Spurious Segments Research Articles

Automated Torso Contour Extraction from Clinical Cardiac MR Slices for 3D Torso Reconstruction.

Whilst the electrocardiogram (ECG) is an essential tool for diagnosing cardiac electrical abnormalities, its characteristics are dependent on anatomical variability. Specifically variation in torso geometry affects relative positions of the leads with respect to the heart. We propose a novel pipeline that uses standard cardiac magnetic resonance images to reconstruct the torso and heart, and recreate the ECG considering torso and cardiac anatomy. This requires automated extraction of the torso contours. Our method combines an initial u-net segmenter with a second network that refines contours and removes spurious segments. The networks were evaluated on a cross validation study dataset and an independent test set. The use of two-channel input, including both original image and initial segmentation, in the refinement network significantly improved performance on the independent test set, reducing the Hausdorff distance from 9.1 pixels to 4.3 pixels and increasing Dice coefficient from 0.75 to 0.93. Clinical Relevance- This method can be utilized to allow ECG simulations with personalized torso geometry which has previously been demonstrated to significantly effect QRS parameters. A clinical tool can be developed using this method that accounts for torso geometry in ECG interpretation.

Road Extraction in SAR Images Using Ordinal Regression and Road-Topology Loss

The road extraction task is mainly composed of two subtasks, namely, road detection and road centerline extraction. As the road detection task and road centerline extraction task are strongly correlated, in this paper, we introduce a multitask learning framework to detect roads and extract road centerlines simultaneously. For the road centerline extraction problem, existing works rely either on regression-based methods, or classification-based methods. The regression-based methods suffer from slow convergence and unsatisfactory local solutions. The classification-based methods ignore the fact that the closer the pixel is to the centerline, the higher our tolerance for its misclassification. To overcome these problems, we first convert the road centerline extraction problem into the problem of discrete normalized distance label prediction, which can be resolved by training an ordinal regressor. For the road extraction task, most of the previous studies apply pixel-wise loss function, for example, Cross-Entropy loss, which is not sufficient, as the road has special topology characteristics such as connectivity. Therefore, we propose a road-topology loss function to improve the connectivity and completeness of the extracted road. The road-topology loss function has two key characteristics: (i) The road-topology loss function combines road detection prediction and road centerline extraction prediction to promote the two subtasks to each other by using the correlation between the two subtasks; (ii) The road-topology loss can emphatically penalize gaps that often appear in road detection results and spurious segments that easily appear in centerline extraction results. In this paper, we select the AdamW optimizer to minimize the road-topology loss. Since there is no public dataset, we build a road extraction dataset to evaluate our method. State-of-the-art semantic segmentation networks (LinkNet34, DLinkNet34, DeeplabV3plus) are used as baseline methods to compare with two kinds of method. The first kind of method modifies the baseline method by adding the road centerline extraction task branch based on ordinal regression. The second kind of method uses the road topology loss and has the same network architecture as the first kind of method. For the road detection task, the two kinds of methods improve the baseline methods by up to 3.51% and 11.98% in IoU metric on our test dataset, respectively. For the road centerline extraction task, the two kinds of methods improve the baseline methods by up to 8.22% and 10.9% in the Quality metric on our test dataset.

Local reconstruction algorithms in the cathode strip chambers of CMS

The design of the CMS detector is optimized for muon measurements. The muon system consists of gas ionization detector technologies. Cathode Strip Chambers (CSC) with both tracking and triggering capabilities are installed in the forward region. The first stage of muon reconstruction uses information from individual muon chambers and is thus called local reconstruction, in contrast to a subsequent global reconstruction where the information from all detectors is combined. First, 2-dimensional spatial points (rechits) describing where a muon crosses the CSC layers are built from the electrical signals induced by the charged particle traversing the chamber. Next, from the reconstructed hits, straight-line track segments are built within each chamber. Local reconstruction becomes particularly challenging at high instantaneous luminosities, which are expected at the HL-LHC. The high rate of particles traversing the detectors leads to increased rate of spurious rechits and segments thus increasing the combinatorial backgrounds. In this respect, work on improving the current and developing new algorithms is essential and is in progress. This document presents the existing local reconstruction algorithms used in the CMS cathode strip chambers. Their performance as well as ongoing efforts towards HL-LHC improvements are discussed.

Coastline extraction from SAR images using spatial fuzzy clustering and the active contour method

ABSTRACTCoastline extraction from synthetic aperture radar (SAR) data is difficult because of the presence of speckle noise and strong signal returns from the wind-roughened and wave-modulated sea surface. High resolution and weather change independent of SAR data lead to better monitoring of coastal sea. Therefore, SAR coastline extraction has taken up much interest. The active contour method is an efficient algorithm for the edge detection task; however, applying this method to high-resolution images is time-consuming. The current article presents an efficient approach to extracting coastlines from high-resolution SAR images. First, fuzzy clustering with spatial constraints is applied to the input SAR image. This clustering method is robust for noise and shows good performance with noisy images. Next, binarization is carried out using Otsu’s method on the fuzzification results. Third, morphological filters are used on the binary image to eliminate spurious segments after binarization. To extract the coastline, an active contour level set method is used on the initial contours and is applied to the input SAR image to refine the segmentation. Because the proposed approach is based on an active contour model, it does not require preprocessing for SAR speckle reduction. Another advantage of the proposed method is the ability to extract the coastline at full resolution of the input SAR image without degrading the resolution. The proposed approach does not require manual initialization for the level set method and the proposed initialization speeds up the level set evolution. Experimental results on low- and high-resolution SAR images showed good performance for coastline extraction. A criterion based on neighbourhood pixels for the coastline is proposed for the quantitative expression of the accuracy of the method.

Use of Intensity and Coherence of X-Band SAR Data to Map Thermokarst Lakes on the Northern Tibetan Plateau

In order to monitor the response of thermokarst lakes on the Tibetan Plateau to rapid climatic changes and human activities, an automated shoreline extraction approach from the high-resolution TerraSAR/TanDEM-X imagery is proposed. First, a preprocessing scheme is applied to calibrate, coregister, and estimate the intensity and coherence of the imagery. Second, the statistical distribution of intensity and coherence are used to refine the data term of a region-based level set model. A distance regularized term and a variable weighting parameter are also added to improve the algorithm efficiency. Finally, a postprocessing is applied to remove false edges related to spurious segments and generate a vector map by geocoding the detected edges. Experiments on the intensity and coherence images demonstrate that: 1) the Fisher distribution can improve the usability of the level set method for extraction of shorelines using the intensity feature, because it can flexibly model the speckle fluctuations of many land classes; 2) the coherence information can significantly improve the efficiency and accuracy of segmentation by suppressing the misclassification caused by the sands around the lakes and the local winds over the lakes; 3) using a variable parameter to weight the data term and a regular term in a level set model can produce more robust and fast segmentation; and 4) using of intensity and coherence in unison can locate the exact position of most of the shorelines and reduce the relative uncertainty within 3 pixels with 90% confidence level.

Skeleton-based tracing of curved fibers from 3D X-ray microtomographic imaging

A skeleton-based fiber tracing algorithm is described and applied on a specific fibrous material, porous metal fiber sintered sheet (PMFSS), featuring high porosity and curved fibers. The skeleton segments are firstly categorized according to the connectivity of the skeleton paths. Spurious segments like fiber bonds are detected making extensive use of the distance transform (DT) values. Single fibers are then traced and reconstructed by consecutively choosing the connecting skeleton segment pairs that show the most similar orientations and radius. Moreover, to reduce the misconnection due to the tracing orders, a multilevel tracing strategy is proposed. The fibrous network is finally reconstructed by dilating single fibers according to the DT values. Based on the traced single fibers, various morphology information regarding fiber length, radius, orientation, and tortuosity are quantitatively analyzed and compared with our previous results (Wang et al., 2013). Moreover, the number of bonds per fibers are firstly accessed. The methodology described in this paper can be expanded to other fibrous materials with adapted parameters.

Vectorization of optically sectioned brain microvasculature: learning aids completion of vascular graphs by connecting gaps and deleting open-ended segments.

A graph of tissue vasculature is an essential requirement to model the exchange of gasses and nutriments between the blood and cells in the brain. Such a graph is derived from a vectorized representation of anatomical data, provides a map of all vessels as vertices and segments, and may include the location of nonvascular components, such as neuronal and glial somata. Yet vectorized data sets typically contain erroneous gaps, spurious endpoints, and spuriously merged strands. Current methods to correct such defects only address the issue of connecting gaps and further require manual tuning of parameters in a high dimensional algorithm. To address these shortcomings, we introduce a supervised machine learning method that (1) connects vessel gaps by "learned threshold relaxation"; (2) removes spurious segments by "learning to eliminate deletion candidate strands"; and (3) enforces consistency in the joint space of learned vascular graph corrections through "consistency learning." Human operators are only required to label individual objects they recognize in a training set and are not burdened with tuning parameters. The supervised learning procedure examines the geometry and topology of features in the neighborhood of each vessel segment under consideration. We demonstrate the effectiveness of these methods on four sets of microvascular data, each with >800(3) voxels, obtained with all optical histology of mouse tissue and vectorization by state-of-the-art techniques in image segmentation. Through statistically validated sampling and analysis in terms of precision recall curves, we find that learning with bagged boosted decision trees reduces equal-error error rates for threshold relaxation by 5-21% and strand elimination performance by 18-57%. We benchmark generalization performance across datasets; while improvements vary between data sets, learning always leads to a useful reduction in error rates. Overall, learning is shown to more than halve the total error rate, and therefore, human time spent manually correcting such vectorizations.

Shoreline Extraction from RADARSAT-2 Intensity Imagery Using a Narrow Band Level Set Segmentation Approach

This paper presents a semi-automated method for shoreline extraction from RADARSAT-2 intensity imagery. First, a preprocessing is applied to enhance the contrast of the SAR image. Second, thresholding combined with morphological filtering is employed to segment the SAR image into the land and the sea. Third, narrow band level set segmentation is implemented to refine the segmentation result. In the last step, morphological filters are utilized to eliminate any remaining spurious segments. Boundaries between the land and the sea are delineated into shorelines based on the segmentation result. Experiment on RADARSAT-2 intensity images demonstrates that the proposed method is promising.

Individual Tooth Image Segmentation by Watershed Algorithm

In this study, we propose a novel method to segment an individual tooth region in a true color image. The difference of the intensity in RGB is initially extracted and subsequent morphological reconstruction is applied to minimize the spurious segmentation regions. Multiple seeds in the tooth regions are chosen by searching regional minima and a Sobel-mask edge operations is performed to apply MCWA(Marker-Controlled Watershed Algorithm). As the results of applying MCWA transform for our proposed tooth segmentation algorithm, the individual tooth region can be resolved in a CCD tooth color image.

Development of morphological technique for segmentation of anatomical objects in abdominal MRI

In this paper, a morphological technique for the segmentation of abdominal organs in magnetic resonance imaging (MRI) images is proposed based on watershed segmentation. New morphological based preprocessing and post-processing techniques are developed to reduce oversegmentation by means of removing and merging spurious segments. The preprocessing aims at removing trivial regions as well as background noise by combining thresholding, morphological smoothing, Gaussian smoothing and morphological edge detection. To obtain a more concise region representation, the watershed segmented image is post-processed, where a region adjacency list is built for the region merging process that produces the final segments. To control the merging process, a similarity function is defined, whence the most similar neighbouring regions are merged. The proposed technique produces effective and significant results in successfully segmenting various anatomical objects in axial MRI images of the abdomen, as it is shown in this paper.

Segmentation of VOI From Multidimensional Dynamic PET Images by Integrating Spatial and Temporal Features

Segmentation of multidimensional dynamic positron emission tomography (PET) images into volumes of interest (VOIs) exhibiting similar temporal behavior and spatial features is a challenging task due to inherently poor signal-to-noise ratio and spatial resolution. In this study, we propose VOI segmentation of dynamic PET images by utilizing both the three-dimensional (3-D) spatial and temporal domain information in a hybrid technique that integrates two independent segmentation techniques of cluster analysis and region growing. The proposed technique starts with a cluster analysis that partitions the image based on temporal similarities. The resulting temporal partitions, together with the 3-D spatial information are utilized in the region growing segmentation. The technique was evaluated with dynamic 2-[18F] fluoro-2-deoxy-D-glucose PET simulations and clinical studies of the human brain and compared with the k-means and fuzzy c-means cluster analysis segmentation methods. The quantitative evaluation with simulated images demonstrated that the proposed technique can segment the dynamic PET images into VOIs of different kinetic structures and outperforms the cluster analysis approaches with notable improvements in the smoothness of the segmented VOIs with fewer disconnected or spurious segmentation clusters. In clinical studies, the hybrid technique was only superior to the other techniques in segmenting the white matter. In the gray matter segmentation, the other technique tended to perform slightly better than the hybrid technique, but the differences did not reach significance. The hybrid technique generally formed smoother VOIs with better separation of the background. Overall, the proposed technique demonstrated potential usefulness in the diagnosis and evaluation of dynamic PET neurological imaging studies.

ANALYSIS AND RECOGNITION OF BROKEN HANDWRITTEN DIGITS BASED ON MORPHOLOGICAL STRUCTURE AND SKELETON

This paper presents an efficient method of reconstructing and recognizing broken handwritten digits. Constrained dilation algorithms are used to bridge small gaps and smooth some spurious points. The contours of broken handwritten digits are smoothed and linearized, and a set of structural points of digits are detected along the outer contours of digits. These structural points are used to describe the morphological structure of broken digits. The broken digits are skeletonized with an improved thinning algorithm. Spurious segments introduced during the extraction of digit fields are detected and deleted based on the structure analysis of digit fields, segment recognition, segment extension, skeleton structure and geometrical features. The broken points of the digits are preselected based on the minimum distance between the "end" points of skeletons of two neighboring regions. The correction rules of the preselected broken points are also based on the structure analysis and comparison of broken digits. Experimental results showing the effectiveness of the method are given.

Strategies for consumer segmentation with applications on preference data

This paper presents various strategies for the identification of consumer segments. One issue is to employ some segmentation method on the “long-thin” versus “short-fat” orientation of the consumer preference data. One strategy is to assign consumers with no strong preference to one segment, and then apply fuzzy clustering (FC) in the segmentation on the remaining consumers. The segments are evaluated by ANOVA and from external preference mapping to sensory descriptive data. Shuffled preference data are subject to segmentation to investigate the robustness of the procedure. The results indicate that segmentation on the long-thin data gives a better relation to the sensory data, and that segmentation on the short-fat data without defining the non-reliable segment gives rise to spurious segments.

Semiautomated segmentation of blood vessels using ellipse-overlap criteria: method and comparison to manual editing.

Two-dimensional intensity-based methods for the segmentation of blood vessels from computed-tomography-angiography data often result in spurious segments that originate from other objects whose intensity distributions overlap with those of the vessels. When segmented images include spurious segments, additional methods are required to select segments that belong to the target vessels. We describe a method that allows experts to select vessel segments from sequences of segmented images with little effort. Our method uses ellipse-overlap criteria to differentiate between segments that belong to different objects and are separated in plane but are connected in the through-plane direction. To validate our method, we used it to extract vessel regions from volumes that were segmented via analysis of isolabel-contour maps, and showed that the difference between the results of our method and manually-edited results was within inter-expert variability. Although the total editing duration for our method, which included user-interaction and computer processing, exceeded that of manual editing, the extent of user interaction required for our method was about a fifth of that required for manual editing.

ROBUST OBJECT MATCHING USING A MODIFIED VERSION OF THE HAUSDORFF MEASURE

The Hausdorff distance (HD) between planar sets of points is known to be an effective measure for determining the degree of resemblance between binary images. In this paper, we analyze the conventional HD measure and propose a new Robust HD (RHD) measure. The proposed RHD measure takes into account not only the location information of the edge points, but also other factors such as the total number of the edge points whose nearest neighbors are within a specified directed distance, spurious edge segments defined by a small number of points, outliers, and occlusions. Experimental results for both synthetic and real images show that the proposed RHD measure is more efficient than the conventional HD measure.

Reconstruction of broken handwritten digits based on structural morphological features

In this paper, a new method of reconstructing broken handwritten digits is developed. The conditional dilation algorithm is used to bridge small gaps. Spurious segments introduced during extraction of digit fields are detected and deleted based on the morphological structural analyses of digit fields. A set of structural points of digits are detected along the outer contours of digits. The preselected broken points of the digits are determined based on the minimum distance between two structural points. The correction rules of the preselected broken points are based on the structural morphological analyses and the stroke extension. The reconstruction and recognition of handwritten internally broken digits are also discussed. Experimental results are given showing the effectiveness of the method.

NLEBS: automatic target detection using a unique nonlinear-enhancement-based system in IR images

A new automatic target detection method for IR images that only requires information about the size of the targets is described. The proposed nonlinear-enhancement-based system (NLEBS) algorithm is based on a nonlinear enhancement paradigm that increases the contrast of the targets with minimal change in the clutter's contrast. The NLEBS employs several stages of processing, each with a different operational purpose. First, the nonlinear enhancement operation is performed by using an iterative procedure. After binarization, segmentation merging causes each local image region to grow by filling in holes. Then segmentation pruning is applied to remove spurious segments. Finally, a heuristic-based metric is employed to validate the possible targets. The performance of the NLEBS was tested with a large set of IR images. The results of these experiments showed a probability of detection greater than 90% and a false-alarm rate of about 1 false alarm per image.

Improved fractal geometry based texture segmentation technique

The problem of natural texture segmentation is considered. The technique is based on four texture features derived using the fractal geometry of images. These four features are fractal dimension (FD) of the original image, FD of above average (high) gray level image, FD of below (low) gray level image, and multifractal of order two. A modified box-counting approach is proposed to estimate the FD and computed features all are normalised in the same range [0, 1]. A feature domain smoothing is activated to reduce the spurious segmentation. Next, a nonsupervised clustering approach is used to segment a scene into the desired number of classes. Some supervised techniques like minimum distance classifier and k-nearest neighbour classifier are also considered. Mosaics of various natural textures are generated and the segmentation results are presented to show the efficiency of the technique.

Band-crossing anomalies in the cranking model

The problems with the cranking model in the vicinity of a band crossing recently pointed out by Hamamoto are reexamined. The sharp peak in the angular-momentum fluctuation and related peculiarities obtained previously in a non-self-consistent cranking calculation applied to an i 13 2 particles + rotor model are found to persist even when the calculation is done self-consistently, contrary to the expectations of Sorensen. A new feature is also found: vanishing interaction between crossing bands for some nucleon numbers. A simple analytic model is introduced which can qualitatively simulate such peculiarities and suggests a possible explanation for them. This model indicates that a check on the stability of self-consistent cranking solutions may sometimes help to eliminate spurious segments of rotational trajectories. Finally, angular-momentum fluctuations resulting from realistic HFB cranking calculations are presented for the first time. A method based on the RPA is suggested for correcting the fluctuation problem for the yrast band.

Parsing and word matching in the Lincoln Laboratory, speech recognition system

The Lincoln system is designed to recognize sentences conforming to a context-free grammar. Parsing is guided by a heuristic evaluation function which combines individual word scores into parse path scores. The word scores measure the degree of correspondence between phonemic dictionary spellings and the results of an acoustic-phonetic analysis of the input sentence. Word scoring is based on two computer-generated scoring matrices derived from confusion statistics gathered from 113 sentences. The synchronization problem resulting from missing and spurious segments is simplified by first aligning the vowels (sometimes in more than one combination). The effect of phonological rules is handled by insetting optional phonemes in the dictionary and flagging others as possibly missing. Other rules, which are specific to Lincoln's front-end analysis, predict spurious segments and the effect of neighboring semivowels on vowel classification. [This work was sponsored by the Advanced Research Projects Agency of the Department of Defense.]