and 25 intermediate AMD subjects. Our experiment demonstrated statistically significant improvement of segmentation accuracy compared to the optimal surface segmentation method with convex priors (OSCS) and two deep learning based UNET methods for both types of data. The average computation time for segmenting an entire OCT volume (consisting of 60 B-scans each) for the proposed method was 12.3 seconds, demonstrating low computation costs and higher performance compared to the graph based optimal surface segmentation and UNET based methods.

Three-dimensional graph-based skin layer segmentation in optical coherence tomography images for roughness estimation

Automatic skin layer segmentation in optical coherence tomography (OCT) images is important for a topographic assessment of skin or skin disease detection. However, existing methods cannot deal with the problem of shadowing in OCT images due to the presence of hair, scales, etc. In this work, we propose a method to segment the topmost layer of the skin (or the skin surface) using 3D graphs with a novel cost function to deal with shadowing in OCT images. 3D graph cuts use context information across B-scans when segmenting the skin surface, which improves the segmentation as compared to segmenting each B-scan separately. The proposed method reduces the segmentation error by more than 20% as compared to the best performing related work. The method has been applied to roughness estimation and shows a high correlation with a manual assessment. Promising results demonstrate the usefulness of the proposed method for skin layer segmentation and roughness estimation in both normal OCT images and OCT images with shadowing.

Artificial intelligence in retina

Major advances in diagnostic technologies are offering unprecedented insight into the condition of the retina and beyond ocular disease. Digital images providing millions of morphological datasets can fast and non-invasively be analyzed in a comprehensive manner using artificial intelligence (AI). Methods based on machine learning (ML) and particularly deep learning (DL) are able to identify, localize and quantify pathological features in almost every macular and retinal disease. Convolutional neural networks thereby mimic the path of the human brain for object recognition through learning of pathological features from training sets, supervised ML, or even extrapolation from patterns recognized independently, unsupervised ML. The methods of AI-based retinal analyses are diverse and differ widely in their applicability, interpretability and reliability in different datasets and diseases. Fully automated AI-based systems have recently been approved for screening of diabetic retinopathy (DR). The overall potential of ML/DL includes screening, diagnostic grading as well as guidance of therapy with automated detection of disease activity, recurrences, quantification of therapeutic effects and identification of relevant targets for novel therapeutic approaches. Prediction and prognostic conclusions further expand the potential benefit of AI in retina which will enable personalized health care as well as large scale management and will empower the ophthalmologist to provide high quality diagnosis/therapy and successfully deal with the complexity of 21st century ophthalmology.

Shared-hole graph search with adaptive constraints for 3D optic nerve head optical coherence tomography image segmentation

Optic nerve head (ONH) is a crucial region for glaucoma detection and tracking based on spectral domain optical coherence tomography (SD-OCT) images. In this region, the existence of a "hole" structure makes retinal layer segmentation and analysis very challenging. To improve retinal layer segmentation, we propose a 3D method for ONH centered SD-OCT image segmentation, which is based on a modified graph search algorithm with a shared-hole and locally adaptive constraints. With the proposed method, both the optic disc boundary and nine retinal surfaces can be accurately segmented in SD-OCT images. An overall mean unsigned border positioning error of 7.27 ± 5.40 µm was achieved for layer segmentation, and a mean Dice coefficient of 0.925 ± 0.03 was achieved for optic disc region detection.

Detection of Lung Contour with Closed Principal Curve and Machine Learning

Radiation therapy plays an essential role in the treatment of cancer. In radiation therapy, the ideal radiation doses are delivered to the observed tumor while not affecting neighboring normal tissues. In three-dimensional computed tomography (3D-CT) scans, the contours of tumors and organs-at-risk (OARs) are often manually delineated by radiologists. The task is complicated and time-consuming, and the manually delineated results will be variable from different radiologists. We propose a semi-supervised contour detection algorithm, which firstly uses a few points of region of interest (ROI) as an approximate initialization. Then the data sequences are achieved by the closed polygonal line (CPL) algorithm, where the data sequences consist of the ordered projection indexes and the corresponding initial points. Finally, the smooth lung contour can be obtained, when the data sequences are trained by the backpropagation neural network model (BNNM). We use the private clinical dataset and the public Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset to measure the accuracy of the presented method, respectively. To the private dataset, experimental results on the initial points which are as low as 15% of the manually delineated points show that the Dice coefficient reaches up to 0.95 and the global error is as low as 1.47 × 10^-2. The performance of the proposed algorithm is also better than the cubic spline interpolation (CSI) algorithm. While on the public LIDC-IDRI dataset, our method achieves superior segmentation performance with average Dice of 0.83.

A Survey of Graph Cuts/Graph Search Based Medical Image Segmentation

Medical image segmentation is a fundamental and challenging problem for analyzing medical images. Among different existing medical image segmentation methods, graph-based approaches are relatively new and show good features in clinical applications. In the graph-based method, pixels or regions in the original image are interpreted into nodes in a graph. By considering Markov random field to model the contexture information of the image, the medical image segmentation problem can be transformed into a graph-based energy minimization problem. This problem can be solved by the use of minimum s-t cut/ maximum flow algorithm. This review is devoted to cut-based medical segmentation methods, including graph cuts and graph search for region and surface segmentation. Different varieties of cut-based methods, including graph-cuts-based methods, model integrated graph cuts methods, graph-search-based methods, and graph search/graph cuts based methods, are systematically reviewed. Graph cuts and graph search with deep learning technique are also discussed.

Automated Whole-Body Bone Lesion Detection for Multiple Myeloma on 68Ga-Pentixafor PET/CT Imaging Using Deep Learning Methods

The identification of bone lesions is crucial in the diagnostic assessment of multiple myeloma (MM). 68Ga-Pentixafor PET/CT can capture the abnormal molecular expression of CXCR-4 in addition to anatomical changes. However, whole-body detection of dozens of lesions on hybrid imaging is tedious and error prone. It is even more difficult to identify lesions with a large heterogeneity. This study employed deep learning methods to automatically combine characteristics of PET and CT for whole-body MM bone lesion detection in a 3D manner. Two convolutional neural networks (CNNs), V-Net and W-Net, were adopted to segment and detect the lesions. The feasibility of deep learning for lesion detection on 68Ga-Pentixafor PET/CT was first verified on digital phantoms generated using realistic PET simulation methods. Then the proposed methods were evaluated on real 68Ga-Pentixafor PET/CT scans of MM patients. The preliminary results showed that deep learning method can leverage multimodal information for spatial feature representation, and W-Net obtained the best result for segmentation and lesion detection. It also outperformed traditional machine learning methods such as random forest classifier (RF), k-Nearest Neighbors (k-NN), and support vector machine (SVM). The proof-of-concept study encourages further development of deep learning approach for MM lesion detection in population study.

Contour segmentation of the intima, media, and adventitia layers in intracoronary OCT images: application to fully automatic detection of healthy wall regions

PURPOSE

Quantitative and automatic analysis of intracoronary optical coherence tomography images is useful and time-saving to assess cardiovascular risk in the clinical arena.

METHODS

First, the interfaces of the intima, media, and adventitia layers are segmented, by means of an original front propagation scheme, running in a 4D multi-parametric space, to simultaneously extract three non-crossing contours in the initial cross-sectional image. Second, information resulting from the tentative contours is exploited by a machine learning approach to identify healthy and diseased regions of the arterial wall. The framework is fully automatic.

RESULTS

The method was applied to 40 patients from two different medical centers. The framework was trained on 140 images and validated on 260 other images. For the contour segmentation method, the average segmentation errors were [Formula: see text] for the intima-media interface, [Formula: see text] for the media-adventitia interface, and [Formula: see text] for the adventitia-periadventitia interface. The classification method demonstrated a good accuracy, with a median Dice coefficient equal to 0.93 and an interquartile range of (0.78-0.98).

CONCLUSION

The proposed framework demonstrated promising offline performances and could potentially be translated into a reliable tool for various clinical applications, such as quantification of tissue layer thickness and global summarization of healthy regions in entire pullbacks.

Displacement of the Lamina Cribrosa in Response to Acute Intraocular Pressure Elevation in Normal Individuals of African and European Descent

Purpose

To assess if the in vivo mechanical displacement of the anterior laminar cribrosa surface (ALCS) as a response of an acute elevation in intraocular pressure (IOP) differs in individuals of European (ED) and African descent (AD).

Methods

Spectral-domain optical coherence tomography (SDOCT) scans were obtained from 24 eyes of 12 individuals of AD and 18 eyes of 9 individuals of ED at their normal baseline IOP and after 60 seconds IOP elevation using ophthalmodynamometry. Change in depth (displacement) of the LC and to the prelaminar tissue (PLT) were computed in association with the change (delta) in IOP (Δ IOP), race, age, corneal thickness, corneal rigidity (ocular response analyzer [ORA]), and axial.

Results

In the ED group for small IOP elevations (Δ IOP < 12 mm Hg), the ALCS initially displaced posteriorly but for larger increase of IOP an anterior displacement of the lamina followed. Inversely, in the AD group the ALCS did not show a significant posterior displacement for small Δ IOP, while for larger IOP increases the ALCS significantly displaced posteriorly. Posterior displacement of the lamina cribrosa (LC) was also significantly correlated with longer axial length, higher corneal thickness, and ORA parameters. Prelaminar tissue posteriorly displaced for any magnitude of Δ IOP, in both groups.

Conclusions

The African descent group demonstrated a greater acute posterior bowing of the LC after adjustment for age, axial length, Bruch's membrane opening (BMO) area, and ORA parameters. Greater PLT posterior displacement was also seen in the AD group with increasing IOP, which was tightly correlated with the displacement of the LC.

A machine-learning graph-based approach for 3D segmentation of Bruch's membrane opening from glaucomatous SD-OCT volumes

Bruch's membrane opening-minimum rim width (BMO-MRW) is a recently proposed structural parameter which estimates the remaining nerve fiber bundles in the retina and is superior to other conventional structural parameters for diagnosing glaucoma. Measuring this structural parameter requires identification of BMO locations within spectral domain-optical coherence tomography (SD-OCT) volumes. While most automated approaches for segmentation of the BMO either segment the 2D projection of BMO points or identify BMO points in individual B-scans, in this work, we propose a machine-learning graph-based approach for true 3D segmentation of BMO from glaucomatous SD-OCT volumes. The problem is formulated as an optimization problem for finding a 3D path within the SD-OCT volume. In particular, the SD-OCT volumes are transferred to the radial domain where the closed loop BMO points in the original volume form a path within the radial volume. The estimated location of BMO points in 3D are identified by finding the projected location of BMO points using a graph-theoretic approach and mapping the projected locations onto the Bruch's membrane (BM) surface. Dynamic programming is employed in order to find the 3D BMO locations as the minimum-cost path within the volume. In order to compute the cost function needed for finding the minimum-cost path, a random forest classifier is utilized to learn a BMO model, obtained by extracting intensity features from the volumes in the training set, and computing the required 3D cost function. The proposed method is tested on 44 glaucoma patients and evaluated using manual delineations. Results show that the proposed method successfully identifies the 3D BMO locations and has significantly smaller errors compared to the existing 3D BMO identification approaches.

ShapeCut: Bayesian surface estimation using shape-driven graph

A variety of medical image segmentation problems present significant technical challenges, including heterogeneous pixel intensities, noisy/ill-defined boundaries and irregular shapes with high variability. The strategy of estimating optimal segmentations within a statistical framework that combines image data with priors on anatomical structures promises to address some of these technical challenges. However, methods that rely on local optimization techniques and/or local shape penalties (e.g., smoothness) have been proven to be inadequate for many difficult segmentation problems. These challenging segmentation problems can benefit from the inclusion of global shape priors within a maximum-a-posteriori estimation framework, which biases solutions toward an object class of interest. In this paper, we propose a maximum-a-posteriori formulation that relies on a generative image model by incorporating both local and global shape priors. The proposed method relies on graph cuts as well as a new shape parameters estimation that provides a global updates-based optimization strategy. We demonstrate our approach on synthetic datasets as well as on the left atrial wall segmentation from late-gadolinium enhancement MRI, which has been shown to be effective for identifying myocardial fibrosis in the diagnosis of atrial fibrillation. Experimental results prove the effectiveness of the proposed approach in terms of the average surface distance between extracted surfaces and the corresponding ground-truth, as well as the clinical efficacy of the method in the identification of fibrosis and scars in the atrial wall.

Automatic Subretinal Fluid Segmentation of Retinal SD-OCT Images With Neurosensory Retinal Detachment Guided by Enface Fundus Imaging

OBJECTIVE

Accurate segmentation of neurosensory retinal detachment (NRD) associated subretinal fluid in spectral domain optical coherence tomography (SD-OCT) is vital for the assessment of central serous chorioretinopathy (CSC). A novel two-stage segmentation algorithm was proposed, guided by Enface fundus imaging.

METHODS

In the first stage, Enface fundus image was segmented using thickness map prior to detecting the fluid-associated abnormalities with diffuse boundaries. In the second stage, the locations of the abnormalities were used to restrict the spatial extent of the fluid region, and a fuzzy level set method with a spatial smoothness constraint was applied to subretinal fluid segmentation in the SD-OCT scans.

RESULTS

Experimental results from 31 retinal SD-OCT volumes with CSC demonstrate that our method can achieve a true positive volume fraction (TPVF), false positive volume fraction (FPVF), and positive predicative value (PPV) of 94.3%, 0.97%, and 93.6%, respectively, for NRD regions. Our approach can also discriminate NRD-associated subretinal fluid from subretinal pigment epithelium fluid associated with pigment epithelial detachment with a TPVF, FPVF, and PPV of 93.8%, 0.40%, and 90.5%, respectively.

CONCLUSION

We report a fully automatic method for the segmentation of subretinal fluid.

SIGNIFICANCE

Our method shows the potential to improve clinical therapy for CSC.

Automated choroid segmentation in three-dimensional 1-μm wide-view OCT images with gradient and regional costs

Choroid thickness and volume estimated from optical coherence tomography (OCT) images have emerged as important metrics in disease management. This paper presents an automated three-dimensional (3-D) method for segmenting the choroid from 1 - ? m wide-view swept source OCT image volumes, including the Bruch’s membrane (BM) and the choroidal–scleral interface (CSI) segmentation. Two auxiliary boundaries are first detected by modified Canny operators and then the optical nerve head is detected and removed. The BM and the initial CSI segmentation are achieved by 3-D multiresolution graph search with gradient-based cost. The CSI is further refined by adding a regional cost, calculated from the wavelet-based gradual intensity distance. The segmentation accuracy is quantitatively evaluated on 32 normal eyes by comparing with manual segmentation and by reproducibility test. The mean choroid thickness difference from the manual segmentation is 19.16 ± 4.32 ?? ? m , the mean Dice similarity coefficient is 93.17 ± 1.30 % , and the correlation coefficients between fovea-centered volumes obtained on repeated scans are larger than 0.97.

Fast automated segmentation of multiple objects via spatially weighted shape learning

Active shape models (ASMs) have proved successful in automatic segmentation by using shape and appearance priors in a number of areas such as prostate segmentation, where accurate contouring is important in treatment planning for prostate cancer. The ASM approach however, is heavily reliant on a good initialisation for achieving high segmentation quality. This initialisation often requires algorithms with high computational complexity, such as three dimensional (3D) image registration. In this work, we present a fast, self-initialised ASM approach that simultaneously fits multiple objects hierarchically controlled by spatially weighted shape learning. Prominent objects are targeted initially and spatial weights are progressively adjusted so that the next (more difficult, less visible) object is simultaneously initialised using a series of weighted shape models. The scheme was validated and compared to a multi-atlas approach on 3D magnetic resonance (MR) images of 38 cancer patients and had the same (mean, median, inter-rater) Dice's similarity coefficients of (0.79, 0.81, 0.85), while having no registration error and a computational time of 12-15 min, nearly an order of magnitude faster than the multi-atlas approach.

Incorporation of gradient vector flow field in a multimodal graph-theoretic approach for segmenting the internal limiting membrane from glaucomatous optic nerve head-centered SD-OCT volumes

The internal limiting membrane (ILM) separates the retina and optic nerve head (ONH) from the vitreous. In the optical coherence tomography volumes of glaucoma patients, while current approaches for the segmentation of the ILM in the peripapillary and macular regions are considered robust, current approaches commonly produce ILM segmentation errors at the ONH due to the presence of blood vessels and/or characteristic glaucomatous deep cupping. Because a precise segmentation of the ILM surface at the ONH is required for computing several newer structural measurements including Bruch's membrane opening-minimum rim width (BMO-MRW) and cup volume, in this study, we propose a multimodal multiresolution graph-based method to precisely segment the ILM surface within ONH-centered spectral-domain optical coherence tomography (SD-OCT) volumes. In particular, the gradient vector flow (GVF) field, which is computed from a multiresolution initial segmentation, is employed for calculating a set of non-overlapping GVF-based columns perpendicular to the initial segmentation. The GVF columns are utilized to resample the volume and also serve as the columns to the graph construction. The ILM surface in the resampled volume is fairly smooth and does not contain the steep slopes. This prior shape knowledge along with the blood vessel information, obtained from registered fundus photographs, are incorporated in a graph-theoretic approach in order to identify the location of the ILM surface. The proposed method is tested on the SD-OCT volumes of 44 subjects with various stages of glaucoma and significantly smaller segmentation errors were obtained than that of current approaches.

Retinal status analysis method based on feature extraction and quantitative grading in OCT images

Background

Optical coherence tomography (OCT) is widely used in ophthalmology for viewing the morphology of the retina, which is important for disease detection and assessing therapeutic effect. The diagnosis of retinal diseases is based primarily on the subjective analysis of OCT images by trained ophthalmologists. This paper describes an OCT images automatic analysis method for computer-aided disease diagnosis and it is a critical part of the eye fundus diagnosis.

Methods

This study analyzed 300 OCT images acquired by Optovue Avanti RTVue XR (Optovue Corp., Fremont, CA). Firstly, the normal retinal reference model based on retinal boundaries was presented. Subsequently, two kinds of quantitative methods based on geometric features and morphological features were proposed. This paper put forward a retinal abnormal grading decision-making method which was used in actual analysis and evaluation of multiple OCT images.

Results

This paper showed detailed analysis process by four retinal OCT images with different abnormal degrees. The final grading results verified that the analysis method can distinguish abnormal severity and lesion regions. This paper presented the simulation of the 150 test images, where the results of analysis of retinal status showed that the sensitivity was 0.94 and specificity was 0.92.The proposed method can speed up diagnostic process and objectively evaluate the retinal status.

Conclusions

This paper aims on studies of retinal status automatic analysis method based on feature extraction and quantitative grading in OCT images. The proposed method can obtain the parameters and the features that are associated with retinal morphology. Quantitative analysis and evaluation of these features are combined with reference model which can realize the target image abnormal judgment and provide a reference for disease diagnosis.

Voxel Based Morphometry in Optical Coherence Tomography: Validation & Core Findings

Optical coherence tomography (OCT) of the human retina is now becoming established as an important modality for the detection and tracking of various ocular diseases. Voxel based morphometry (VBM) is a long standing neuroimaging analysis technique that allows for the exploration of the regional differences in the brain. There has been limited work done in developing registration based methods for OCT, which has hampered the advancement of VBM analyses in OCT based population studies. Following on from our recent development of an OCT registration method, we explore the potential benefits of VBM analysis in cohorts of healthy controls (HCs) and multiple sclerosis (MS) patients. Specifically, we validate the stability of VBM analysis in two pools of HCs showing no significant difference between the two populations. Additionally, we also present a retrospective study of age and sex matched HCs and relapsing remitting MS patients, demonstrating results consistent with the reported literature while providing insight into the retinal changes associated with this MS subtype.

An automated framework for 3D serous pigment epithelium detachment segmentation in SD-OCT images

Pigment epithelium detachment (PED) is an important clinical manifestation of multiple chorioretinal diseases, which can cause loss of central vision. In this paper, an automated framework is proposed to segment serous PED in SD-OCT images. The proposed framework consists of four main steps: first, a multi-scale graph search method is applied to segment abnormal retinal layers; second, an effective AdaBoost method is applied to refine the initial segmented regions based on 62 extracted features; third, a shape-constrained graph cut method is applied to segment serous PED, in which the foreground and background seeds are obtained automatically; finally, an adaptive structure elements based morphology method is applied to remove false positive segmented regions. The proposed framework was tested on 25 SD-OCT volumes from 25 patients diagnosed with serous PED. The average true positive volume fraction (TPVF), false positive volume fraction (FPVF), dice similarity coefficient (DSC) and positive predictive value (PPV) are 90.08%, 0.22%, 91.20% and 92.62%, respectively. The proposed framework can provide clinicians with accurate quantitative information, including shape, size and position of the PED region, which can assist clinical diagnosis and treatment.

Fully Automatic Localization and Segmentation of 3D Vertebral Bodies from CT/MR Images via a Learning-Based Method

In this paper, we address the problems of fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images. We propose a learning-based, unified random forest regression and classification framework to tackle these two problems. More specifically, in the first stage, the localization of 3D vertebral bodies is solved with random forest regression where we aggregate the votes from a set of randomly sampled image patches to get a probability map of the center of a target vertebral body in a given image. The resultant probability map is then further regularized by Hidden Markov Model (HMM) to eliminate potential ambiguity caused by the neighboring vertebral bodies. The output from the first stage allows us to define a region of interest (ROI) for the segmentation step, where we use random forest classification to estimate the likelihood of a voxel in the ROI being foreground or background. The estimated likelihood is combined with the prior probability, which is learned from a set of training data, to get the posterior probability of the voxel. The segmentation of the target vertebral body is then done by a binary thresholding of the estimated probability. We evaluated the present approach on two openly available datasets: 1) 3D T2-weighted spine MR images from 23 patients and 2) 3D spine CT images from 10 patients. Taking manual segmentation as the ground truth (each MR image contains at least 7 vertebral bodies from T11 to L5 and each CT image contains 5 vertebral bodies from L1 to L5), we evaluated the present approach with leave-one-out experiments. Specifically, for the T2-weighted MR images, we achieved for localization a mean error of 1.6 mm, and for segmentation a mean Dice metric of 88.7% and a mean surface distance of 1.5 mm, respectively. For the CT images we achieved for localization a mean error of 1.9 mm, and for segmentation a mean Dice metric of 91.0% and a mean surface distance of 0.9 mm, respectively.

MASCG: Multi-Atlas Segmentation Constrained Graph method for accurate segmentation of hip CT images

This paper addresses the issue of fully automatic segmentation of a hip CT image with the goal to preserve the joint structure for clinical applications in hip disease diagnosis and treatment. For this purpose, we propose a Multi-Atlas Segmentation Constrained Graph (MASCG) method. The MASCG method uses multi-atlas based mesh fusion results to initialize a bone sheetness based multi-label graph cut for an accurate hip CT segmentation which has the inherent advantage of automatic separation of the pelvic region from the bilateral proximal femoral regions. We then introduce a graph cut constrained graph search algorithm to further improve the segmentation accuracy around the bilateral hip joint regions. Taking manual segmentation as the ground truth, we evaluated the present approach on 30 hip CT images (60 hips) with a 15-fold cross validation. When the present approach was compared to manual segmentation, an average surface distance error of 0.30 mm, 0.29 mm, and 0.30 mm was found for the pelvis, the left proximal femur, and the right proximal femur, respectively. A further look at the bilateral hip joint regions demonstrated an average surface distance error of 0.16 mm, 0.21 mm and 0.20 mm for the acetabulum, the left femoral head, and the right femoral head, respectively.

Automated choroid segmentation based on gradual intensity distance in HD-OCT images

The choroid is an important structure of the eye and plays a vital role in the pathology of retinal diseases. This paper presents an automated choroid segmentation method for high-definition optical coherence tomography (HD-OCT) images, including Bruch's membrane (BM) segmentation and choroidal-scleral interface (CSI) segmentation. An improved retinal nerve fiber layer (RNFL) complex removal algorithm is presented to segment BM by considering the structure characteristics of retinal layers. By analyzing the characteristics of CSI boundaries, we present a novel algorithm to generate a gradual intensity distance image. Then an improved 2-D graph search method with curve smooth constraints is used to obtain the CSI segmentation. Experimental results with 212 HD-OCT images from 110 eyes in 66 patients demonstrate that the proposed method can achieve high segmentation accuracy. The mean choroid thickness difference and overlap ratio between our proposed method and outlines drawn by experts was 6.72µm and 85.04%, respectively.

Automated 3-D retinal layer segmentation of macular optical coherence tomography images with serous pigment epithelial detachments

Automated retinal layer segmentation of optical coherence tomography (OCT) images has been successful for normal eyes but becomes challenging for eyes with retinal diseases if the retinal morphology experiences critical changes. We propose a method to automatically segment the retinal layers in 3-D OCT data with serous retinal pigment epithelial detachments (PED), which is a prominent feature of many chorioretinal disease processes. The proposed framework consists of the following steps: fast denoising and B-scan alignment, multi-resolution graph search based surface detection, PED region detection and surface correction above the PED region. The proposed technique was evaluated on a dataset with OCT images from 20 subjects diagnosed with PED. The experimental results showed the following. 1) The overall mean unsigned border positioning error for layer segmentation is 7.87±3.36 μm , and is comparable to the mean inter-observer variability ( 7.81±2.56 μm). 2) The true positive volume fraction (TPVF), false positive volume fraction (FPVF) and positive predicative value (PPV) for PED volume segmentation are 87.1%, 0.37%, and 81.2%, respectively. 3) The average running time is 220 s for OCT data of 512 × 64 × 480 voxels.

Fast segmentation of anterior segment optical coherence tomography images using graph cut

Background

Optical coherence tomography (OCT) is a non-invasive imaging system that can be used to obtain images of the anterior segment. Automatic segmentation of these images will enable them to be used to construct patient specific biomechanical models of the human eye. These models could be used to help with treatment planning and diagnosis of patients.

Methods

A novel graph cut technique using regional and shape terms was developed. It was evaluated by segmenting 39 OCT images of the anterior segment. The results of this were compared with manual segmentation and a previously reported level set segmentation technique. Three different comparison techniques were used: Dice’s similarity coefficient (DSC), mean unsigned surface positioning error (MSPE), and 95% Hausdorff distance (HD). A paired t-test was used to compare the results of different segmentation techniques.

Results

When comparison with manual segmentation was performed, a mean DSC value of 0.943 ± 0.020 was achieved, outperforming other previously published techniques. A substantial reduction in processing time was also achieved using this method.

Conclusions

We have developed a new segmentation technique that is both fast and accurate. This has the potential to be used to aid diagnostics and treatment planning.

Longitudinal graph-based segmentation of macular OCT using fundus alignment

Segmentation of retinal layers in optical coherence tomography (OCT) has become an important diagnostic tool for a variety of ocular and neurological diseases. Currently all OCT segmentation algorithms analyze data independently, ignoring previous scans, which can lead to spurious measurements due to algorithm variability and failure to identify subtle changes in retinal layers. In this paper, we present a graph-based segmentation framework to provide consistent longitudinal segmentation results. Regularization over time is accomplished by adding weighted edges between corresponding voxels at each visit. We align the scans to a common subject space before connecting the graphs by registering the data using both the retinal vasculature and retinal thickness generated from a low resolution segmentation. This initial segmentation also allows the higher dimensional temporal problem to be solved more efficiently by reducing the graph size. Validation is performed on longitudinal data from 24 subjects, where we explore the variability between our longitudinal graph method and a cross-sectional graph approach. Our results demonstrate that the longitudinal component improves segmentation consistency, particularly in areas where the boundaries are difficult to visualize due to poor scan quality.

Multi-surface and multi-field co-segmentation of 3-D retinal optical coherence tomography

When segmenting intraretinal layers from multiple optical coherence tomography (OCT) images forming a mosaic or a set of repeated scans, it is attractive to exploit the additional information from the overlapping areas rather than discarding it as redundant, especially in low contrast and noisy images. However, it is currently not clear how to effectively combine the multiple information sources available in the areas of overlap. In this paper, we propose a novel graph-theoretic method for multi-surface multi-field co-segmentation of intraretinal layers, assuring consistent segmentation of the fields across the overlapped areas. After 2-D en-face alignment, all the fields are segmented simultaneously, imposing a priori soft interfield-intrasurface constraints for each pair of overlapping fields. The constraints penalize deviations from the expected surface height differences, taken to be the depth-axis shifts that produce the maximum cross-correlation of pairwise-overlapped areas. The method's accuracy and reproducibility are evaluated qualitatively and quantitatively on 212 OCT images (20 nine-field, 32 single-field acquisitions) from 26 patients with glaucoma. Qualitatively, the obtained thickness maps show no stitching artifacts, compared to pronounced stitches when the fields are segmented independently. Quantitatively, two ophthalmologists manually traced four intraretinal layers on 10 patients, and the average error ( 4.58 ±1.46 μm) was comparable to the average difference between the observers ( 5.86±1.72 μm). Furthermore, we show the benefit of the proposed approach in co-segmenting longitudinal scans. As opposed to segmenting layers in each of the fields independently, the proposed co-segmentation method obtains consistent segmentations across the overlapped areas, producing accurate, reproducible, and artifact-free results.

Subvoxel accurate graph search using non-Euclidean graph space

Graph search is attractive for the quantitative analysis of volumetric medical images, and especially for layered tissues, because it allows globally optimal solutions in low-order polynomial time. However, because nodes of graphs typically encode evenly distributed voxels of the volume with arcs connecting orthogonally sampled voxels in Euclidean space, segmentation cannot achieve greater precision than a single unit, i.e. the distance between two adjoining nodes, and partial volume effects are ignored. We generalize the graph to non-Euclidean space by allowing non-equidistant spacing between nodes, so that subvoxel accurate segmentation is achievable. Because the number of nodes and edges in the graph remains the same, running time and memory use are similar, while all the advantages of graph search, including global optimality and computational efficiency, are retained. A deformation field calculated from the volume data adaptively changes regional node density so that node density varies with the inverse of the expected cost. We validated our approach using optical coherence tomography (OCT) images of the retina and 3-D MR of the arterial wall, and achieved statistically significant increased accuracy. Our approach allows improved accuracy in volume data acquired with the same hardware, and also, preserved accuracy with lower resolution, more cost-effective, image acquisition equipment. The method is not limited to any specific imaging modality and readily extensible to higher dimensions.

Automated retinal layers segmentation in SD-OCT images using dual-gradient and spatial correlation smoothness constraint

Automatic segmentation of retinal layers in spectral domain optical coherence tomography (SD-OCT) images plays a vital role in the quantitative assessment of retinal disease, because it provides detailed information which is hard to process manually. A number of algorithms to automatically segment retinal layers have been developed; however, accurate edge detection is challenging. We developed an automatic algorithm for segmenting retinal layers based on dual-gradient and spatial correlation smoothness constraint. The proposed algorithm utilizes a customized edge flow to produce the edge map and a convolution operator to obtain local gradient map in the axial direction. A valid search region is then defined to identify layer boundaries. Finally, a spatial correlation smoothness constraint is applied to remove anomalous points at the layer boundaries. Our approach was tested on two datasets including 10 cubes from 10 healthy eyes and 15 cubes from 6 patients with age-related macular degeneration. A quantitative evaluation of our method was performed on more than 600 images from cubes obtained in five healthy eyes. Experimental results demonstrated that the proposed method can estimate six layer boundaries accurately. Mean absolute boundary positioning differences and mean absolute thickness differences (mean±SD) were 4.43±3.32 μm and 0.22±0.24 μm, respectively.

LOGISMOS-B: layered optimal graph image segmentation of multiple objects and surfaces for the brain

Automated reconstruction of the cortical surface is one of the most challenging problems in the analysis of human brain magnetic resonance imaging (MRI). A desirable segmentation must be both spatially and topologically accurate, as well as robust and computationally efficient. We propose a novel algorithm, LOGISMOS-B, based on probabilistic tissue classification, generalized gradient vector flows and the LOGISMOS graph segmentation framework. Quantitative results on MRI datasets from both healthy subjects and multiple sclerosis patients using a total of 16,800 manually placed landmarks illustrate the excellent performance of our algorithm with respect to spatial accuracy. Remarkably, the average signed error was only 0.084 mm for the white matter and 0.008 mm for the gray matter, even in the presence of multiple sclerosis lesions. Statistical comparison shows that LOGISMOS-B produces a significantly more accurate cortical reconstruction than FreeSurfer, the current state-of-the-art approach (p << 0.001). Furthermore, LOGISMOS-B enjoys a run time that is less than a third of that of FreeSurfer, which is both substantial, considering the latter takes 10 h/subject on average, and a statistically significant speedup.

Probabilistic intra-retinal layer segmentation in 3-D OCT images using global shape regularization

With the introduction of spectral-domain optical coherence tomography (OCT), resulting in a significant increase in acquisition speed, the fast and accurate segmentation of 3-D OCT scans has become evermore important. This paper presents a novel probabilistic approach, that models the appearance of retinal layers as well as the global shape variations of layer boundaries. Given an OCT scan, the full posterior distribution over segmentations is approximately inferred using a variational method enabling efficient probabilistic inference in terms of computationally tractable model components: Segmenting a full 3-D volume takes around a minute. Accurate segmentations demonstrate the benefit of using global shape regularization: We segmented 35 fovea-centered 3-D volumes with an average unsigned error of 2.46 ± 0.22 μm as well as 80 normal and 66 glaucomatous 2-D circular scans with errors of 2.92 ± 0.5 μm and 4.09 ± 0.98 μm respectively. Furthermore, we utilized the inferred posterior distribution to rate the quality of the segmentation, point out potentially erroneous regions and discriminate normal from pathological scans. No pre- or postprocessing was required and we used the same set of parameters for all data sets, underlining the robustness and out-of-the-box nature of our approach.

Multiple-object geometric deformable model for segmentation of macular OCT

Optical coherence tomography (OCT) is the de facto standard imaging modality for ophthalmological assessment of retinal eye disease, and is of increasing importance in the study of neurological disorders. Quantification of the thicknesses of various retinal layers within the macular cube provides unique diagnostic insights for many diseases, but the capability for automatic segmentation and quantification remains quite limited. While manual segmentation has been used for many scientific studies, it is extremely time consuming and is subject to intra- and inter-rater variation. This paper presents a new computational domain, referred to as flat space, and a segmentation method for specific retinal layers in the macular cube using a recently developed deformable model approach for multiple objects. The framework maintains object relationships and topology while preventing overlaps and gaps. The algorithm segments eight retinal layers over the whole macular cube, where each boundary is defined with subvoxel precision. Evaluation of the method on single-eye OCT scans from 37 subjects, each with manual ground truth, shows improvement over a state-of-the-art method.