Bidirectional Segments Research Articles

A bi-directional segmentation method for prostate ultrasound images under semantic constraints.

Due to the lack of sufficient labeled data for the prostate and the extensive and complex semantic information in ultrasound images, accurately and quickly segmenting the prostate in transrectal ultrasound (TRUS) images remains a challenging task. In this context, this paper proposes a solution for TRUS image segmentation using an end-to-end bidirectional semantic constraint method, namely the BiSeC model. The experimental results show that compared with classic or popular deep learning methods, this method has better segmentation performance, with the Dice Similarity Coefficient (DSC) of 96.74% and the Intersection over Union (IoU) of 93.71%. Our model achieves a good balance between actual boundaries and noise areas, reducing costs while ensuring the accuracy and speed of segmentation.

Single probe shear scanning method for on-machine measurement of an optical profile.

This study presents a new (to the best of our knowledge) error separation method with a single displacement probe, named as single probe shear scanning (SPSS) method, for the on-machine optical profile measurement to overcome the problems of the existing multiprobe method like the large deviation of probe spacing and the probes' performance difference. The confocal sensor with superior dynamic range, high lateral resolution, and large measurement angle to surface is applied in this study to fulfill the measurement of the optical aspheric surface. The single probe measurement system, in which the probe fixed on a flexure hinge is driven straight within a millimeter-level travel range, is established to realize the function of the multiprobe. For the established system, a new exact profile reconstruction algorithm is built to eliminate the influences of straightness errors of the scanning stage and the systemic errors of shear stage, and to reduce the effect of the sensor drift. The reconstruction algorithms by difference measurement with two shears are studied to build the bidirectional segment stitching reconstruction method, which reduces the error accumulation and improves the reconstruction accuracy under the condition of measuring errors. A profile reconstruction method with three shears measurement is proposed to make a further improvement on the reconstruction accuracy. The proposed reconstruction method with three shears measurement is successfully employed for the on-machine measurement of an aspheric surface profile, and the evaluation results agree well with those from the Taylor profiler.

SECTOR: A Neural Model for Coherent Topic Segmentation and Classification

When searching for information, a human reader first glances over a document, spots relevant sections, and then focuses on a few sentences for resolving her intention. However, the high variance of document structure complicates the identification of the salient topic of a given section at a glance. To tackle this challenge, we present SECTOR, a model to support machine reading systems by segmenting documents into coherent sections and assigning topic labels to each section. Our deep neural network architecture learns a latent topic embedding over the course of a document. This can be leveraged to classify local topics from plain text and segment a document at topic shifts. In addition, we contribute WikiSection, a publicly available data set with 242k labeled sections in English and German from two distinct domains: diseases and cities. From our extensive evaluation of 20 architectures, we report a highest score of 71.6% F1 for the segmentation and classification of 30 topics from the English city domain, scored by our SECTOR long short-term memory model with Bloom filter embeddings and bidirectional segmentation. This is a significant improvement of 29.5 points F1 over state-of-the-art CNN classifiers with baseline segmentation.

Effects of chip pretreatment and feeding segments on specific energy and pulp quality in TMP production

Abstract Increased wood softening and refining intensity have earlier been utilized to improve refining efficiency in mechanical pulping. We have evaluated a combination of increased softening by low dose sulphite chip pretreatment and increased intensity by feeding segment design in a TMP line for production of high quality printing papers. Norway spruce wood chips were preheated, compressed in an Impressafiner and impregnated with water or sodium sulphite solutions (Na2SO3 charges 3.6 and 7.2 kg/t). Chips were refined in two parallel 68” double disc refiners using two different refining conditions: standard bidirectional segments at normal production rate (9 t/h) and feeding segments at increased production rate (11.1–12.1 t/h). The feeding segments enabled a 30 % increase in production rate. Refining with feeding segments at 12.1 t/h production rate combined with chip pretreatment with 3.6 kg/t sodium sulphite reduced the specific energy 360 kWh/t (19 %) compared to refining with standard segments and no pretreatment. Pulp properties were similar for the two configurations. The combination of feeding segments and chip pretreatment with water reduced the specific energy 180 kWh/t (9 %). Implementation of most of the technology presented has reduced the electrical energy use for the mill by approximately 80 GWh/year.

Performance Improvement of Cluster-Based Routing Protocol in VANET

Vehicular ad-hoc NETworks (VANETs) have received considerable attention in recent years, due to its unique characteristics, which are different from mobile ad-hoc NETworks, such as rapid topology change, frequent link failure, and high vehicle mobility. The main drawback of VANETs network is the network instability, which yields to reduce the network efficiency. In this paper, we propose three algorithms: cluster-based life-time routing (CBLTR) protocol, Intersection dynamic VANET routing (IDVR) protocol, and control overhead reduction algorithm (CORA). The CBLTR protocol aims to increase the route stability and average throughput in a bidirectional segment scenario. The cluster heads (CHs) are selected based on maximum lifetime among all vehicles that are located within each cluster. The IDVR protocol aims to increase the route stability and average throughput, and to reduce end-to-end delay in a grid topology. The elected intersection CH receives a set of candidate shortest routes (SCSR) closed to the desired destination from the software defined network. The IDVR protocol selects the optimal route based on its current location, destination location, and the maximum of the minimum average throughput of SCSR. Finally, the CORA algorithm aims to reduce the control overhead messages in the clusters by developing a new mechanism to calculate the optimal numbers of the control overhead messages between the cluster members and the CH. We used SUMO traffic generator simulators and MATLAB to evaluate the performance of our proposed protocols. These protocols significantly outperform many protocols mentioned in the literature, in terms of many parameters.

A three-dimensional image processing program for accurate, rapid, and semi-automated segmentation of neuronal somata with dense neurite outgrowth.

Three-dimensional (3-D) image analysis techniques provide a powerful means to rapidly and accurately assess complex morphological and functional interactions between neural cells. Current software-based identification methods of neural cells generally fall into two applications: (1) segmentation of cell nuclei in high-density constructs or (2) tracing of cell neurites in single cell investigations. We have developed novel methodologies to permit the systematic identification of populations of neuronal somata possessing rich morphological detail and dense neurite arborization throughout thick tissue or 3-D in vitro constructs. The image analysis incorporates several novel automated features for the discrimination of neurites and somata by initially classifying features in 2-D and merging these classifications into 3-D objects; the 3-D reconstructions automatically identify and adjust for over and under segmentation errors. Additionally, the platform provides for software-assisted error corrections to further minimize error. These features attain very accurate cell boundary identifications to handle a wide range of morphological complexities. We validated these tools using confocal z-stacks from thick 3-D neural constructs where neuronal somata had varying degrees of neurite arborization and complexity, achieving an accuracy of ≥95%. We demonstrated the robustness of these algorithms in a more complex arena through the automated segmentation of neural cells in ex vivo brain slices. These novel methods surpass previous techniques by improving the robustness and accuracy by: (1) the ability to process neurites and somata, (2) bidirectional segmentation correction, and (3) validation via software-assisted user input. This 3-D image analysis platform provides valuable tools for the unbiased analysis of neural tissue or tissue surrogates within a 3-D context, appropriate for the study of multi-dimensional cell-cell and cell-extracellular matrix interactions.

Bidirectional segmentation of three-dimensional cardiac MR images using a subject-specific dynamical model.

Statistical model-based segmentation of the left ventricles has received considerable attention these years. While many statistical models have been shown to improve segmentation results, most of them either belong to (1) static models (SM) that neglect the temporal coherence of a cardiac sequence, or (2) generic dynamical models (GDM) that neglect the individual differences of cardiac motion. In this paper, we propose a subject-specific dynamical model (SSDM) that can simultaneously handle inter-subject variability and temporal cardiac dynamics (intra-subject variability). We also design a dynamic prediction algorithm that can progressively predict the shape of a new cardiac sequence at a given frame based on the shapes observed in earlier frames. Furthermore, to reduce the accumulation of the segmentation errors throughout the entire sequence, we take into account the periodic nature of cardiac motion and perform bidirectional segmentation from a certain frame in a cardiac sequence. "Leave-one-out" validation on 32 sequences show that our algorithm can capture local shape variations and suppress the propagation of segmentation errors.

Bi-directional segmentation from the color image sequence for in-vivo visualization

Bi-directional segmentation from the color image sequence for in-vivo visualization