No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Three-dimensional segmentation of retroperitoneal masses using continuous convex relaxation and accumulated gradient distance for radiotherapy planning
Abstract
An innovative algorithm has been developed for the segmentation of retroperitoneal tumors in 3D radiological images. This algorithm makes it possible for radiation oncologists and surgeons semiautomatically to select tumors for possible future radiation treatment and surgery. It is based on continuous convex relaxation methodology, the main novelty being the introduction of accumulated gradient distance, with intensity and gradient information being incorporated into the segmentation process. The algorithm was used to segment 26 CT image volumes. The results were compared with manual contouring of the same tumors. The proposed algorithm achieved 90 % sensitivity, 100 % specificity and 84 % positive predictive value, obtaining a mean distance to the closest point of 3.20 pixels. The algorithm's dependence on the initial manual contour was also analyzed, with results showing that the algorithm substantially reduced the variability of the manual segmentation carried out by different specialists. The algorithm was also compared with four benchmark algorithms (thresholding, edge-based level-set, region-based level-set and continuous max-flow with two labels). To the best of our knowledge, this is the first time the segmentation of retroperitoneal tumors for radiotherapy planning has been addressed.
... Over recent years, energy minimization algorithms based on convex relaxation have been developed [29,30]. This paper presents an algorithm using convex relaxation based on a previous work by the authors [31,32]. The original idea was proposed by Papadakis and Rabin [33]. ...
Basal Cell Carcinoma (BCC) is the most frequent skin cancer and its increasing incidence is producing a high overload in dermatology services. In this sense, it is convenient to aid physicians in detecting it soon. Thus, in this paper, we propose a tool for the detection of BCC to provide a prioritization in the teledermatology consultation. Firstly, we analyze if a previous segmentation of the lesion improves the ulterior classification of the lesion. Secondly, we analyze three deep neural networks and ensemble architectures to distinguish between BCC and nevus, and BCC and other skin lesions. The best segmentation results are obtained with a SegNet deep neural network. A 98% accuracy for distinguishing BCC from nevus and a 95% accuracy classifying BCC vs. all lesions have been obtained. The proposed algorithm outperforms the winner of the challenge ISIC 2019 in almost all the metrics. Finally, we can conclude that when deep neural networks are used to classify, a previous segmentation of the lesion does not improve the classification results. Likewise, the ensemble of different neural network configurations improves the classification performance compared with individual neural network classifiers. Regarding the segmentation step, supervised deep learning-based methods outperform unsupervised ones.
In order to obtain scaffold that can meet the therapeutic effect, researchers have carried out research on irregular porous structures. However, there are deficiencies in the design method of accurately controlling the apparent elastic modulus of the structure at present. Natural bone has a gradient porous structure. However, there are few studies on the mechanical property advantages of gradient bionic bone scaffold. In this paper, an improved method based on Voronoi-tessellation is proposed. The method can get controllable gradient scaffolds to fit the modulus of natural bone, and accurately control the apparent elastic modulus of porous structure, which is conducive to improving the stress shielding. To verify the designed structure can be fabricated by additive manufacturing, several designed models are obtained by SLM and EBM. Through finite element analysis (FEA), it is verified that the irregular porous structure based on Voronoi-tessellation is more stable than the traditional regular porous structure of the same structure volume, the same pore number and the same material. Furthermore, it is verified that the gradient irregular structure has a better stability than the non-gradient structure. An experiment is conducted successfully to verify the stability performance got by FEA. In addition, a dynamic impact FEA is also performed to simulate impact resistance. The result shows that the impact resistance of the regular porous structure, the irregular porous structure and the gradient irregular porous structure becomes better in turn. The mechanical property verification provides a theoretical basis for the structural design of gradient irregular porous bone tissue engineering scaffolds.
Purpose:
To develop a 4-dimensional computerized magnetic resonance imaging phantom with image textures extracted from real patient scans for liver motion studies.
Methods:
The proposed phantom was developed based on the current version of 4-dimensional extended cardiac-torso computerized phantom and a clinical magnetic resonance scan. Initially, the extended cardiac-torso phantom was voxelized in abdominal-chest region at the end of exhalation phase. Structures/tissues were classified into 4 categories: (1) Seven key textured organs, including liver, gallbladder, spleen, stomach, heart, kidneys, and pancreas, were mapped from a clinical T1-weighted liver magnetic resonance scan using deformable registration. (2) Large textured soft tissue volumes were simulated via an iterative pattern generation method using the same magnetic resonance scan. (3) Lung and intestine structures were generated by assigning uniform intensity with proper noise modeling. (4) Bony structures were generated by assigning the magnetic resonance values. A spherical hypointensity tumor was inserted into the liver. Other respiratory phases of the 4-dimensional phantom were generated using the backward deformation vector fields exported by the extended cardiac-torso program, except that bony structures were generated separately for each phase. A weighted image filtering process was utilized to improve the overall tissue smoothness at each phase.
Results:
Three 4-dimensional series with different motion amplitudes were generated. The developed motion phantom produced good illustrations of abdominal-chest region with anatomical structures in key organs and texture patterns in large soft tissue volumes. In a standard series, the tumor volume was measured as 13.90 ± 0.11 cm(3) in a respiratory cycle and the tumor's maximum center-of-mass shift was 2.95 cm/1.84 cm on superior-inferior/anterior-posterior directions. The organ motion during the respiratory cycle was well rendered. The developed motion phantom has the flexibility of motion pattern variation, organ geometry variation, and tumor modeling variation.
Conclusions:
A 4-D computerized phantom was developed and could be used to produce image series with synthetic magnetic resonance textures for magnetic resonance imaging research of liver motion.
Purpose:
In 2005, an application for surgical planning called AYRA[Formula: see text] was designed and validated by different surgeons and engineers at the Virgen del Rocío University Hospital, Seville (Spain). However, the segmentation methods included in AYRA and in other surgical planning applications are not able to segment accurately tumors that appear in soft tissue. The aims of this paper are to offer an exhaustive validation of an accurate semiautomatic segmentation tool to delimitate retroperitoneal tumors from CT images and to aid physicians in planning both radiotherapy doses and surgery.
Methods:
A panel of 6 experts manually segmented 11 cases of tumors, and the segmentation results were compared exhaustively with: the results provided by a surgical planning tool (AYRA), the segmentations obtained using a radiotherapy treatment planning system (Pinnacle[Formula: see text]), the segmentation results obtained by a group of experts in the delimitation of retroperitoneal tumors and the segmentation results using the algorithm under validation.
Results:
11 cases of retroperitoneal tumors were tested. The proposed algorithm provided accurate results regarding the segmentation of the tumor. Moreover, the algorithm requires minimal computational time-an average of 90.5% less than that required when manually contouring the same tumor.
Conclusion:
A method developed for the semiautomatic selection of retroperitoneal tumor has been validated in depth. AYRA, as well as other surgical and radiotherapy planning tools, could be greatly improved by including this algorithm.
We propose a novel algorithm to jointly delineate the femoral artery lumen and outer wall surfaces from 3D black-blood MR images, while enforcing the spatial consistency of the reoriented MR slices along the medial axis of the femoral artery. We demonstrate that the resulting optimization problem of the proposed segmentation can be solved globally and exactly by means of convex relaxation, for which we introduce a novel coupled continuous max-flow (CCOMF) model based on an Ishikawa-type flow configuration and show its duality to the studied convex relaxed optimization problem. Using the proposed CCMF model, the exactness and globalness of its dual convex relaxation problem is proven. Experiment results demonstrate that the proposed method yielded high accuracy (i.e. Dice similarity coefficient > 85%) for both the lumen and outer wall and high reproducibility (intra-class correlation coefficient of 0.95) for generating vessel wall area. The proposed method outperformed the previous method, in terms of computation time, by a factor of pproximately 20.
Intraventricular hemorrhage (IVH) is a common disease among preterm infants with an occurrence of 12-20% in those born at less than 35 weeks gestational age. Neonates at risk of IVH are monitored by conventional 2D ultrasound (US) for hemorrhage and potential ventricular dilation. Compared to 2D US relying on linear measurements from a single slice and visually estimates to determine ventricular dilation, 3D US can provide volumetric ventricle measurements, more sensitive to longitudinal changes in ventricular volume. In this work, we propose a global optimization-based surface evolution approach to the segmentation of the lateral ventricles in preterm neonates with IVH. The proposed segmentation approach makes use of convex optimization technique in combination with a subject-specific shape model. We show that the introduced challenging combinatorial optimization problem can be solved globally by means of convex relaxation. In this regard, we propose a coupled continuous max-flow model, which derives a new and efficient dual based algorithm, that can be implemented on GPUs to achieve a high-performance in numerics. Experiments demonstrate the advantages of our approach in both accuracy and efficiency. To the best of our knowledge, this paper reports the first study on semi-automatic segmentation of lateral ventricles in neonates with IVH from 3D US images.
We propose a novel global optimization-based approach to segmentation of 3-D prostate transrectal ultrasound (TRUS) and T2 weighted magnetic resonance (MR) images, enforcing inherent axial symmetry of prostate shapes to simultaneously adjust a series of 2-D slice-wise segmentations in a “global” 3-D sense. We show that the introduced challenging combinatorial optimization problem can be solved globally and exactly by means of convex relaxation. In this regard, we propose a novel coherent continuous max-flow model (CCMFM), which derives a new and efficient duality-based algorithm, leading to a GPU-based implementation to achieve high computational speeds. Experiments with 25 3-D TRUS images and 30 3-D T2w MR images from our dataset, and 50 3-D T2w MR images from a public dataset, demonstrate that the proposed approach can segment a 3-D prostate TRUS/MR image within 5–6 s including 4–5 s for initialization, yielding a mean Dice similarity coefficient of $93.2%pm 2.0%$ for 3-D TRUS images and $88.5%pm 3.5%$ for 3-D MR images. The proposed method also yields relatively low intra- and inter-observer variability introduced by user manual initialization, suggesting a high reproducibility, independent of observers.
Primary retroperitoneal masses are a rare but important group of neoplasms. Cross-sectional imaging has revolutionised the investigation of patients with retroperitoneal neoplasms. Both computed tomography (CT) and magnetic resonance imaging (MRI) can contribute to tumour diagnosis, though histological confirmation is often required because of the considerable overlap of imaging features. Cross-sectional imaging is key to the pre-operative staging and planning of retroperitoneal masses, though ultrasound may also help in certain instances. Imaging also helps to select and guide the site to biopsy from these usually large and heterogeneous neoplasms. This article aims to review many of the primary retroperitoneal neoplasms that may be encountered by the radiologist.
In this paper, we present a graph cut application dealing with MRI brain image segmentation. We here propose another emerging approach of region segmentation based on graph cut which supports on the eigenspace characteristics and the perceptual grouping properties to classify brain tumoral tissue. Image segmentation is considered as solving the partitioning clustering problem by extracting the global impression of image. In the aim of providing visual and quantitative information for the diagnosis help in brain diseases, tumor features observed in image sequences must be extracted efficiently. We lastly extend this approach to perform volume segmentation by matching 2D contours set. This D representation provides a precise quantitative measure for following up the tumor brain evolution in the case of patients under pharmaceutical treatments.
Combinatorial graph cut algorithms have been successfully applied to a wide range of problems in vision and graphics. This paper focusses on possibly the simplest application of graph-cuts: segmentation of objects in image data. Despite its simplicity, this application epitomizes the best features of combinatorial graph cuts methods in vision: global optima, practical efficiency, numerical robustness, ability to fuse a wide range of visual cues and constraints, unrestricted topological properties of segments, and applicability to N-D problems. Graph cuts based approaches to object extraction have also been shown to have interesting connections with earlier segmentation methods such as snakes, geodesic active contours, and level-sets. The segmentation energies optimized by graph cuts combine boundary regularization with region-based properties in the same fashion as Mumford-Shah style functionals. We present motivation and detailed technical description of the basic combinatorial optimization framework for image segmentation via s/t graph cuts. After the general concept of using binary graph cut algorithms for object segmentation was first proposed and tested in Boykov and Jolly (2001), this idea was widely studied in computer vision and graphics communities. We provide links to a large number of known extensions based on iterative parameter re-estimation and learning, multi-scale or hierarchical approaches, narrow bands, and other techniques for demanding photo, video, and medical applications.
Segmenting 3D end firing transrectal ultrasound (TRUS) prostate images efficiently and accurately is of utmost importance for the planning and guiding 3D TRUS guided prostate biopsy. Poor image quality and imaging artifacts of 3D TRUS images often introduce a challenging task in computation to directly extract the 3D prostate surface. In this work, we propose a novel global optimization approach to delineate 3D prostate boundaries using its rotational resliced images around a specified axis, which properly enforces the inherent rotational symmetry of prostate shapes to jointly adjust a series of 2D slice wise segmentations in the global 3D sense. We show that the introduced challenging combinatorial optimization problem can be solved globally and exactly by means of convex relaxation. In this regard, we propose a novel coupled continuous max-flow model, which not only provides a powerful mathematical tool to analyze the proposed optimization problem but also amounts to a new and efficient duality-based algorithm. Extensive experiments demonstrate that the proposed method significantly outperforms the state-of-art methods in terms of efficiency, accuracy, reliability and less user-interactions, and reduces the execution time by a factor of 100.
Ultrasound-guided prostate interventions could benefit from incorporating the radiologic localization of the tumor which can be acquired from multiparametric MRI. To enable this integration, we propose and compare two solutions for registration of T2 weighted MR images with transrectal ultrasound. Firstly, we propose an innovative and practical approach based on deformable registration of binary label maps obtained from manual segmentation of the gland in the two modalities. This resulted in a target registration error of 3.6±1.7 mm. Secondly, we report a novel surface-based registration method that uses a biomechanical model of the tissue and results in registration error of 3.2±1.3 mm. We compare the two methods in terms of accuracy, clinical use and technical limitations.
In this paper, we propose a novel global optimization based 3D multi-region segmentation algorithm for T1-weighted black-blood carotid magnetic resonance (MR) images. The proposed algorithm partitions a 3D carotid MR image into 3 regions: wall, lumen, and background. The algorithm performs such partitioning by simultaneously evolving two coupled 3D surfaces of carotid artery adventitia boundary (AB) and lumen-intima boundary (LIB) while preserving their anatomical inter-surface consistency such that the LIB is always located within the AB. In particular, we show that the proposed algorithm results in
a fully time implicit scheme that propagates the two linearly ordered surfaces of the AB and LIB to their globally optimal positions during each discrete time frame by convex relaxation. In this regard, we introduce the continuous max-flow model and prove its duality/equivalence to the convex relaxed optimization
problem with respect to each evolution step. We then propose a fully parallelized continuous max-flow-based algorithm, which can be readily implemented on a GPU to achieve high computational
efficiency. Extensive experiments, with four users using 12 3T MR and 26 1.5T MR images, demonstrate that the proposed algorithm yields high accuracy and low operator variability in computing vessel wall volume. In addition, we show the algorithm outperforms previous methods in terms of high computational
efficiency and robustness with fewer user interactions.
Purpose
The segmentation of prostate in CT images is of essential importance to external beam radiotherapy, which is one of the major treatments for prostate cancer nowadays. During the radiotherapy, the prostate is radiated by high‐energy x rays from different directions. In order to maximize the dose to the cancer and minimize the dose to the surrounding healthy tissues (e.g., bladder and rectum), the prostate in the new treatment image needs to be accurately localized. Therefore, the effectiveness and efficiency of external beam radiotherapy highly depend on the accurate localization of the prostate. However, due to the low contrast of the prostate with its surrounding tissues (e.g., bladder), the unpredicted prostate motion, and the large appearance variations across different treatment days, it is challenging to segment the prostate in CT images. In this paper, the authors present a novel classification based segmentation method to address these problems.
Methods
To segment the prostate, the proposed method first uses sparse representation based classification (SRC) to enhance the prostate in CT images by pixel‐wise classification, in order to overcome the limitation of poor contrast of the prostate images. Then, based on the classification results, previous segmented prostates of the same patient are used as patient‐specific atlases to align onto the current treatment image and the majority voting strategy is finally adopted to segment the prostate. In order to address the limitations of the traditional SRC in pixel‐wise classification, especially for the purpose of segmentation, the authors extend SRC from the following four aspects: (1) A discriminant subdictionary learning method is proposed to learn a discriminant and compact representation of training samples for each class so that the discriminant power of SRC can be increased and also SRC can be applied to the large‐scale pixel‐wise classification. (2) The L1 regularized sparse coding is replaced by the elastic net in order to obtain a smooth and clear prostate boundary in the classification result. (3) Residue‐based linear regression is incorporated to improve the classification performance and to extend SRC from hard classification to soft classification. (4) Iterative SRC is proposed by using context information to iteratively refine the classification results.
Results
The proposed method has been comprehensively evaluated on a dataset consisting of 330 CT images from 24 patients. The effectiveness of the extended SRC has been validated by comparing it with the traditional SRC based on the proposed four extensions. The experimental results show that our extended SRC can obtain not only more accurate classification results but also smoother and clearer prostate boundary than the traditional SRC. Besides, the comparison with other five state‐of‐the‐art prostate segmentation methods indicates that our method can achieve better performance than other methods under comparison.
Conclusions
The authors have proposed a novel prostate segmentation method based on the sparse representation based classification, which can achieve considerably accurate segmentation results in CT prostate segmentation.
A method of local contrast enhancement in space frequency domain together with a segmentation method for medical 3D-CT image data by active contours is presented. The pur-pose of the project is to define tumor volumes for irradiation in cancer therapy. For a better performance of the contour-ing algorithm the image is primarily processed by a nonli-near operator in space frequency domain for local contrast enhancement.
Common error in bibliographies: "Étude comparative de la distribution florale dans une portion des Alpes et des Jura".
Level set methods have been widely used in image processing and computer vision. In conventional level set formulations, the level set function typically develops irregularities during its evolution, which may cause numerical errors and eventually destroy the stability of the evolution. Therefore, a numerical remedy, called reinitialization, is typically applied to periodically replace the degraded level set function with a signed distance function. However, the practice of reinitialization not only raises serious problems as when and how it should be performed, but also affects numerical accuracy in an undesirable way. This paper proposes a new variational level set formulation in which the regularity of the level set function is intrinsically maintained during the level set evolution. The level set evolution is derived as the gradient flow that minimizes an energy functional with a distance regularization term and an external energy that drives the motion of the zero level set toward desired locations. The distance regularization term is defined with a potential function such that the derived level set evolution has a unique forward-and-backward (FAB) diffusion effect, which is able to maintain a desired shape of the level set function, particularly a signed distance profile near the zero level set. This yields a new type of level set evolution called distance regularized level set evolution (DRLSE). The distance regularization effect eliminates the need for reinitialization and thereby avoids its induced numerical errors. In contrast to complicated implementations of conventional level set formulations, a simpler and more efficient finite difference scheme can be used to implement the DRLSE formulation. DRLSE also allows the use of more general and efficient initialization of the level set function. In its numerical implementation, relatively large time steps can be used in the finite difference scheme to reduce the number of iterations, while ensuring sufficient-
-
numerical accuracy. To demonstrate the effectiveness of the DRLSE formulation, we apply it to an edge-based active contour model for image segmentation, and provide a simple narrowband implementation to greatly reduce computational cost.
Lymph nodes routinely need to be considered in clinical practice in all kinds of oncological examinations. Automatic detection of lymph nodes from chest CT data is however challenging because of low contrast and clutter. Sliding window detectors using traditional features easily get confused by similar structures like muscles and vessels. It recently has been proposed to combine segmentation and detection to improve the detection performance. Features extracted from a segmentation that is initialized with a detection candidate can be used to train a classifier that decides whether the detection is a true or false positive. In this paper, the graph cuts method is adapted to the problem of lymph nodes segmentation. We propose a setting that requires only a single positive seed and at the same time solves the small cut problem of graph cuts. Furthermore, we propose a feature set that is extracted from the candidate segmentation. A classifier is trained on this feature set and used to reject false alarms. Cross validation on 54 CT datasets showed that the proposed system reaches a detection rate of 60.9% with only 6.1 false alarms per volume image, which is better than the current state of the art of mediastinal lymph node detection.
This paper is devoted to the optimization problem of continuous multi-partitioning, or multi-labeling, which is based on a convex relaxation of the continuous Potts model. In contrast to previous efforts, which are tackling the optimal labeling problem in a direct manner, we first propose a novel dual model and then build up a corresponding duality-based approach. By analyzing the dual formulation, sufficient conditions are derived which show that the relaxation is often exact, i.e. there exists optimal solutions that are also globally optimal to the original nonconvex Potts model. In order to deal with the nonsmooth dual problem, we develop a smoothing method based on the log-sum exponential function and indicate that such a smoothing approach leads to a novel smoothed primal-dual model and suggests labelings with maximum entropy. Such a smoothing method for the dual model also yields a new thresholding scheme to obtain approximate solutions. An expectation maximization like algorithm is proposed based on the smoothed formulation which is shown to be superior in efficiency compared to earlier approaches from continuous optimization. Numerical experiments also show that our method outperforms several competitive approaches in various aspects, such as lower energies and better visual quality.
Introduced the statistic kappa to measure nominal scale agreement between a fixed pair of raters. Kappa was generalized to the case where each of a sample of 30 patients was rated on a nominal scale by the same number of psychiatrist raters (n = 6), but where the raters rating 1 s were not necessarily the same as those rating another. Large sample standard errors were derived.
Lymph nodes are assessed routinely in clinical practice and their size is followed throughout radiation or chemotherapy to monitor the effectiveness of cancer treatment. This paper presents a robust learning-based method for automatic detection and segmentation of solid lymph nodes from CT data, with the following contributions. First, it presents a learning based approach to solid lymph node detection that relies on marginal space learning to achieve great speedup with virtually no loss in accuracy. Second, it presents a computationally efficient segmentation method for solid lymph nodes (LN). Third, it introduces two new sets of features that are effective for LN detection, one that self-aligns to high gradients and another set obtained from the segmentation result. The method is evaluated for axillary LN detection on 131 volumes containing 371 LN, yielding a 83.0% detection rate with 1.0 false positive per volume. It is further evaluated for pelvic and abdominal LN detection on 54 volumes containing 569 LN, yielding a 80.0% detection rate with 3.2 false positives per volume. The running time is 5-20 s per volume for axillary areas and 15-40 s for pelvic. An added benefit of the method is the capability to detect and segment conglomerated lymph nodes.
Retroperitoneal masses not arising from major solid organs are uncommon. Although there is no simple method of classifying retroperitoneal masses, a reasonable approach is to consider the masses as predominantly solid or cystic and to subdivide these into neoplastic and nonneoplastic masses. Because the treatment options vary, it is useful to be able to differentiate these masses by using imaging criteria. Although the differential diagnosis of retroperitoneal masses can be narrowed down to a certain extent on the basis of imaging characteristics, patterns of involvement, and demographics, there is still a considerable overlap of imaging findings for these masses, and histologic examination is often required for definitive diagnosis. Computed tomography (CT) and magnetic resonance (MR) imaging play an important role in characterization and in the assessment of the extent of the disease and involvement of adjacent and distant structures. Familiarity with the CT and MR imaging features of various retroperitoneal masses will facilitate accurate diagnosis and staging for aggressive lesions.
In medical imaging, segmenting accurately lung tumors stay a quite challenging task when touching directly with healthy tissues. In this paper, we address the problem of extracting interactively these tumors with graph cuts. The originality of this work consists in (1) reducing input graphs to reduce resource consumption when segmenting large volume data and (2) introducing a novel energy formulation to inhibit the propagation of the object seeds. We detail our strategy to achieve relevant segmentations of lung tumors and compare our results to hand made segmentations provided by an expert. Comprehensive experiments show how our method can get solutions near from ground truth in a fast and memory efficient way.
State-of-the-art research on MRFs, successful MRF applications, and advanced topics for future study.
This volume demonstrates the power of the Markov random field (MRF) in vision, treating the MRF both as a tool for modeling image data and, utilizing recently developed algorithms, as a means of making inferences about images. These inferences concern underlying image and scene structure as well as solutions to such problems as image reconstruction, image segmentation, 3D vision, and object labeling. It offers key findings and state-of-the-art research on both algorithms and applications.
After an introduction to the fundamental concepts used in MRFs, the book reviews some of the main algorithms for performing inference with MRFs; presents successful applications of MRFs, including segmentation, super-resolution, and image restoration, along with a comparison of various optimization methods; discusses advanced algorithmic topics; addresses limitations of the strong locality assumptions in the MRFs discussed in earlier chapters; and showcases applications that use MRFs in more complex ways, as components in bigger systems or with multiterm energy functions. The book will be an essential guide to current research on these powerful mathematical tools.
In this paper a new algorithm for the segmentation of retroperitoneal tumors is presented. In this paper an accumulated gradient distance is proposed as a new regional term in the continuous max-flow algorithm. In this preliminary study, three CT images have been segmented and compared with manual segmentations. DICE, Jaccard, Sensitivity and Postive Predictive Value (PPV) indexes have been computed and their values show promising results.
This study investigates a convex relaxation approach to figure-ground separation with a global distribution matching prior evaluated by the Bhattacharyya measure. The problem amounts to finding a region that most closely matches a known model distribution. It has been previously addressed by curve evolution, which leads to suboptimal and computationally intensive algorithms, or by graph cuts, which result in metrication errors. Solving a sequence of convex subproblems, the proposed relaxation is based on a novel bound of the Bhattacharyya measure which yields an algorithm robust to initial conditions. Furthermore, we propose a novel flow configuration that accounts for labeling-function variations, unlike existing configurations. This leads to a new max-flow formulation which is dual to the convex relaxed subproblems we obtained. We further prove that such a formulation yields exact and global solutions to the original, nonconvex subproblems. A comprehensive experimental evaluation on the Microsoft GrabCut database demonstrates that our approach yields improvements in optimality and accuracy over related recent methods.
Early detection of cancer is the most promising way to enhance a patient's chance for survival. This paper presents a computer aided classification method in computed tomography (CT) images of lungs developed using artificial neural network. The entire lung is segmented from the CT images and the parameters are calculated from the segmented image. The statistical parameters like mean, standard deviation, skewness, kurtosis, fifth central moment and sixth central moment are used for classification. The classification process is done by feed forward and feed forward back propagation neural networks. Compared to feed forward networks the feed forward back propagation network gives better classification. The parameter skewness gives the maximum classification accuracy. Among the already available thirteen training functions of back propagation neural network, the Traingdx function gives the maximum classification accuracy of 91.1%. Two new training functions are proposed in this paper. The results show that the proposed training function 1 gives an accuracy of 93.3%, specificity of 100% and sensitivity of 91.4% and a mean square error of 0.998. The proposed training function 2 gives a classification accuracy of 93.3% and minimum mean square error of 0.0942.
Computer-aided detection (CAD) can help radiologists to detect pulmonary nodules at an early stage. In pulmonary nodule CAD systems, feature extraction is very important for describing the characteristics of nodule candidates. In this paper, we propose a novel three-dimensional shape-based feature descriptor to detect pulmonary nodules in CT scans. After lung volume segmentation, nodule candidates are detected using multi-scale dot enhancement filtering in the segmented lung volume. Next, we extract feature descriptors from the detected nodule candidates, and these are refined using an iterative wall elimination method. Finally, a support vector machine-based classifier is trained to classify nodules and non-nodules. The performance of the proposed system is evaluated on Lung Image Database Consortium data. The proposed method significantly reduces the number of false positives in nodule candidates. This method achieves 97.5% sensitivity, with only 6.76 false positives per scan.
Minimal paths are proposed as a powerful way to extract faint linear structures in noisy gray-level images. A global algorithm based on gray-weighted distance transforms is proposed and shown to sometimes be a compelling alternative t o w atersheds. A more general local minimal path method is also introduced, together with an algorithm for extracting minimal path cost at each pixel location. The proposed algorithms are very eecient, and examples of applications are used to demonstrate their robustness.
In this paper, we proposes a local C-V level set algorithm integrated with local OTSU method for the segmentation of liver lesion. We first construct a local liver lesion image, then pre-segment the lesion with OTSU method to get the initial contour, finally evolve the active contour with local C-V level set method to get the final contour of lesion. Experiments showed this method can extract liver tumor efficiently.
The measurement of the size of lesions in follow-up CT examinations of cancer patients is important to evaluate the success of treatment. This paper presents an automatic algorithm for identifying and segmenting lymph nodes in CT images across longitudinal time points. Firstly, a two-step image registration method is proposed to locate the lymph nodes including coarse registration based on body region detection and fine registration based on a double-template matching algorithm. Then, to make the initial segmentation approximate the boundaries of lymph nodes, the initial image registration result is refined with intensity and edge information. Finally, a snake model is used to evolve the refined initial curve and obtain segmentation results. Our algorithm was tested on 26 lymph nodes at multiple time points from 14 patients. The image at the earlier time point was used as the baseline image to be used in evaluating the follow-up image, resulting in 76 total test cases. Of the 76 test cases, we made a 76 (100%) successful detection and 38/40 (95%) correct clinical assessment according to Response Evaluation Criteria in Solid Tumors (RECIST). The quantitative evaluation based on several metrics, such as average Hausdorff distance, indicates that our algorithm is produces good results. In addition, the proposed algorithm is fast with an average computing time 2.58s. The proposed segmentation algorithm for lymph nodes is fast and can achieve high segmentation accuracy, which may be useful to automate the tracking and evaluation of cancer therapy.
Background and purpose:
To investigate the hypothesis that primary tumor volume is prognostic independent of T and N stages in patients with non-small cell lung cancer (NSCLC) treated by definitive radiotherapy.
Materials and methods:
Multicenter prospective observational study. Patient eligibility: pathologically proven stage I-III non-small cell lung cancer planned for definitive radiotherapy (minimum 50 Gy in 20 fractions) using CT-based contouring. Volumes of the primary tumor and enlarged nodes were measured according to a standardized protocol. Survival was adjusted for the effect of T and N stage.
Results:
There were 509 eligible patients. Five-year survival rates for tumor volume grouped by quartiles were, for increasing tumor volume, 22%, 14%, 15% and 21%. Larger primary tumor volume was associated with shorter survival (HR=1.060 (per doubling); 95% CI 1.01-1.12; P=0.029). However, after adjusting for the effects of T and N stage, there was no evidence for an association (HR=1.029, 95% CI, 0.96-1.10, P=0.39). There was evidence, however, that larger primary tumor volume was associated with an increased risk of dying, independently of T and N stage, in the first 18 months but not beyond.
Conclusions:
In patients treated by non-surgical means we were unable to show that lung tumor volume, overall, provides additional prognostic information beyond the T and N stage (TNM, 6th edition). There is evidence, however, that larger primary tumor volume adversely affects outcome only within the first 18 months. Larger tumor size alone should not by itself exclude patients from curative (chemo)radiotherapy.
Lymph nodes have high clinical relevance and routinely need to be considered in clinical practice. Automatic detection is, however, challenging due to clutter and low contrast. In this paper, a method is presented that fully automatically detects and segments lymph nodes in 3-D computed tomography images of the chest. Lymph nodes can easily be confused with other structures, it is therefore vital to incorporate as much anatomical prior knowledge as possible in order to achieve a good detection performance. Here, a learned prior of the spatial distribution is used to model this knowledge. Different prior types with increasing complexity are proposed and compared to each other. This is combined with a powerful discriminative model that detects lymph nodes from their appearance. It first generates a number of candidates of possible lymph node center positions. Then, a segmentation method is initialized with a detected candidate. The graph cuts method is adapted to the problem of lymph nodes segmentation. We propose a setting that requires only a single positive seed and at the same time solves the small cut problem of graph cuts. Furthermore, we propose a feature set that is extracted from the segmentation. A classifier is trained on this feature set and used to reject false alarms. Cross-validation on 54 CT datasets showed that for a fixed number of four false alarms per volume image, the detection rate is well more than doubled when using the spatial prior. In total, our proposed method detects mediastinal lymph nodes with a true positive rate of 52.0% at the cost of only 3.1 false alarms per volume image and a true positive rate of 60.9% with 6.1 false alarms per volume image, which compares favorably to prior work on mediastinal lymph node detection.
The aim of segmentation of tumor regions in positron emission tomography (PET) is to provide more accurate measurements of tumor size and extension into adjacent structures, than is possible with visual assessment alone and hence improve patient management decisions. We propose a segmentation energy function for the graph cuts technique to improve lung tumor segmentation with PET. Our segmentation energy is based on an analysis of the tumor voxels in PET images combined with a standardized uptake value (SUV) cost function and a monotonic downhill SUV feature. The monotonic downhill feature avoids segmentation leakage into surrounding tissues with similar or higher PET tracer uptake than the tumor and the SUV cost function improves the boundary definition and also addresses situations where the lung tumor is heterogeneous. We evaluated the method in 42 clinical PET volumes from patients with non-small cell lung cancer (NSCLC). Our method improves segmentation and performs better than region growing approaches, the watershed technique, fuzzy-c-means, region-based active contour and tumor customized downhill.
In place of flows on a discrete network we study flows described by a vector field σ(x,y) in a plane domain ω. The analogue of the capacity constraint is |σ|≤c(x,y), and the strength of sources and sinks is σ·n=λf on the boundary and—div σ=λF in the interior. We show that the largest λ (the maximal flow) is determined by the minimal cut. As in the discrete case
the dual problem has a 0–1 solution, given by the characteristic function of the minimal cut; for the continuous problem the
argument depends on the coarea formula for functions of bounded variation.
The retroperitoneum is the compartmentalized space bounded anteriorly by the posterior parietal peritoneum and posteriorly by the transversalis fascia. It extends from the diaphragm superiorly to the pelvic brim inferiorly. This article discusses clinically relevant anatomy of the abdominal retroperitoneal spaces, their cross-sectional imaging evaluation with computed tomography and magnetic resonance imaging, and the imaging features of common retroperitoneal pathologic processes.
We devise new numerical algorithms, called PSC algorithms, for following fronts propagating with curvature-dependent speed. The speed may be an arbitrary function of curvature, and the front also can be passively advected by an underlying flow. These algorithms approximate the equations of motion, which resemble Hamilton-Jacobi equations with parabolic right-hand sides, by using techniques from hyperbolic conservation laws. Non-oscillatory schemes of various orders of accuracy are used to solve the equations, providing methods that accurately capture the formation of sharp gradients and cusps in the moving fronts. The algorithms handle topological merging and breaking naturally, work in any number of space dimensions, and do not require that the moving surface be written as a function. The methods can be also used for more general Hamilton-Jacobi-type problems. We demonstrate our algorithms by computing the solution to a variety of surface motion problems.
This paper describes algorithms for computing various functions on a digital picture which depend on the distance to a given subset of the picture. The algorithms involve local operations which are performed repeatedly, “in parallel”, on every picture element and its immediate neighbors. Applications to the detection of “clusters” and “regularities” in a picture, and to the dissection of a region into “pieces”, are also described.
We propose and study novel max-flow models in the continuous setting, which directly map the discrete graph-based max-flow problem to its continuous optimization formulation. We show such a continuous max-flow model leads to an equivalent min-cut problem in a natural way, as the corresponding dual model. In this regard, we revisit basic conceptions used in discrete max-flow / min-cut models and give their new explanations from a variational perspective. We also propose corresponding continuous max-flow and min-cut models constrained by priori supervised information and apply them to interactive image segmentation/labeling problems. We prove that the proposed continuous max-flow and min-cut models, with or without supervised constraints, give rise to a series of global binary solutions λ*(x) ϵ {0,1}, which globally solves the original nonconvex image partitioning problems. In addition, we propose novel and reliable multiplier-based max-flow algorithms. Their convergence is guaranteed by classical optimization theories. Experiments on image segmentation, unsupervised and supervised, validate the effectiveness of the discussed continuous max-flow and min-cut models and suggested max-flow based algorithms.
We address the continuous problem of assigning multiple (unordered) labels with the minimum perimeter. The corresponding discrete Potts model is typically addressed with a-expansion which can generate metrication artifacts. Existing convex continuous formulations of the Potts model use TV-based functionals directly encoding perimeter costs. Such formulations are analogous to 'min-cut' problems on graphs. We propose a novel convex formulation with a continous 'max-flow' functional. This approach is dual to the standard TV-based formulations of the Potts model. Our continous max-flow approach has significant numerical advantages; it avoids extra computational load in enforcing the simplex constraints and naturally allows parallel computations over different labels. Numerical experiments show competitive performance in terms of quality and significantly reduced number of iterations compared to the previous state of the art convex methods for the continuous Potts model.
In this paper, we propose a new model for active contours to detect objects in a given image, based on techniques of curve evolution, Mumford--Shah functional for segmentation and level sets. Our model can detect objects whose boundaries are not necessarily defined by gradient. We minimize an energy which can be seen as a particular case of the minimal partition problem. In the level set formulation, the problem becomes a "mean-curvature flow"-like evolving the active contour, which will stop on the desired boundary. However, the stopping term does not depend on the gradient of the image, as in the classical active contour models, but is instead related to a particular segmentation of the image. We will give a numerical algorithm using finite differences. Finally, we will present various experimental results and in particular some examples for which the classical snakes methods based on the gradient are not applicable. Also, the initial curve can be anywhere in the image, and interior contours are automatically detected.
Multi-object segmentation with mutual interaction is a challenging task in medical image analysis. We report a novel solution to a segmentation problem, in which target objects of arbitrary shape mutually interact with terrain-like surfaces, which widely exists in the medical imaging field. The approach incorporates context information used during simultaneous segmentation of multiple objects. The object-surface interaction information is encoded by adding weighted inter-graph arcs to our graph model. A globally optimal solution is achieved by solving a single maximum flow problem in a low-order polynomial time. The performance of the method was evaluated in robust delineation of lung tumors in megavoltage cone-beam CT images in comparison with an expert-defined independent standard. The evaluation showed that our method generated highly accurate tumor segmentations. Compared with the conventional graph-cut method, our new approach provided significantly better results (p < 0.001). The Dice coefficient obtained by the conventional graph-cut approach (0.76 +/- 0.10) was improved to 0.84 +/- 0.05 when employing our new method for pulmonary tumor segmentation.
In this article, we present a novel approach to localize anatomical features-breast costal cartilage-in dynamic contrast-enhanced MRI using level sets. Current breast MRI diagnosis involves magnetic-resonance compatible needles for localization. However, if the breast costal cartilage structure can be used as an alternative to the MR needle, this will not only assist in avoiding invasive procedures, but will also facilitate monitoring of the movement of breasts caused by cardiac and respiratory motion. This article represents a novel algorithm for achieving reliable detection and extraction of costal cartilage structures, which can be used for the analysis of motion artifacts, with possible shape variations of the structure caused by uptake of contrast agent, as well as a potential for the registration of breast. The algorithm represented in this article is to extract volume features from post-contrast MR images at three different time slices for the analysis of motion artifacts, and we validate the current algorithm according to the anatomic structure. This utilizes the level-set method for the size selection of the region of interest. The variable shape of contours acquired from a level-set-based segment image actually determines the feature region of interest, which is used as a guide to achieve initial masks for feature extraction. Following this, the algorithm uses a K-means method for classification of the feature regions from other types of tissue and morphological operations with a choice of an appropriate structuring element to achieve reliable masks and extraction of features. The segments of features can be therefore obtained with the application of extracted masks for subsequent motion analysis of breast and for potential registration purposes.
Inter-observer variability in anatomical contouring is the biggest contributor to uncertainty in radiation treatment planning. Contouring studies are frequently performed to investigate the differences between multiple contours on common datasets. There is, however, no widely accepted method for contour comparisons. The purpose of this study is to review the literature on contouring studies in the context of radiation oncology, with particular consideration of the contouring comparison methods they employ. A literature search, not limited by date, was conducted using Medline and Google Scholar with key words: contour, variation, delineation, inter/intra observer, uncertainty and trial dummy-run. This review includes a description of the contouring processes and contour comparison metrics used. The use of different processes and metrics according to tumour site and other factors were also investigated with limitations described. A total of 69 relevant studies were identified. The most common tumour sites were prostate (26), lung (10), head and neck cancers (8) and breast (7).The most common metric of comparison was volume used 59 times, followed by dimension and shape used 36 times, and centre of volume used 19 times. Of all 69 publications, 67 used a combination of metrics and two used only one metric for comparison. No clear relationships between tumour site or any other factors that may influence the contouring process and the metrics used to compare contours were observed from the literature. Further studies are needed to assess the advantages and disadvantages of each metric in various situations.