Segmentation of the pancreatic computed tomography (CT) image in the Internet of Medical Things (IoMT) environment faces dual challenges of feature robustness and accurate recognition of small organs. As a clinically critical but anatomically challenging organ, the pancreas exhibits small volume, high inter-patient variability, and low contrast with surrounding tissues, making automatic pancreas segmentation a representative and difficult task in abdominal CT analysis. Existing automatic, machine-centric segmentation methods often perform unsatisfactorily across different medical institutions due to variations in imaging devices, changes in scanning protocols, as well as the irregular shape and blurred boundaries of the pancreas. To address this problem, this paper proposes a SimCLR-based Contrastive Swin-UNet model (ContSwinU), which integrates contrastive learning with the Swin Transformer architecture to achieve feature robustness learning and high-precision pancreas segmentation. Specifically, ContSwinU leverages SimCLR to learn robust feature representations, thereby enhancing the model’s generalization capability across diverse scenarios. Additionally, by incorporating the hierarchical window attention mechanism of the Swin Transformer, the model effectively balances local texture and global structural information, improving segmentation accuracy for the pancreas as a small organ. Experimental results on a public pancreas CT dataset demonstrate that ContSwinU achieves an IoU of 0.8041, a Dice coefficient of 0.8872, and a recall of 0.9014, significantly outperforming mainstream baseline methods. These results indicate that the proposed framework is well suited for challenging small-organ segmentation tasks and has the potential to be extended to other organs and multi-center IoMT scenarios. This study provides an effective solution for pancreas segmentation in IoMT environments and has substantial clinical application value.

Multi-thread flexible microelectrodes hold the promise of high-quality and long-term neural signal recording. To implant fragile microelectrodes into brain, a microneedle is usually used as a shuttle to increase stiffness. However, hooking microelectrodes with a microneedle is error-prone and time-consuming, due to the difficulty in accurately obtaining micro-object coordinates through low-quality microscope images. To solve this problem, this paper proposes an intelligent microscope vision system based on few-shot segmentation method. Firstly, a stereo vision system is designed to enable cameras to focus on all microelectrode threads simultaneously. Secondly, a few-shot instance segmentation method is proposed to obtain key-point coordinates for vision guidance, which consists of data augmentation, improved Mask-RCNN and anchor-free clustering loss. The data augmentation method synthesizes low-quality images to strengthen model’s generalization ability. To improve the proposal quality, a residual region proposal module is introduced into Mask-RCNN. By clustering instance features in metric space, the anchor-free clustering loss enhances the model capability of predicting hard instances and avoids the intra-class bias of fixed anchor. Experimental result shows that the proposed method achieves 99.72% and 90% correct rate for microelectrode and microneedle segmentation with 5-shot training. Code is available athttps://github.com/NamingIsEasy/FSS_implantation. Note to Practitioners—Multi-thread flexible microelectrodes are an emerging brain-computer interface platform. Compared with traditional electrodes, they have the advantages of low elastic modulus, micron-level width and material biocompatibility. However, the low elastic modulus also makes it difficult to be inserted into brain. Thus, researchers proposed “sewing machine” paradigm, in which a microneedle is used to hook microelectrodes and drive them to be inserted into brain. The hooking process is threading the microneedle into engaging holes at the end of microelectrodes. However, undesirable conditions in microscope images, such as out-of-focus blur and occlusion, make it difficult to accurately obtain microneedle and microelectrode coordinates. Towards automated hooking operation, this paper proposed an intelligent microscope vision system based on few-shot segmentation. Firstly, a stereo vision system is designed to focus cameras on all microelectrode threads simultaneously. Secondly, a few-shot segmentation method is proposed to reduce time of image acquisition and annotation process. It consists of data augmentation, improved Mask-RCNN and anchor-free clustering loss. The data augmentation method synthesizes undesirable-condition images to reduce the bias of training dataset. The classical region proposal module in Mask-RCNN is replaced with an improved residual version. To make the model focus more on hard instances during training, an anchor-free clustering loss is introduced. The proposed method achieves 99.72% and 90% correct rate for microelectrode and microneedle segmentation in 5-shot experiments. In future, we will explore automated hooking control and subsequent implantation process based on the proposed vision system.

Ultrasound can non-invasively detect muscle deformations and has great potential applications in prosthetic hand control. Traditional ultrasound equipment was usually too bulky to be applied in wearable scenarios. This research presented a compact ultrasound device that could be integrated into a prosthetic hand socket. The miniaturized ultrasound system included four A-mode ultrasound transducers for sensing musculature deformations, a signal excitation/acquisition module, and a prosthetic hand control module. The size of the ultrasound system was 65*75*25 mm, weighing only 85 g. For the first time, we integrated the ultrasound system into a prosthetic hand socket to evaluate its performance in practical prosthetic hand control. We designed an experiment requiring twenty subjects to perform six commonly used gestures. The performance of decoding ultrasound signals was analyzed offline using four classification algorithms and then was assessed in online control. The average values of online classification accuracy with and without wearing the physical prosthetic were 91.5 [Formula: see text] and 96.5 [Formula: see text], respectively. We found that wearing the prosthetic hand influenced the ultrasound gestures classification accuracy, but remarkable online classification performance could still be maintained. These experimental results demonstrated the efficacy of the designed integrated ultrasound system for practical use, paving the way for an effective HMI system that could be widely used in prosthetic hand control.

Image-guided radiation therapy (IGRT) is the most effective treatment for head and neck cancer. The successful implementation of IGRT requires accurate delineation of organ-at-risk (OAR) in the computed tomography (CT) images. In routine clinical practice, OARs are manually segmented by oncologists, which is time-consuming, laborious, and subjective. To assist oncologists in OAR contouring, we proposed a three-dimensional (3D) lightweight framework for simultaneous OAR registration and segmentation. The registration network was designed to align a selected OAR template to a new image volume for OAR localization. A region of interest (ROI) selection layer then generated ROIs of OARs from the registration results, which were fed into a multiview segmentation network for accurate OAR segmentation. To improve the performance of registration and segmentation networks, a centre distance loss was designed for the registration network, an ROI classification branch was employed for the segmentation network, and further, context information was incorporated to iteratively promote both networks' performance. The segmentation results were further refined with shape information for final delineation. We evaluated registration and segmentation performances of the proposed framework using three datasets. On the internal dataset, the Dice similarity coefficient (DSC) of registration and segmentation was 69.7% and 79.6%, respectively. In addition, our framework was evaluated on two external datasets and gained satisfactory performance. These results showed that the 3D lightweight framework achieved fast, accurate and robust registration and segmentation of OARs in head and neck cancer. The proposed framework has the potential of assisting oncologists in OAR delineation.

Recently, an emerging trend in medical image classification is to combine radiomics framework with deep learning classification network in an integrated system. Although this combination is efficient in some tasks, the deep learning-based classification network is often difficult to capture an effective representation of lesion regions, and prone to face the challenge of overfitting, leading to unreliable features and inaccurate results, especially when the sizes of the lesions are small or the training dataset is small. In addition, these combinations mostly lack an effective feature selection mechanism, which makes it difficult to obtain the optimal feature selection. In this paper, we introduce a novel and effective deep semantic segmentation feature-based radiomics (DSFR) framework to overcome the above-mentioned challenges, which consists of two modules: the deep semantic feature extraction module and the feature selection module. Specifically, the extraction module is utilized to extract hierarchical semantic features of the lesions from a trained segmentation network. The feature selection module aims to select the most representative features by using a novel feature similarity adaptation algorithm. Experiments are extensively conducted to evaluate our method in two clinical tasks: the pathological grading prediction in pancreatic neuroendocrine neoplasms (pNENs), and the prediction of thrombolytic therapy efficacy in deep venous thrombosis (DVT). Experimental results on both tasks demonstrate that the proposed method consistently outperforms the state-of-the-art approaches by a large margin.

As two of the most important characteristics of workloads, burstiness and self-similarity are gaining more and more attention. Workload generation, which is a key technique for performance analysis and simulations, has also attracted an increasing interest in cloud community in recent years. Though a large number of methods for synthetically generating bursty or self-similar workloads have been proposed in the literature, none of them can deal with workload generation with both of the two characteristics. In this paper, a configurable and intelligible synthetic generator (BURSE) is proposed for bursty and self-similar workloads in cloud computing based on a superposition of two-state Markov Modulated Poisson Processes (MMPP2s). The proposed generator can produce workloads with both specified intension of burstiness and self-similarity. Detailed experimental evaluation demonstrates the accuracy, robustness and good applicability of BURSE.

As one of most important characteristics of Web-based systems'workloads, burstiness is gaining more and more attentions. And synthetically generating bursty workloads is a key technique for performance analysis. In this paper, a configurable and intelligible synthetic bursty workload generation method for Web 2.0 benchmark Olio has been proposed based on 2-state Markovian arrival processes (MAP2). By comparing the actual value of index of dispersion for counts (IDC) estimated from system logs with the target value deduced from MAP2 model, we show that our method is more accurate than related work.

A central goal of cloud computing is high resource utilization through hardware sharing; however, utilization often remains modest in practice due to the challenges in predicting consolidated application performance accurately. We present a thorough experimental study of consolidated n-tier application performance at high utilization to address this issue through reproducible measurements. Our experimental method illustrates opportunities for increasing operational efficiency by making consolidated application performance more predictable in high utilization scenarios. The main focus of this paper are non-trivial dependencies between SLA-critical response time degradation effects and software configurations (i.e., readily available tuning knobs). Methodologically, we directly measure and analyze the resource utilizations, request rates, and performance of two consolidated n-tier application benchmark systems (RUBBoS) in an enterprise-level computer virtualization environment. We find that monotonically increasing the workload of an n-tier application system may unexpectedly spike the overall response time of another co-located system by 300 percent despite stable throughput. Based on these findings, we derive a software configuration best-practice to mitigate such non-monotonic response time variations by enabling higher request-processing concurrency (e.g., more threads) in all tiers. More generally, this experimental study increases our quantitative understanding of the challenges and opportunities in the widely used (but seldom supported, quantified, or even mentioned) hypothesis that applications consolidate with linear performance in cloud environments.

Parallel processing is an important pattern in cluster systems. To analyze the performance of parallel processing systems, we leveraged the fork-join queueing network (FJQN) models. However, there are no easy solutions to these models, especially for the multi-class closed ones. In this paper, a novel and efficient method named horizontal decomposition has been proposed. The main idea of our method is to approximate a non-product-form FJQN with some closed and open product-form networks. So the computational complexity can be dramatically reduced compared with the traditional hierarchical decomposition approach. And the algorithms for solving single-class and multi-class closed FJQNs have been developed respectively based on the horizontal decomposition. With these algorithms, the response time and throughput of each service center in a FJQN can be approximately calculated. The evaluation results show that 90 percentile of relative errors of most service centers are less than 15% except for the shared ones. The evaluation results also showed that the number of iterations in the algorithm for the multi-class FJQNs almost grows linearly with the population of networks.

Enterprise service bus is one of the most promising infrastructures for simplifying enterprise application integration (EAI). However, in order to exploit its full potential for integrating large scale cross-organizational applications, a flexible and reliable distributed environment management infr

Over the last decade, the architectures and technologies used for enterprise application integration have been improved, and many companies have proposed varied solutions for integration. But these traditional approaches have some disadvantages such as high cost, poor flexibility and vendor lock-in. And now, the service oriented architecture, advanced in loose-couple, low cost and high integration ability, is thought to be the most advisable approach for business integration. In this paper, we introduce an SOA based enterprise application integration platform named JTang Synergy. JTang Synergy is composed of a basic integration platform, a supported platform, administration tools and development tools. As the core of JTang Synergy, the basic integration platform is implemented according to Java Business Integration which makes JTang Synergy more flexible and vendor-neutral. And we employed an event-based enterprise service bus to realize integration. The supported framework and the tools ease JTang Synergy to develop and integrate services. And a scenario is introduced to illustrate the integration process using JTang Synergy.