Shape Segmentation Research Articles

12-APR Segmentation and Global Hu-F Descriptor for Human Spine MRI Image Retrieval

The image retrieval system has been used to provide the needed correct images to the physicians while the diagnosis and treatment process is being conducted. The earlier image retrieval system was a text-based image retrieval system (TBIRS) that used keywords for the image context and it requires human’s help to manually make text annotation on the images. The text annotation process is a laborious task especially when dealing with a huge database and is prone to human errors. To overcome the aforementioned issues, the approach of a content-based image retrieval system (CBIRS) with automatic indexing using visual features such as colour, shape and texture becomes popular. Thus, this study proposes a semi-automated shape segmentation method using a 12-anatomical point representation method of the human spine vertebrae for CBIRS. The 12 points, which are annotated manually on the region of interest (ROI), is followed by automatic ROI extraction. The segmentation method performs excellently, as evidenced by the highest accuracy of 0.9987, specificity of 0.9989, and sensitivity of 0.9913. The features of the segmented ROI are extracted with a novel global Hu-F descriptor that combines a global shape descriptor, a Hu moment invariant, and a Fourier descriptor based on the ANOVA selection approach. The retrieval phase is implemented using 100 MRI data of the human spine for thoracic, lumbar, and sacral bones. The highest obtained precision is 0.9110 using a normalized Manhattan metric for lumbar bones. In a conclusion, a retrieval system to retrieve lumbar bones of the MRI human spine has been successfully developed to help radiologists in diagnosing human spine diseases.

Fast VMAT planning for prostate radiotherapy: dosimetric validation of a deep learning-based initial segment generation method

Objective. To develop and evaluate a deep learning based fast volumetric modulated arc therapy (VMAT) plan generation method for prostate radiotherapy. Approach. A customized 3D U-Net was trained and validated to predict initial segments at 90 evenly distributed control points of an arc, linked to our research treatment planning system (TPS) for segment shape optimization (SSO) and segment weight optimization (SWO). For 27 test patients, the VMAT plans generated based on the deep learning prediction (VMATDL) were compared with VMAT plans generated with a previously validated automated treatment planning method (VMATref). For all test cases, the deep learning prediction accuracy, plan dosimetric quality, and the planning efficiency were quantified and analyzed. Main results. For all 27 test cases, the resulting plans were clinically acceptable. The V 95% for the PTV2 was greater than 99%, and the V 107% was below 0.2%. Statistically significant difference in target coverage was not observed between the VMATref and VMATDL plans (P = 0.3243 > 0.05). The dose sparing effect to the OARs between the two groups of plans was similar. Small differences were only observed for the Dmean of rectum and anus. Compared to the VMATref, the VMATDL reduced 29.3% of the optimization time on average. Significance. A fully automated VMAT plan generation method may result in significant improvement in prostate treatment planning efficiency. Due to the clinically acceptable dosimetric quality and high efficiency, it could potentially be used for clinical planning application and real-time adaptive therapy application after further validation.

The Optimal Choice of Technique for Stereotactic Radiosurgery—A LINAC-Based Dosimetric Study between DCA, DCA-SSO, DCA-SSO-VDR, and VMAT

Abstract Introduction Advanced radiation therapy delivery techniques require greater understanding of various planning sequences and methods. The aim of this study is to determine a class solution that finds the best possible technique to deliver for stereotactic radiosurgery between dynamic conformal arc (DCA) techniques using various options such as DCA, DCA + SSO (segment shape optimization), and DCA + SSO + VDR (variable dose rate) using noncoplanar beam arrangement and volumetric modulated arc therapy (VMAT) using coplanar beams. Materials and Methods In this dosimetric study, 11 brain cases were retrospectively planned for various techniques and analyzed for the Paddick conformity index (CI), Radiation Therapy Oncology Group homogeneity index (HI), Paddick gradient index (GI), treatment time in terms of monitor units (MU) and normal brain dose (V12Gy). The paired t-test was performed to know the statistical significance between the techniques. Results In terms of CI, GI, and control of the normal brain dose, the VMAT plan was superior to other techniques. But, HI was found to be better with DCA. Above all, VMAT delivered higher MU than any other technique. The p-values between DCA + SSO and DCA, DCA + SSO + VDR and DCA + SSO, and VMAT and DCA + SSO + VDR are as follows: CI: 0.0004, 0.015, and 0.03; GI: 0.03, 0.33, and 0.29; HI: 0.008, 0.04, and 0.06; V12 Gy of normal brain: 0.1, 0.01, 0.38. VMAT requires approximately 41 ± 17% more MU than DCA + SSO + VDR. Conclusion VMAT using coplanar beams is preferable among all the techniques, considering the dosimetric parameters studied. If VMAT is not available in the facility, DCA + SSO + VDR technique using non coplanar beams can be used to deliver SRS treatment.

Asymmetric sparse telescope

We designed and built a novel model of a deployed space telescope which can reliably align its segments to achieve the finest possible resolution. An asymmetric design of both the segment shapes and their pupil locations were tested in simulation and experiment. We optimised the sparse aperture for better spatial frequency coverage and for smoother images with less artifacts. The unique segment shapes allow for an easier identification and alignment, and the feedback is based only upon the focal image. The autonomous alignment and fine tuning are governed by mechanical simplicity and reliability.

Enhanced thermal and tensile behaviour of MWCNT reinforced palm oil polyol based shape memory polyurethane

Shape memory polyurethane (SMPU) has received tremendous interest because of its low cost, low density, as well as easy processing. However, its inferior mechanical properties compared to shape memory alloys have constrained its application in a broad range of engineering areas. Nanofillers are commonly added to polymers to overcome the problem associated with low mechanical characteristics. This study aims to examine the effect of various loadings of multiwalled carbon nanotubes (MWCNT) on the thermal stability, soft segment crystallinity, tensile and shape memory behaviour of palm oil polyol based SMPU nanocomposites. The SMPU nanocomposites were synthesised using a two-step polymerisation process. Microphase-separated SMPU nanocomposites obtained as the differential scanning calorimetric analysis showed two melting transitions, which belonged to the soft and hard phase domains. Furthermore, it was found that MWCNT had acted as a nucleating agent, which promoted the crystallisation process of SMPU nanocomposites. The thermal stability and tensile properties of SMPU/MWCNT nanocomposites were enhanced significantly as the MWCNT was added to the SMPU matrix. A considerable enhancement in the shape fixity (SF) value was revealed for PU-30 and PU-40 samples with the addition of MWCNT. The shape recovery (SR) time of SMPU was faster for samples reinforced with MWCNT, whereas SF increased while SR decreased upon increasing the shape memory cycle. The SMPU nanocomposites produced demonstrated enhanced thermal and tensile properties, which has the potential as smart material in many industrial applications.

SPAGHETTI

Neural implicit fields are quickly emerging as an attractive representation for learning based techniques. However, adopting them for 3D shape modeling and editing is challenging. We introduce a method for E diting I mplicit S hapes T hrough P art A ware G enera T ion, permuted in short as SPAGHETTI. Our architecture allows for manipulation of implicit shapes by means of transforming, interpolating and combining shape segments together, without requiring explicit part supervision. SPAGHETTI disentangles shape part representation into extrinsic and intrinsic geometric information. This characteristic enables a generative framework with part-level control. The modeling capabilities of SPAGHETTI are demonstrated using an interactive graphical interface, where users can directly edit neural implicit shapes. Our code, editing user interface demo and pre-trained models are available at github.com/amirhertz/spaghetti.

On the shape and size of liquid droplets on flat solid surfaces

This article introduces two dimensionless positive geometric parameters that characterize the shape of a liquid droplet on a flat solid surface, which formed by the surface tension. The first parameter, “shape coefficient” K, is defined by the ratio of volume to surface and is always >3 (3 is the space dimension). The second parameter, “holding limit” κ0, is defined by the fraction of osculating surface and K and is <1. The ratio of the surface tension energy of a droplet attached to a substrate in zero gravity to the energy of the same droplet floating in zero gravity is presented through these parameters as 1-(K-3)(κ0-κ)/3(1-κ0), where the material parameter κ (which appears in the Young equation κ=cosθ) indicates the decrease in liquid surface tension by the solid The relative energy of the surface tension, K and κ0, are explicitly expressed for a droplet of an elliptical rounded segment (ERS) shape through its eccentricity e, relative height χ, and relative rounding radius η. It is shown that the Young equation is a self-consistent (i.e., leading to η=0) minimum condition of the energy only in the spherical (e=0) case. The rounding, either inner or outer, is specified by the legs of a triangle with zero angles and the median as a slope line. The main result obtained is the proof that the outer rounded ERS weighty droplets with inflection points, due to weight and hydrostatic forces, cannot exist if their radii larger than 2-4 capillary length. This proscription is absent in zero gravity.

BIM generation from 3D point clouds by combining 3D deep learning and improved morphological approach

The demand for the models of BIM has increased due to the numerous applications in emergency response and location-based services. Creating a semantically rich 3D interior model has traditionally been a very manual process. Although the latest LiDAR scanning and photogrammetry techniques efficiently capture the existing building, the automatic reconstruction of complete volumetric and functional interior models is still an intensive and challenging research topic. This paper presents a novel parametric modeling method for reconstructing semantic volumetric building interiors from the unstructured point cloud of a building. Unlike existing partitioning-based methods, our proposed method overcomes the limitations by providing a flexible framework for combining 3D Deep Learning and an improved morphological approach for inverse BIM modeling. By employing a flexible and robust three-step mechanism, the proposed method first classifies the point cloud into thirteen types using a 3D Deep Learning method, then extracts the surfaces and generates the initial feature space. In regularizing the space and modeling BIM, the space boundaries are optimized by formulating the subordination between the grid cells generated by walls and the segmented boundary shapes generated by the gridded floor plan through energy minimization. Then, a grammar-enhanced point-line polygon and parametric description are designed to generate the final BIM model. By using a robust space partitioning and optimization method, three main goals are achieved: recovery of geometric and semantic information, robustness in different data sources (especially in non-Manhattan scenes), parametric BIM modeling in our proposed method. The paper demonstrates the potential of our algorithms for both RGB-D and LiDAR point clouds acquired from scenes in Manhattan and outside Manhattan. Experimental results show that this method is capable of automatically generating a geometrically and semantically consistent BIM model that is competitive with the existing method in terms of geometric accuracy and model completeness.

A semi-analytical method for moving force identification of bridge structures based on the discrete cosine transform and FEM

A semi-analytical method is proposed for moving force identification (MFI) based on the finite element model of the bridge structures. The moving force can be expanded by a set of cosine basis functions based on the discrete cosine transform (DCT) in the time domain. By constructing the segmented continuous mode shape of the bridge deck, the analytical relationship between the measured acceleration responses and the basis coefficients is derived using the Duhamel integral, which is not affected by the time step. The weighted l1-norm regularization method is used to solve the basis coefficients to improve the accuracy and noise immunity for identification. For complex bridge structures, the relationship between the responses and the moving forces can be analytically characterized by only knowing node modes of the bridge deck elements. Thus the identification can be carried out effectively. In numerical simulations, the effects of measured locations, noise levels, mode numbers, and moving speeds on the recognition accuracy are discussed under different models. The effectiveness, applicability, and robustness of the proposed method are verified.

Iso efficiency in nanostructured thermoelectric materials

A study is carried out for the efficiency of segmented thermoelectric microgenerators (μSTEGs). The study includes a) n-type and p-type double or triple segmentation and b) geometry shape factor of the thermoelements. The temperature-dependent thermoelectric properties of nanostructured materials are determined from experimental data. In addition, the impact of internal resistance, as a function of the thermoelement-geometric shape factor, on the efficiency surfaces of the μSTEGs is studied based on non-equilibrium thermodynamics. Results show that the efficiency surfaces of different μSTEGs intersect under different working conditions. The curve formed by the intersection points of the efficiency surfaces of the two thermoelectric systems is called the iso-efficiency curve. Thus, segmented thermoelectric systems with different efficiencies can reach a common efficiency for a given segmentation and geometric shape form of their thermoelements under different working conditions. The common efficiency that reaches (corresponds to) these thermoelectric systems is called Iso efficiency. The iso efficiency is reached due to the n-type and p-type material segmentation and geometric shape, which affect each thermoelement’s internal resistance. Furthermore, the efficiency of a μSTEG system can be improved due to the combination of effects such as the relationship between load resistance and internal resistance when it is affected by the geometric shape, temperature difference, and segmentation. Our results allow determinate the new iso efficiency parameters with a good selection of the thermodynamic, electrical, and geometric parameters and establish guidance for other materials engineering investigations, to improve the efficiency of μSTEGs.

Traditional Pattern Feature Extraction and Cultural Creative Design Application Based on Multilevel Histogram Shape Segmentation

Content-based stereo video and image retrieval relies on traditional pattern feature extraction and cultural creative design applications. In a 3D system, the 3D model is typically projected into a 2D point cloud, after which feature extraction takes place. A depth map is an image created by orthogonal projection of three-dimensional data or viewpoint matching, parallax calculation, and resampling into regular data based on depth value. In this paper, a multilevel histogram-based shape segmentation method is proposed. The threshold can be determined by analyzing the relationship between the peaks if there are several obvious peaks on the image histogram. This paper focuses on the use of traditional pattern feature extraction and cultural creative design based on the shape segmentation of multilevel histograms. Each algorithm can achieve good classification results in the experiment of rotation invariant similarity classification. The average accuracy of the HOD algorithm is 84.1%, the average accuracy of the RSDF algorithm is 86.2%, the average accuracy of the GIF algorithm is 81.3%, and the average accuracy of this paper’s algorithm is 89.9% when the rotation angle is 60–120°. The results show that this paper’s algorithm has a higher classification accuracy compared to the other algorithms and that it maintains a high average classification accuracy across all rotation angles, indicating that it is rotation invariant and robust. The histogram-based threshold method has the advantage of not requiring knowledge of the image’s prior information. The algorithm is easy to understand, straightforward, and quick. However, because the valley point in the histogram is not visible in images with low or high contrast between the target and the background area, it is difficult to select the threshold. The results of traditional pattern feature extraction can be improved using the retrieved pixels.

A new species of Megaglena Peters amp; Edmunds, 1970 (Ephemeroptera: Leptophlebiidae) from Tamil Nadu, India.

Megaglena sivarubani sp. nov. is described based on the nymphs from the Puliyuthu falls of Tamil Nadu, Southern India. The number of species of Megaglena Peters Edmunds is now expanded to three and it is the first record of the genus from the Tamil Nadu part of Southern Western Ghats. Megaglena sivarubani sp. nov. can be distinguished from Indian species M. agasthiya Vasanth, Subramanian Selvakumar by the body size of the nymphs, shape of the labial palp segment III, and by the setation of foretibia. The morphological variations between all the known species of Megaglena are discussed and summarized.

A Fully Soft Bionic Grasping Device with the Properties of Segmental Bending Shape and Automatically Adjusting Grasping Range

A Fully Soft Bionic Grasping Device with the Properties of Segmental Bending Shape and Automatically Adjusting Grasping Range

First record of the Marine Calanoid Copepod Pseudodiaptomus c.f. ardjuna from Shatt Al-Arab River, Iraq

The marine calanoid copepod Pseudodiaptomus c.f. ardjuna (Brehm, 1953) was recorded from some freshwater habitats in some regions of the Shatt A-Arab River during March – July 2009. These regions include Al-Kurnish area, Al-Sindebad Island during April-August 2009 and at Al-Gurna city on March 2009 only. The species is briefly described in this work and its morphological characters are compared with earlier descriptions from Iraqi coastal water, like the total length of female and male, body shape, female genital segment, the shape of the male posterior prosomal segment and number of the setae of the furcal rami.

OA08 Development of an automated deep learning-based system for distinguishing between ‘systemic sclerosis' and ‘normal' capillaries

Abstract Background/Aims Nailfold capillaroscopy is a key investigation in differentiating between primary and systemic sclerosis (SSc)-related Raynaud’s phenomenon (RP). However, interpreting capillaroscopy images (i.e. distinguishing ‘normal’ capillaries of primary RP [PRP] from abnormal capillaries of SSc) can be challenging. Our objectives were: (1) to develop a complete deep learning-based system to identify and classify capillary apices, and compute useful parameters such as width, shape score and vessel density; and (2) use the measured parameters to train and test a logistic regressor to distinguish between subjects with SSc and those with ‘normal’ capillary appearance. Methods 911 mosaic images were included for image-level feature extraction. 456 mosaic images (104 healthy control [HC], 83 PRP, 269 SSc) were used for training and the remaining 455 mosaic images (104 HC, 83 PRP and 268 SSc) were used for validation and testing the deep learning model. For subject-level classification 133 subjects (105 [79%] female, median age [range] 57 [19-80]) were used; 87 (25 HC, 14 PRP, and 48 SSc) were used for training and the remaining 46 (12 HC, 3 PRP, 31 SSc) for testing the logistic regressor. Images from patients with PRP and healthy subjects were grouped for all cases. The deep learning system uses a UNet architecture for capillary detection and vessel segmentation (density and shape score estimation). A ResNet-34 framework is used for capillary classification (distal vs. non-distal) and computing vessel widths. Area under Receiver Operating Characteristic (ROC) curves (AUC) measures the classification accuracy when assigning individuals to SSc and HC/PRP groups. Repeatability experiments were performed with different random seeds to validate the reproducibility of the results. Results For apex detection, the sensitivity and average false positive count from the Free-response Receiver Operating Characteristic (FROC) curve were 0.91 and 127.6, respectively. Apex classification accuracy (distal apices) was 93.8%, with an AUC of 0.92 and sensitivity of 0.9603. Overall AUC for subject level classification (HC/PRP vs SSc) for the current approach was 0.9739 ± 0.0207. Conclusion We have developed a completely automated nailfold capillary detection and analysis system based on deep learning. Apex detection, distal classification, and subsequent computation of distal apex measurements from nailfold capillaroscopy images are all performed with no human input. We have combined image-level features and have built a subject-level classifier model which successfully discriminates between SSc and HC/PRP with an improved AUC (i.e. improved sensitivity and specificity) compared to our previous work. We have performed the repeatability experiments with different random seeds and the performance of system is consistent with all the seeds. Disclosure P. Gurunath Bharathi: None. M. Berks: None. A. Herrick: None. G. Dinsdale: None. A. Murray: None. J. Manning: None. S. Wilkinson: None. C. Taylor: None.

A Novel Efficient Data Gathering Algorithm for Disconnected Sensor Networks Based on Mobile Edge Computing

Employing mobile elements is an efficient solution to the performance improvement of wireless sensor networks (WSNs). We propose an efficient data gathering mechanism for disconnected WSNs with rendezvous points (DGM-RPs). The mobile sink traverses the entire network and stops only at the rendezvous points (RPs) while gathers the data from sensors in every disconnected segment. In this paper, mobile sinks perform the task of edge computing and alleviate the load of upper cloud. We measure the shape of disconnected segments, layering them by use of the convex hull, and then design the travelling path of the mobile sink to minimize the travel latency to visit all disconnected segments. At least one RPs will be selected in a segment firstly, and then, on this basis, we consider the distribution density of sensor nodes and the location of the RPs already exist to adding new RPs, which make good use of the margin to reducing the energy consumption and prolong the network lifetime.

Bisphenol B disrupts testis differentiation partly via the estrogen receptor-mediated pathway and subsequently causes testicular dysgenesis in Xenopus laevis

There is growing concern about adverse effects of bisphenol A alternatives including bisphenol B (BPB) due to their estrogenic activity. However, limited data are available concerning the influences of BPB on male reproductive development in vertebrates, especially in amphibians, which are believed to be susceptible to estrogenic chemicals. The present study investigated the effects of 10, 100 and 1000 nM BPB (2.42, 24.2 and 242 μg/L) on testis development in Xenopus laevis, a model amphibian species for studying gonadal feminization. We found that exposure to BPB from stages 45/46 to 52 resulted in down-regulation of testis-biased gene expression and up-regulation of ovary-biased gene and vitellogenin (vtgb1) expression in gonad-mesonephros complexes (GMCs) of tadpoles at stage 52, coupled with suppressed cell proliferation in testes and reduced gonadal metameres, resembling the effects of 17ß-estradiol. Moreover, an estrogen receptor (ER) antagonist ICI 182780 antagonized BPB-caused up-regulation of ovary-biased gene and vtgb1 expression to some degree, indicating that the effects of BPB on X. laevis testis differentiation could be partly mediated by ER. All observations demonstrate that early exposure to BPB inhibited testis differentiation and exerted certain feminizing effects during gonadal differentiation. When exposure was extended to post-metamorphosis, testes exhibited histological and morphological abnormalities including segmented, discontinuous and fragmented shapes, besides altered sex-dimorphic gene expression. Notably, most of BPB-caused alterations were not concentration-dependent, but the lowest concentration indeed exerted significant effects. Overall, our study for the first time reveals that low concentrations of BPB can disrupt testis differentiation partly due to its estrogenic activity and subsequently cause testicular dysgenesis after metamorphosis, highlighting its reproductive risk to amphibians and other vertebrates including humans. Our finding also implies that estrogenic chemicals-caused testis differentiation inhibition at tadpole stages could predict later testicular dysgenesis after metamorphosis, meaning a possibility of early detection of abnormal testis development caused by estrogenic chemicals.

Multiblock (segmented) shape memory copolymers containing Polyurethane and rigid-chain polyimide blocks

Multiblock (segmented) shape memory copolymers containing Polyurethane and rigid-chain polyimide blocks

Concentric Push–Pull Robots: Planar Modeling and Design

Concentric push–pull robots (CPPR) combine the simplicity, miniaturization potential, and open lumen of concentric-tube robots with the kinematic advantages and stability of push–pull multibackbone designs. A CPPR segment is made from a pair concentric tubes with notches asymmetrically cut into their sides in opposing directions. The two tubes are attached to one another at their tips, and push–pull translation of the tube bases relative to each other changes the curvature along the length of the combined tube pair. Custom, variable-curvature shapes are possible by varying the notch parameters along the tubes. In this article, we present a planar, variable-curvature mechanics model for the actuated segment shape and a method for designing the notch pattern to achieve a desired planar, variable-curvature shape with maximal stiffness within specified strain limits. Experiments validate accuracy for various shapes, materials, and cross sections, showing that the design method achieves a variety of desired shapes. We also demonstrate a multisegment robot made from multiple tube pairs that can independently rotate and actuate, increasing the robot DOF.

Classification of Glaucoma Using Invariant Moment Methods on K-Nearest Neighbor and Random Forest Models

One of the cardiovascular diseases that can interfere with eye vision is glaucoma. This disease is caused by high pressure on the inside of the eyeball to cause blindness slowly. In general, screening or early diagnosis can help prevent glaucoma, specifically by analyzing several eye components affected by pressure, including the optical disc, optical cup, and blood vessels. Thus, by blending machine learning algorithms and computer vision technology, glaucoma classification and identification can be accelerated and improved. This study applied the Invariant Moment method to extract the optical cup and blood vessel segmentation's shape, scale, and rotation features. To obtain segmentation results for these two objects, we threshold two image datasets, DrishtiGS-1 and REFUGE, and implemented the approach described in this study to analyze system performance on these datasets. For the classification method used in this study, we proposed KNN and RF models to evaluate the suitability of the methods we used on the REFUGE and DrishtiGS-1 datasets and demonstrated that both models could be used to identify glaucoma through the use of fundus images. When the datasets were merged, we obtained 81.86% and 75.86% of accuracy when using blood vessel and optical cup segmentation results, respectively