Rotationally resliced 3D prostate segmentation of MR images using Bhattacharyya similarity and active band theory

PurposeIn this article, we propose a novel, semi-automatic segmentation method to process 3D MR images of the prostate using the Bhattacharyya coefficient and active band theory with the goal of providing technical support for computer-aided diagnosis and surgery of the prostate.MethodsOur method consecutively segments a stack of rotationally resectioned 2D slices of a prostate MR image by assessing the similarity of the shape and intensity distribution in neighboring slices. 2D segmentation is first performed on an initial slice by manually selecting several points on the prostate boundary, after which the segmentation results are propagated consecutively to neighboring slices. A framework of iterative graph cuts is used to optimize the energy function, which contains a global term for the Bhattacharyya coefficient with the help of an auxiliary function. Our method does not require previously segmented data for training or for building statistical models, and manual intervention can be applied flexibly and intuitively, indicating the potential utility of this method in the clinic.ResultsWe tested our method on 3D T2-weighted MR images from the ISBI dataset and PROMISE12 dataset of 129 patients, and the Dice similarity coefficients were 90.34 ± 2.21% and 89.32 ± 3.08%, respectively. The comparison was performed with several state-of-the-art methods, and the results demonstrate that the proposed method is robust and accurate, achieving similar or higher accuracy than other methods without requiring training.ConclusionThe proposed algorithm for segmenting 3D MR images of the prostate is accurate, robust, and readily applicable to a clinical environment for computer-aided surgery or diagnosis.     

Automatic liver segmentation in MRI images using an iterative watershed algorithm and artificial neural network

Precise liver segmentation in abdominal MRI images is one of the most important steps for the computer-aided diagnosis of liver pathology. The first and essential step for diagnosis is automatic liver segmentation, and this process remains challenging. Extensive research has examined liver segmentation; however, it is challenging to distinguish which algorithm produces more precise segmentation results that are applicable to various medical imaging techniques. In this paper, we present a new automatic system for liver segmentation in abdominal MRI images. The system includes several successive steps. Preprocessing is applied to enhance the image (edge-preserved noise reduction) by using mathematical morphology. The proposed algorithm for liver region extraction is a combined algorithm that utilizes MLP neural networks and watershed algorithm. The traditional watershed transformation generally results in oversegmentation when directly applied to medical image segmentation. Therefore, we use trained neural networks to extract features of the liver region. The extracted features are used to monitor the quality of the segmentation using the watershed transform and adjust the required parameters automatically. The process of adjusting parameters is performed sequentially in several iterations. The proposed algorithm extracts liver region in one slice of the MRI images and the boundary tracking algorithm is suggested to extract the liver region in other slices, which is left as our future work. This system was applied to a series of test images to extract the liver region. Experimental results showed positive results for the proposed algorithm.     

Efficient liver segmentation in CT images based on graph cuts and bottleneck detection

Liver segmentation from abdominal computed tomography (CT) volumes is extremely important for computer-aided liver disease diagnosis and surgical planning of liver transplantation. Due to ambiguous edges, tissue adhesion, and variation in liver intensity and shape across patients, accurate liver segmentation is a challenging task. In this paper, we present an efficient semi-automatic method using intensity, local context, and spatial correlation of adjacent slices for the segmentation of healthy liver regions in CT volumes. An intensity model is combined with a principal component analysis (PCA) based appearance model to exclude complex background and highlight liver region. They are then integrated with location information from neighboring slices into graph cuts to segment the liver in each slice automatically. Finally, a boundary refinement method based on bottleneck detection is used to increase the segmentation accuracy. Our method does not require heavy training process or statistical model construction, and is capable of dealing with complicated shape and intensity variations. We apply the proposed method on XHCSU14 and SLIVER07 databases, and evaluate it by MICCAI criteria and Dice similarity coefficient. Experimental results show our method outperforms several existing methods on liver segmentation.     

Automatic Segmentation of the Left Ventricle in Cardiac MRI Using Local Binary Fitting Model and Dynamic Programming Techniques

Segmentation of the left ventricle is very important to quantitatively analyze global and regional cardiac function from magnetic resonance. The aim of this study is to develop a novel algorithm for segmenting left ventricle on short-axis cardiac magnetic resonance images (MRI) to improve the performance of computer-aided diagnosis (CAD) systems. In this research, an automatic segmentation method for left ventricle is proposed on the basis of local binary fitting (LBF) model and dynamic programming techniques. The validation experiments are performed on a pool of data sets of 45 cases. For both endo- and epi-cardial contours of our results, percentage of good contours is about 93.5%, the average perpendicular distance are about 2 mm. The overlapping dice metric is about 0.91. The regression and determination coefficient between the experts and our proposed method on the LV mass is 1.038 and 0.9033, respectively; they are 1.076 and 0.9386 for ejection fraction (EF). The proposed segmentation method shows the better performance and has great potential in improving the accuracy of computer-aided diagnosis systems in cardiovascular diseases.     

Segmentation of left ventricle in short-axis echocardiographic sequences by weighted radial edge filtering and adaptive recovery of dropout regions

In this paper, we present a weighted radial edge filtering algorithm with adaptive recovery of dropout regions for the semi-automatic delineation of endocardial contours in short-axis echocardiographic image sequences. The proposed algorithm requires minimal user intervention at the end diastolic frame of the image sequence for specifying the candidate points of the contour. The region of interest is identified by fitting an ellipse in the region defined by the specified points. Subsequently, the ellipse centre is used for originating the radial lines for filtering. A weighted radial edge filter is employed for the detection of edge points. The outliers are corrected by global as well as local statistics. Dropout regions are recovered by incorporating the important temporal information from the previous frame by means of recursive least squares adaptive filter. This ensures fairly accurate segmentation of the cardiac structures for further determination of the functional cardiac parameters. The proposed algorithm was applied to 10 data-sets over a full cardiac cycle and the results were validated by comparing computer-generated boundaries to those manually outlined by two experts using Hausdorff distance (HD) measure, radial mean square error (rmse) and contour similarity index. The rmse was 1.83 mm with a HD of 5.12 ± 1.21 mm. We have also compared our results with two existing approaches, level set and optical flow. The results indicate an improvement when compared with ground truth due to incorporation of temporal clues. The weighted radial edge filtering algorithm in conjunction with adaptive dropout recovery offers semi-automatic segmentation of heart chambers in 2D echocardiography sequences for accurate assessment of global left ventricular function to guide therapy and staging of the cardiovascular diseases.     

Improved Estimation of Cardiac Function Parameters Using a Combination of Independent Automated Segmentation Results in Cardiovascular Magnetic Resonance Imaging

This work aimed at combining different segmentation approaches to produce a robust and accurate segmentation result. Three to five segmentation results of the left ventricle were combined using the STAPLE algorithm and the reliability of the resulting segmentation was evaluated in comparison with the result of each individual segmentation method. This comparison was performed using a supervised approach based on a reference method. Then, we used an unsupervised statistical evaluation, the extended Regression Without Truth (eRWT) that ranks different methods according to their accuracy in estimating a specific biomarker in a population. The segmentation accuracy was evaluated by estimating six cardiac function parameters resulting from the left ventricle contour delineation using a public cardiac cine MRI database. Eight different segmentation methods, including three expert delineations and five automated methods, were considered, and sixteen combinations of the automated methods using STAPLE were investigated. The supervised and unsupervised evaluations demonstrated that in most cases, STAPLE results provided better estimates than individual automated segmentation methods. Overall, combining different automated segmentation methods improved the reliability of the segmentation result compared to that obtained using an individual method and could achieve the accuracy of an expert.     

A watershed approach for improving medical image segmentation

In this paper, a novel watershed approach based on seed region growing and image entropy is presented which could improve the medical image segmentation. The proposed algorithm enables the prior information of seed region growing and image entropy in its calculation. The algorithm starts by partitioning the image into several levels of intensity using watershed multi-degree immersion process. The levels of intensity are the input to a computationally efficient seed region segmentation process which produces the initial partitioning of the image regions. These regions are fed to entropy procedure to carry out a suitable merging which produces the final segmentation. The latter process uses a region-based similarity representation of the image regions to decide whether regions can be merged. The region is isolated from the level and the residual pixels are uploaded to the next level and so on, we recall this process as multi-level process and the watershed is called multi-level watershed. The proposed algorithm is applied to challenging applications: grey matter–white matter segmentation in magnetic resonance images (MRIs). The established methods and the proposed approach are experimented by these applications to a variety of simulating immersion, multi-degree, multi-level seed region growing and multi-level seed region growing with entropy. It is shown that the proposed method achieves more accurate results for medical image oversegmentation.     

Automatic Localization of the Left Ventricle from Cardiac Cine Magnetic Resonance Imaging: A New Spectrum-Based Computer-Aided Tool

Traditionally, cardiac image analysis is done manually. Automatic image processing can help with the repetitive tasks, and also deal with huge amounts of data, a task which would be humanly tedious. This study aims to develop a spectrum-based computer-aided tool to locate the left ventricle using images obtained via cardiac magnetic resonance imaging. Discrete Fourier Transform was conducted pixelwise on the image sequence. Harmonic images of all frequencies were analyzed visually and quantitatively to determine different patterns of the left and right ventricles on spectrum. The first and fifth harmonic images were selected to perform an anisotropic weighted circle Hough detection. This tool was then tested in ten volunteers. Our tool was able to locate the left ventricle in all cases and had a significantly higher cropping ratio of 0.165 than did earlier studies. In conclusion, a new spectrum-based computer aided tool has been proposed and developed for automatic left ventricle localization. The development of this technique, which will enable the automatic location and further segmentation of the left ventricle, will have a significant impact in research and in diagnostic settings. We envisage that this automated method could be used by radiographers and cardiologists to diagnose and assess ventricular function in patients with diverse heart diseases.     

Développement et évaluation d’un algorithme de segmentation automatisée des ventricules gauche et droit sur des images ciné d’IRM

An automated segmentation of the left and right ventricles on cine MRI is presented here. A rectangular region around the object of interest is defined in the original image, a morphological filter is then applied that combines openings and closings on connected sets, providing an image with homogeneous regions, which is finally segmented with an active contour model. The algorithm was tested on two databases with an expert's segmentation on the ventricles. One of the databases was provided by the Multicentric Initiative for a Platform of Evaluation in Cardiac Imaging (IMPEIC) group. Results show a very satisfactory correlation between the area (given in mm²) of expertise (x) and the area of automated segmentation (y) of the left ventricle (y = 1.00x + 8.6, r = 0.99). First results on the right ventricle show more than 83% similarity. The systolic phase proved to be more difficult to segment, which could be taken into consideration by introducing time regularization criteria in the algorithm.     

Segmentation of left ventricle in short-axis echocardiographic sequences by weighted radial edge filtering and adaptive recovery of dropout regions

In this paper, we present a weighted radial edge filtering algorithm with adaptive recovery of dropout regions for the semi-automatic delineation of endocardial contours in short-axis echocardiographic image sequences. The proposed algorithm requires minimal user intervention at the end diastolic frame of the image sequence for specifying the candidate points of the contour. The region of interest is identified by fitting an ellipse in the region defined by the specified points. Subsequently, the ellipse centre is used for originating the radial lines for filtering. A weighted radial edge filter is employed for the detection of edge points. The outliers are corrected by global as well as local statistics. Dropout regions are recovered by incorporating the important temporal information from the previous frame by means of recursive least squares adaptive filter. This ensures fairly accurate segmentation of the cardiac structures for further determination of the functional cardiac parameters. The proposed algorithm was applied to 10 data-sets over a full cardiac cycle and the results were validated by comparing computer-generated boundaries to those manually outlined by two experts using Hausdorff distance (HD) measure, radial mean square error (rmse) and contour similarity index. The rmse was 1.83 mm with a HD of 5.12 ± 1.21 mm. We have also compared our results with two existing approaches, level set and optical flow. The results indicate an improvement when compared with ground truth due to incorporation of temporal clues. The weighted radial edge filtering algorithm in conjunction with adaptive dropout recovery offers semi-automatic segmentation of heart chambers in 2D echocardiography sequences for accurate assessment of global left ventricular function to guide therapy and staging of the cardiovascular diseases.     

The heart-forming fields: one or multiple?

The recent identification of a second mesodermal region as a source of cardiomyocytes has challenged the views on the formation of the heart. This second source of cardiomyocytes is localized centrally on the embryonic disc relative to the remainder of the classic cardiac crescent, a region also called the pharyngeal mesoderm. In this review, we discuss the concept of the primary and secondary cardiogenic fields in the context of folding of the embryo, and the subsequent temporal events involved in formation of the heart. We suggest that, during evolution, the heart developed initially only with the components required for a systemic circulation, namely a sinus venosus, a common atrium, a 'left' ventricle and an arterial cone, the latter being the myocardial outflow tract as seen in the heart of primitive fishes. These components developed in their entirety from the classic cardiac crescent. Only later in the course of evolution did the appearance of novel signalling pathways permit the central part of the cardiac crescent, and possibly the contiguous pharyngeal mesoderm, to develop into the cardiac components required for the pulmonary circulation. These latter components comprise the right ventricle, and that part of the left atrium that derives from the mediastinal myocardium, namely the dorsal atrial wall and the atrial septum. It is these elements which are now recognized as developing from the second field of pharyngeal mesoderm. We suggest that, rather than representing development from separate fields, the cardiac components required for both the systemic and pulmonary circulations are derived by patterning from a single cardiac field, albeit with temporal delay in the process of formation.     

A pipeline to quantify spinal cord atrophy with deep learning: Application to differentiation of MS and NMOSD patients

PurposeQuantitative measurement of various anatomical regions of the brain and spinal cord (SC) in MRI images are used as unique biomarkers to consider progress and effects of demyelinating diseases of the central nervous system. This paper presents a fully-automated image processing pipeline which quantifies the SC volume of MRI images.MethodsIn the proposed pipeline, after conducting some pre-processing tasks, a deep convolutional network is utilized to segment the spinal cord cross-sectional area (SCCSA) of each slice. After full segmentation, certain extra slices interpolate between each two adjacent slices using the shape-based interpolation method. Then, a 3D model of the SC is reconstructed, and, by counting the voxels of it, the SC volume is calculated. The performance of the proposed method for the SCCSA segmentation is evaluated on 140 MRI images. Subsequently, to demonstrate the application of the proposed pipeline, we study the differentiations of SC atrophy between 38 Multiple Sclerosis (MS) and 25 Neuromyelitis Optica Spectrum Disorder (NMOSD) patients.ResultsThe experimental results of the SCCSA segmentation indicate that the proposed method, adapted by Mask R-CNN, presented the most satisfactory result with the average Dice coefficient of 0.96. For this method, statistical metrics including sensitivity, specificity, accuracy, and precision are 97.51%, 99.98%, 99.92%, and 98.04% respectively. Moreover, the t-test result (p-value = 0.00089) verified a significant difference between the SC atrophy of MS and NMOSD patients.ConclusionThe pipeline efficiently quantifies the SC volume of MRI images and can be utilized as an affordable computer-aided tool for diagnostic purposes.     

Loss of cardiac muscle taurine after acute left ventricular ischemia

Ischemia was produced by occluding the circumflex branch of the left coronary artery in dogs. The artery remained patent in control animals. Tissue samples were obtained after 4 hours with or without occlusion. Right and left atria contained the highest taurine levels. In controls, an increasing outer to inner gradient in taurine content was observed in the posterolateral wall ventricle. No gradient was found in the right ventricular wall. For the first time, ischemia has been shown to reduce cardiac muscle taurine 47 percent in the left ventricle and 26 percent in right and left atria. Thus heart taurine 1) shows a non-uniform regional distribution in control and ischemic animals, and 2) is decreased after ischemic injury.     

A robust heart sounds segmentation module based on S-transform

This paper presents a new module for heart sounds segmentation based on S-transform. The heart sounds segmentation process segments the PhonoCardioGram (PCG) signal into four parts: S1 (first heart sound), systole, S2 (second heart sound) and diastole. It can be considered one of the most important phases in the auto-analysis of PCG signals. The proposed segmentation module can be divided into three main blocks: localization of heart sounds, boundaries detection of the localized heart sounds and classification block to distinguish between S1 and S2. An original localization method of heart sounds are proposed in this study. The method named SSE calculates the Shannon energy of the local spectrum calculated by the S-transform for each sample of the heart sound signal. The second block contains a novel approach for the boundaries detection of S1 and S2. The energy concentrations of the S-transform of localized sounds are optimized by using a window width optimization algorithm. Then the SSE envelope is recalculated and a local adaptive threshold is applied to refine the estimated boundaries. To distinguish between S1 and S2, a feature extraction method based on the singular value decomposition (SVD) of the S-matrix is applied in this study. The proposed segmentation module is evaluated at each block according to a database of 80 sounds, including 40 sounds with cardiac pathologies.     

Quantification of the non-planarity of the human carotid bifurcation

The carotid bifurcation has been a region of particular interest due to its predilection for clinically significant atherosclerosis. It has been shown that the vessel geometry is a major determinant of the local haemodynamic properties which are believed to be associated with the location of atherosclerotic lesions. Current knowledge of the geometry of the carotid bifurcation is insufficient and restricted to basic geometric parameters. To provide some means of quantifying the degree of complexity of the 3D shape of the bifurcation, we made an initial attempt by evaluating the non-planarity of an arterial bifurcation based upon the singular value decomposition theorem.In this paper we present our results obtained on the right carotid bifurcations of six normal subjects, each of whom was scanned twice using the 2D time-of-flight MR sequence. The acquired 2D cross sectional images were processed by using our in-house software which comprises 2D segmentation, 3D reconstruction and smoothing. The centroids of each transverse slices were determined and used as input data for the non-planarity analysis. Our results using the singular value decomposition method have demonstrated discernible differences in non-planarity among individuals. Comparisons with the planarity definition proposed by other investigators suggest that the singular value decomposition method offers more information about the linearity and planarity of the bifurcation. However, it is also realised that a single measure of non-planarity can never fully characterise a bifurcation owing to the great variety of geometries.     

An improved approach for the segmentation of starch granules in microscopic images

Background

Starches are the main storage polysaccharides in plants and are distributed widely throughout plants including seeds, roots, tubers, leaves, stems and so on. Currently, microscopic observation is one of the most important ways to investigate and analyze the structure of starches. The position, shape, and size of the starch granules are the main measurements for quantitative analysis. In order to obtain these measurements, segmentation of starch granules from the background is very important. However, automatic segmentation of starch granules is still a challenging task because of the limitation of imaging condition and the complex scenarios of overlapping granules.

Results

We propose a novel method to segment starch granules in microscopic images. In the proposed method, we first separate starch granules from background using automatic thresholding and then roughly segment the image using watershed algorithm. In order to reduce the oversegmentation in watershed algorithm, we use the roundness of each segment, and analyze the gradient vector field to find the critical points so as to identify oversegments. After oversegments are found, we extract the features, such as the position and intensity of the oversegments, and use fuzzy c-means clustering to merge the oversegments to the objects with similar features. Experimental results demonstrate that the proposed method can alleviate oversegmentation of watershed segmentation algorithm successfully.

Conclusions

We present a new scheme for starch granules segmentation. The proposed scheme aims to alleviate the oversegmentation in watershed algorithm. We use the shape information and critical points of gradient vector flow (GVF) of starch granules to identify oversegments, and use fuzzy c-mean clustering based on prior knowledge to merge these oversegments to the objects. Experimental results on twenty microscopic starch images demonstrate the effectiveness of the proposed scheme.

     

Breast mass segmentation using region-based and edge-based methods in a 4-stage multiscale system

Mass segmentation in mammograms is a challenging task due to problems such as low contrast, ill-defined, fuzzy or spiculated borders, and the presence of intensity inhomogeneities. These facts complicate the development of computer-aided diagnosis (CAD) systems to assist radiologists. In this paper, a novel mass segmentation algorithm for mammograms based on robust multiscale feature-fusion, and automatic estimation based maximum a posteriori (MAP) method is presented. The proposed segmentation technique consists of mainly four stages: a dynamic contrast improvement scheme applied to a selected region-of-interest (ROI), background-influence correction by template matching, detection of mass candidate points by prior and posterior probabilities based on robust multiscale feature-fusion, and final delineation of the mass region by a MAP scheme. This segmentation method is applied to 480 ROI masses that used ground truth from two radiologists. To compare its effectiveness with the state-of-the-art segmentation methods, three statistical metrics are employed. The experimental results indicate that the developed methods can reliably segment ill-defined or spiculated lesions when compared to other algorithms. Its integration in a CAD system may result in an improved aid to radiologists.     

Tree balance,time slices,and evolutionary turnover in cretaceous planktonic foraminifera

Studies of phylogenetic tree shape often concentrate on the balance of phylogenies of extant taxa. Paleontological phylogenies (which include extinct taxa) can contain additional useful information and can directly document changes in tree shape through evolutionary time. Unfortunately, the inclusion of extinct taxa lowers the power of direct examinations of tree balance because it increases the range of tree shapes expected under null models of evolution (with equal rates of speciation and extinction across lineages). A promising approach for the analysis of tree shape in paleontological phylogenies is to break the phylogeny down into time slices, examining the shape of the phylogeny of taxa alive at each time slice and changes in that shape between successive time slices. This method was illustrated with 57 time slices through a stratophenetic phylogeny of the Cretaceous planktonic foraminiferal superfamily Globotruncanacea. At 3 of 56 intervals between time slices, 93-92.5 million years ago (MYA), 89-88.5 MYA, and 85.5-84 MYA, the group showed steep increases in imbalance. Although none of these increases were significant after Bonferroni correction, these points in the history of the Globotruncanacea were nevertheless identified as deserving of further macroevolutionary investigation. The 84 MYA time slice coincides with a peak in species turnover for the superfamily. Time slices through phylogenies may prove useful for identifying periods of time when evolution was proceeding in a nonstochastic manner.