ORCID Profile
0000-0001-9013-0818
Current Organisations
Central South University
,
Research Center for Artificial Intelligence, Monash University
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Korean Society for Internet Information (KSII)
Date: 30-05-2016
Publisher: Springer Science and Business Media LLC
Date: 13-08-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2020
Publisher: Springer Science and Business Media LLC
Date: 20-06-2016
Publisher: Hindawi Limited
Date: 18-05-2020
DOI: 10.1155/2020/6509596
Abstract: Prostate cancer (PCa) is one of the main diseases that endanger men’s health worldwide. In developing countries, due to the large number of patients and the lack of medical resources, there is a big conflict between doctors and patients. To solve this problem, an auxiliary medical decision system for prostate cancer was constructed. The system used six relevant tumor markers as the input features and employed classical machine learning models (support vector machine and artificial neural network). Stacking method aimed at different ensemble models together was used for the reduction of overfitting. 1,933,535 patient information items had been collected from three first-class hospitals in the past five years to train the model. The result showed that the auxiliary medical system could make use of massive data. Its performance is continuously improved as the amount of data increases. Based on the system and collected data, statistics on the incidence of prostate cancer in the past five years were carried out. In the end, influence of diet habit and genetic inheritance for prostate cancer was analyzed. Results revealed the increasing prevalence of PCa and great negative impact caused by high-fat diet and genetic inheritance.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2023
Publisher: Springer International Publishing
Date: 2021
Publisher: Springer Science and Business Media LLC
Date: 04-06-2019
Publisher: MDPI AG
Date: 06-08-2018
DOI: 10.3390/FI10080074
Abstract: In the social scene of opportunistic networks, message applications find suitable relay nodes or certain transmission destinations from the surrounding neighbors through specific network addresses of users. However, at the dawn of big data and 5G networks, the variational location information of nodes is difficult to be available to mobile devices all the time, and a long wait for the destination may cause severe end-to-end delay. To improve the transmission environment, this study constructs an efficient routing-delivery scheme (Predict and Forward) based on node profile for the opportunistic networks. The node profile effectively characterizes nodes by analyzing and comparing their attributes instead of network addresses, such as physical characteristics, places of residence, workplaces, occupations or hobbies. According to the optimal stopping theory, this algorithm implements the optimal transmission for Prelearn messages by iding the complex data transmission process into two different phases (Predict and Forward). Through simulations and the comparison of routing algorithms in opportunistic networks, the proposed strategy increases the delivery ratio by 80% with the traditional methods on average, and the average end-to-end delay in this algorithm is the lowest.
Publisher: MDPI AG
Date: 28-02-2023
DOI: 10.3390/MATH11051187
Abstract: Medical image analysis methods have been applied to clinical scenarios of tumor diagnosis and treatment. Many studies have attempted to optimize the effectiveness of tumor MRI image segmentation by deep learning, but they do not consider the optimization of local details and the interaction of global semantic information. Second, although medical image pattern recognition can learn representative semantic features, it is challenging to ignore useless features in order to learn generalizable embeddings. Thus, a tumor-assisted segmentation method is proposed to detect tumor lesion regions and boundaries with complex shapes. Specifically, we introduce a denoising convolutional autoencoder (DCAE) for MRI image noise reduction. Furthermore, we design a novel tumor MRI image segmentation framework (NFSR-U-Net) based on class-correlation pattern aggregation, which first aggregates class-correlation patterns in MRI images to form a class-correlational representation. Then the relationship of similar class features is identified to closely correlate the dense representations of local features for classification, which is conducive to identifying image data with high heterogeneity. Meanwhile, the model uses a spatial attention mechanism and residual structure to extract effective information of the spatial dimension and enhance statistical information in MRI images, which bridges the semantic gap in skip connections. In the study, over 4000 MRI images from the Monash University Research Center for Artificial Intelligence are analyzed. The results show that the method achieves segmentation accuracy of up to 96% for tumor MRI images with low resource consumption.
Publisher: Springer Science and Business Media LLC
Date: 10-10-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: Hindawi Limited
Date: 26-11-2021
DOI: 10.1155/2021/8554351
Abstract: As the Internet of Things (IoT) smart mobile devices explode in complex opportunistic social networks, the amount of data in complex networks is increasing. Large amounts of data cause high latency, high energy consumption, and low-reliability issues when dealing with computationally intensive and latency-sensitive emerging mobile applications. Therefore, we propose a task-sharing strategy that comprehensively considers delay, energy consumption, and terminal reputation value (DERV) for this context. The model consists of a task-sharing decision model that integrates latency and energy consumption, and a reputation value-based model for the allocation of the computational resource game. The two submodels apply an improved particle swarm algorithm and a Lagrange multiplier, respectively. Mobile nodes in the complex social network are given the opportunity to make decisions so that they can choose to share computationally intensive, latency-sensitive computing tasks to base stations with greater computing power in the same network. At the same time, to prevent malicious competition from end nodes, the base station decides the allocation of computing resources based on a database of reputation values provided by a trusted authority. The simulation results show that the proposed strategy can meet the service requirements of low delay, low power consumption, and high reliability for emerging intelligent applications. It effectively realizes the overall optimized allocation of computation sharing resources and promotes the stable transmission of massive data in complex networks.
Publisher: Hindawi Limited
Date: 06-07-2022
DOI: 10.1002/INT.22949
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2022
Publisher: Research Square Platform LLC
Date: 31-01-2020
Abstract: Background Most developing countries face great problems in the medical, and the threat posed by large populations, scarce medical resources and inadequate medical personnel will affect the development and stability of the society. Therefore, for most developing countries, the development of intelligent medical systems can greatly alleviate the social contradictions arising from this problem. Intelligent Medical System is a system to assist doctors to make decisions. Through effective input, the system makes corresponding decisions and provides doctors with corresponding auxiliary diagnosis and relevant treatment plans. Methods The experimental team collected and compiled about 2,156,528 data items based on the hospitalization information of more than 8,000 prostate patients in three hospitals of Xiangya. The ratio of experimental data to test data was about 7: 3. Combining prostate cancer images and physical indicators to assist diagnosis and make decisions, from the extraction of corresponding image feature data to the final diagnosis decision, a new intelligent system for prostate cancer data decision-making based on Perceptron neural network is proposed. In the comprehensive decision-making, the final decision is made by using the rule-reasoning model. Through data collection, medical data analysis and integration, image processing and analysis, and disease detection and decision-making processes, patients are assisted in diagnosis and treatment to solve the problems and social contradictions facing most developing countries. Results Through the study of hospitalization information of more than 8,000 prostate patients in three hospitals, about 2,156,528 data items were collected and compiled for experiment purposes. Experimental data shows that when the patient base increases from 200 to 8,000, the accuracy of the machine-assisted diagnostic system will increase from 61% to 87%, and the doctor's diagnosis rate will be reduced to 81%. Conclusions From the study, it is concluded that when the patient base reaches a certain number, the diagnostic accuracy of the machine-assisted diagnosis system will exceed the doctor's expertise. So the smart medical system can help doctors and Medical experts make suggest more effective treatments.
Publisher: Wiley
Date: 13-12-2021
DOI: 10.1002/DAC.5062
Abstract: With the advent of the era of Big Data, users are increasingly demanding network bandwidth and data storage in the Internet of Things (IoT) system. While current research on the opportunistic social network does not take the redundant influence of high‐speed data transmission into account, which leads to problems such as lower delivery ratio, we present an effective data transmission scheme based on IoT system (EDTS). To ide the community, which consists of devices with relatively close connections, we measure the social relationship of nodes by quantifying the remaining cache, social relation, and interest similarity in opportunistic social networks. An efficient strategy is designed in this paper to update the community by analyzing the change of edge weights between two nodes in the community, deciding whether the community should be further ided, and whether the nodes should join the larger community. The proposed scheme also involves data transmission methods based on community, which involve inter‐community forwarding and intra‐community forwarding. Simulation results show that EDTS outperforms other comparative algorithms with regard to average delivery ratio, end‐to‐end delay, and routing overhead.
Publisher: Elsevier BV
Date: 09-2022
Publisher: Wiley
Date: 05-05-2021
Abstract: Ethylene is one of the most widely used chemical compounds. It is readily transformed to a variety of useful products that can replace those derived from fossil sources. Further, the ability to produce ethylene from atmospheric carbon dioxide would significantly assist in the urgent need to stabilize, and ultimately to reduce, the concentration of greenhouse gases in the atmosphere. This review covers the electrochemical reduction of carbon dioxide at copper‐based cathodes. The direct production of ethylene is the focus of the review, but it is also relevant to include the important ethylene precursor and intermediate in the carbon dioxide reduction reaction, carbon monoxide. Carbon monoxide can be reduced to ethylene on a copper cathode under similar conditions to carbon dioxide. Ethanol is another potential product of the reduction of carbon dioxide at a copper cathode. It can be readily dehydrated to ethylene, further enhancing the overall yield of ethylene. The aim of the review is to show that there are many interacting parameters that influence the effectiveness and efficiency of the electrochemical reduction of carbon dioxide at copper‐based cathodes.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: MDPI AG
Date: 31-10-2022
DOI: 10.3390/HEALTHCARE10112189
Abstract: Histopathological examination is an important criterion in the clinical diagnosis of osteosarcoma. With the improvement of hardware technology and computing power, pathological image analysis systems based on artificial intelligence have been widely used. However, classifying numerous intricate pathology images by hand is a tiresome task for pathologists. The lack of labeling data makes the system costly and difficult to build. This study constructs a classification assistance system (OHIcsA) based on active learning (AL) and a generative adversarial network (GAN). The system initially uses a small, labeled training set to train the classifier. Then, the most informative s les from the unlabeled images are selected for expert annotation. To retrain the network, the final chosen images are added to the initial labeled dataset. Experiments on real datasets show that our proposed method achieves high classification performance with an AUC value of 0.995 and an accuracy value of 0.989 using a small amount of labeled data. It reduces the cost of building a medical system. Clinical diagnosis can be aided by the system’s findings, which can also increase the effectiveness and verifiable accuracy of doctors.
Publisher: MDPI AG
Date: 06-11-2018
DOI: 10.3390/SYM10110600
Abstract: The amount of data has skyrocketed in Fifth-generation (5G) networks. How to select an appropriate node to transmit information is important when we analyze complex data in 5G communication. We could sophisticate decision-making methods for more convenient data transmission, and opportunistic complex social networks play an increasingly important role. Users can adopt it for information sharing and data transmission. However, the encountering of nodes in mobile opportunistic network is random. The latest probabilistic routing method may not consider the social and cooperative nature of nodes, and could not be well applied to the large data transmission problem of social networks. Thus, we quantify the social and cooperative relationships symmetrically between the mobile devices themselves and the nodes, and then propose a routing algorithm based on an improved probability model to predict the probability of encounters between nodes (PEBN). Since our algorithm comprehensively considers the social relationship and cooperation relationship between nodes, the prediction result of the target node can also be given without encountering information. The neighbor nodes with higher probability are filtered by the prediction result. In the experiment, we set the node’s selfishness randomly. The simulation results show that compared with other state-of-art transmission models, our algorithm has significantly improved the message delivery rate, hop count, and overhead.
Publisher: Hindawi Limited
Date: 2018
DOI: 10.1155/2018/1571974
Abstract: In real network environment, nodes may acquire the communication destination during data transmission and find a suitable neighbor node to perform effective data classification transmission. This is similar to finding certain transmission targets during data transmission with mobile devices. However, the node cache space in networks is limited, and waiting for the destination node can also cause end-to-end delay. To improve the transmission environment, this study established Data Transmission Probability and Cache Management method. According to selection of high meeting probability node, cache space is reconstructed by node. It is good for nodes to improve delivery ratio and reduce delay. Through experiments and the comparison of opportunistic network algorithms, this method improves the cache utilization rate of nodes, reduces data transmission delay, and improves the overall network efficiency.
Publisher: Springer Science and Business Media LLC
Date: 02-04-2019
Publisher: Institution of Engineering and Technology (IET)
Date: 30-06-2023
DOI: 10.1049/IPR2.12854
Abstract: Due to the improvement in computing power and the development of computer technology, deep learning has pene‐trated into various fields of the medical industry. Segmenting lesion areas in medical scans can help clinicians make accurate diagnoses. In particular, convolutional neural networks (CNNs) are a dominant tool in computer vision tasks. They can accurately locate and classify lesion areas. However, due to their inherent inductive bias, CNNs may lack an understanding of long‐term dependencies in medical images, leading to less accurate grasping of details in the images. To address this problem, we explored a Transformer‐based solution and studied its feasibility in medical imaging tasks (OstT). First, we performed super‐resolution reconstruction on the original MRI image of osteosarcoma and improved the texture features of the tissue structure to reduce the error caused by the unclear tissue structure in the image during model training. Then, we propose a Transformer‐based method for medical image segmentation. A gated axial attention model is used, which augments existing architectures by introducing an additional control mechanism in the self‐attention module to improve segmentation accuracy. Experiments on real datasets show that our method outper‐forms existing models such as Unet. It can effectively assist doctors in imaging examinations.
Publisher: MDPI AG
Date: 13-05-2022
DOI: 10.3390/MATH10101669
Abstract: With the advent of the 5G era, the number of Internet of Things (IoT) devices has surged, and the population’s demand for information and bandwidth is increasing. The mobile device networks in IoT can be regarded as independent “social nodes”, and a large number of social nodes are combined to form a new “opportunistic social network”. In this network, a large amount of data will be transmitted and the efficiency of data transmission is low. At the same time, the existence of “malicious nodes” in the opportunistic social network will cause problems of unstable data transmission and leakage of user privacy. In the information society, these problems will have a great impact on data transmission and data security therefore, in order to solve the above problems, this paper first ides the nodes into “community isions”, and then proposes a more effective node selection algorithm, i.e., the FL node selection algorithm based on Distributed Proximal Policy Optimization in IoT (FABD) algorithm, based on Federated Learning (FL). The algorithm is mainly ided into two processes: multi-threaded interaction and a global network update. The device node selection problem in federated learning is constructed as a Markov decision process. It takes into account the training quality and efficiency of heterogeneous nodes and optimizes it according to the distributed near-end strategy. At the same time, malicious nodes are screened to ensure the reliability of data, prevent data loss, and alleviate the problem of user privacy leakage. Through experimental simulation, compared with other algorithms, the FABD algorithm has a higher delivery rate and lower data transmission delay and significantly improves the reliability of data transmission.
Publisher: Hindawi Limited
Date: 07-2022
DOI: 10.1155/2022/4879557
Abstract: Billions of people around the world send and receive data over online networks daily. Sufficient and redundant data are transmitted over social platforms with AI-assisted in 5G networks. In opportunistic social networks, the main challenge faced by traditional methods is that numerous user nodes participate in data transmission, causing a lot of message copy redundancy and node cache consumption. As a result, the transmission delay of the algorithm is high, the node energy consumption is too large, and even information is lost. To solve these problems, this study establishes an artificial intelligence-based optimization multiple evaluation method. The main purpose of this method is to avoid information loss caused by data loss when reducing data noise, reasonably select communication nodes in opportunistic social network scenarios, optimize data transmission performance, and avoid network congestion. Moreover, our method can effectively identify and exclude potential malicious nodes, reducing the situation that packets are intercepted and discarded. The experiment confirms that the optimized transmission evaluation scheme can effectively reduce routing overheads and energy consumption of a user node, improve the delivery ratio of node data transmission, and ensure the reliability and security of data transmission.
Publisher: MDPI AG
Date: 12-05-2022
DOI: 10.3390/MATH10101665
Abstract: Osteosarcoma is a malignant bone tumor that is extremely dangerous to human health. Not only does it require a large amount of work, it is also a complicated task to outline the lesion area in an image manually, using traditional methods. With the development of computer-aided diagnostic techniques, more and more researchers are focusing on automatic segmentation techniques for osteosarcoma analysis. However, existing methods ignore the size of osteosarcomas, making it difficult to identify and segment smaller tumors. This is very detrimental to the early diagnosis of osteosarcoma. Therefore, this paper proposes a Contextual Axial-Preserving Attention Network (CaPaN)-based MRI image-assisted segmentation method for osteosarcoma detection. Based on the use of Res2Net, a parallel decoder is added to aggregate high-level features which effectively combines the local and global features of osteosarcoma. In addition, channel feature pyramid (CFP) and axial attention (A-RA) mechanisms are used. A lightweight CFP can extract feature mapping and contextual information of different sizes. A-RA uses axial attention to distinguish tumor tissues by mining, which reduces computational costs and thus improves the generalization performance of the model. We conducted experiments using a real dataset provided by the Second Xiangya Affiliated Hospital and the results showed that our proposed method achieves better segmentation results than alternative models. In particular, our method shows significant advantages with respect to small target segmentation. Its precision is about 2% higher than the average values of other models. For the segmentation of small objects, the DSC value of CaPaN is 0.021 higher than that of the commonly used U-Net method.
Publisher: Hindawi Limited
Date: 05-05-2022
DOI: 10.1155/2022/5067849
Abstract: The nodes in the opportunistic network make up communities according to the relevance between them. Some of the structural characteristics of an opportunistic network can be reflected by the structure of the communities that exist in the network. Therefore, finding community from the network is of great significance for people to better study, use, and transform the network. The overlap of communities is considered to be an important feature of communities. Almost all community discovery algorithms were based on nonoverlapping communities in the past. A node in a nonoverlapping community belongs to only one community. However, there are overlapping and interrelated characteristics between communities, so it is not in line with the actual environment of the network. As a result, the previous algorithms have many shortcomings in the face of practical application scenarios, coupled with the limitation of the computing capacity of mobile devices data transmission for low delay and the low energy consumption is difficult to meet the requirements. In the study, we formulate the problem of iding nodes into several communities in the opportunistic social network as how to build communities dynamically according to weight distribution. Then, we propose a modified data delivery strategy based on stochastic block model and community detection (DDBSC). The simulation results show that, compared with other algorithms in the experiments, the strategy proposed in this paper exhibits good performance in terms of overhead, energy consumption, and delivery rate.
Publisher: Hindawi Limited
Date: 28-05-2021
DOI: 10.1155/2021/9928771
Abstract: With the rapid development of 5G era, the number of messages on the network has increased sharply. The traditional opportunistic networks algorithm has some shortcomings in processing data. Most traditional algorithms ide the nodes into communities and then perform data transmission according to the ided communities. However, these algorithms do not consider enough nodes’ characteristics in the communities’ ision, and two positively related nodes may ide into different communities. Therefore, how to accurately ide the community is still a challenging issue. We propose an efficient data transmission strategy for community detection (EDCD) algorithm. When iding communities, we use mobile edge computing to combine network topology attributes with social attributes. When forwarding the message, we select optimal relay node as transmission according to the coefficients of channels. In the simulation experiment, we analyze the efficiency of the algorithm in four different real datasets. The results show that the algorithm has good performance in terms of delivery ratio and routing overhead.
Publisher: Springer Science and Business Media LLC
Date: 21-07-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2021
Publisher: Hindawi Limited
Date: 19-01-2022
DOI: 10.1155/2022/7703583
Abstract: Osteosarcoma is the most common primary malignant bone tumor in children and adolescents. It has a high degree of malignancy and a poor prognosis in developing countries. The doctor manually explained that magnetic resonance imaging (MRI) suffers from subjectivity and fatigue limitations. In addition, the structure, shape, and position of osteosarcoma are complicated, and there is a lot of noise in MRI images. Directly inputting the original data set into the automatic segmentation system will bring noise and cause the model’s segmentation accuracy to decrease. Therefore, this paper proposes an osteosarcoma MRI image segmentation system based on a deep convolution neural network, which solves the overfitting problem caused by noisy data and improves the generalization performance of the model. Firstly, we use Mean Teacher to optimize the data set. The noise data is put into the second round of training of the model to improve the robustness of the model. Then, we segment the image using a deep separable U-shaped network (SepUNet) and conditional random field (CRF). SepUnet can segment lesion regions of different sizes at multiple scales CRF further optimizes the boundary. Finally, this article calculates the area of the tumor area, which provides a more intuitive reference for assisting doctors in diagnosis. More than 80000 MRI images of osteosarcoma from three hospitals in China were tested. The results show that the proposed method guarantees the balance of speed, accuracy, and cost under the premise of improving accuracy.
Publisher: MDPI AG
Date: 30-11-2021
DOI: 10.3390/S21237996
Abstract: In many regions of the world, early diagnosis of non-small cell lung cancer (NSCLC) is a major challenge due to the large population and lack of medical resources, which is difficult toeffectively address via limited physician manpower alone. Therefore, we developed a convolutional neural network (CNN)-based assisted diagnosis and decision-making intelligent medical system with sensors. This system analyzes NSCLC patients’ medical records using sensors to assist staging a diagnosis and provides recommended treatment plans to physicians. To address the problem of unbalanced case s les across pathological stages, we used transfer learning and dynamic s ling techniques to reconstruct and iteratively train the model to improve the accuracy of the prediction system. In this paper, all data for training and testing the system were obtained from the medical records of 2,789,675 patients with NSCLC, which were recorded in three hospitals in China over a five-year period. When the number of case s les reached 8000, the system achieved an accuracy rate of 0.84, which is already close to that of the doctors (accuracy: 0.86). The experimental results proved that the system can quickly and accurately analyze patient data and provide decision information support for physicians.
Publisher: Hindawi Limited
Date: 17-08-2020
DOI: 10.1155/2020/5363549
Abstract: Most developing countries face huge challenges in the medical field scarce medical resources and inadequate medical personnel will affect the development and stability of the society. Therefore, for most developing countries, the development of intelligent medical systems can greatly alleviate the social contradictions arising from this problem. In this study, a new data decision-making intelligent system for prostate cancer based on perceptron neural network is proposed, which mainly makes decisions by associating some relevant disease indicators and combining them with medical images. Through data collection, analysis and integration of medical data, as well as the disease detection and decision-making process, patients are given an auxiliary diagnosis and treatment, so as to solve the problems and social contradictions faced by most developing countries. Through the study of hospitalization information of more than 8,000 prostate patients in three hospitals, about 2,156,528 data items were collected and compiled for experiment purposes. Experimental data shows that when the patient base increases from 200 to 8,000, the accuracy of the machine-assisted diagnostic system will increase from 61% to 87%, and the doctor’s diagnosis rate will be reduced to 81%. From the study, it is concluded that when the patient base reaches a certain number, the diagnostic accuracy of the machine-assisted diagnosis system will exceed the doctor’s expertise. Therefore, intelligent systems can help doctors and medical experts treat patients more effectively.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: MDPI AG
Date: 10-05-1970
DOI: 10.3390/ELECTRONICS10091128
Abstract: With the popularization of 5G communications, the scale of social networks has grown rapidly, and the types of messages have become increasingly complex. The rapid increases in the number of access nodes and the amount of data have put a greater burden on the transmission of information in the networks. However, when transferring data from a large number of users, the performance of traditional opportunistic network routing algorithms is insufficient, which often leads to problems such as high energy consumption, network congestion, and data packet loss. The way in which to improve this transmission environment has become a difficult task. Therefore, in order to ensure the effective transmission of data and reduce network congestion, this paper proposed a link prediction model based on triangular relationships in opportunistic social networks (LPMBT). In the topological structure of the social network, the algorithm scores links based on the frequency of use and selects the optimal relay node based on the score. It can also efficiently track the target node and reconstruct the sub-community. The simulation experimental results showed that the algorithm had excellent performance, effectively reduced overhead, reduced the end-to-end delay, and greatly improved the data transfer rate in the opportunistic network.
Publisher: Springer Science and Business Media LLC
Date: 03-08-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Institution of Engineering and Technology (IET)
Date: 19-10-2021
DOI: 10.1049/CMU2.12283
Publisher: MDPI AG
Date: 07-01-2023
DOI: 10.3390/DIAGNOSTICS13020223
Abstract: Bone malignant tumors are metastatic and aggressive, with poor treatment outcomes and prognosis. Rapid and accurate diagnosis is crucial for limb salvage and increasing the survival rate. There is a lack of research on deep learning to segment bone malignant tumor lesions in medical images with complex backgrounds and blurred boundaries. Therefore, we propose a new intelligent auxiliary framework for the medical image segmentation of bone malignant tumor lesions, which consists of a supervised edge-attention guidance segmentation network (SEAGNET). We design a boundary key points selection module to supervise the learning of edge attention in the model to retain fine-grained edge feature information. We precisely locate malignant tumors by instance segmentation networks while extracting feature maps of tumor lesions in medical images. The rich contextual-dependent information in the feature map is captured by mixed attention to better understand the uncertainty and ambiguity of the boundary, and edge attention learning is used to guide the segmentation network to focus on the fuzzy boundary of the tumor region. We implement extensive experiments on real-world medical data to validate our model. It validates the superiority of our method over the latest segmentation methods, achieving the best performance in terms of the Dice similarity coefficient (0.967), precision (0.968), and accuracy (0.996). The results prove the important contribution of the framework in assisting doctors to improve the accuracy of diagnosis and clinical efficiency.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: No publisher found
Date: 2022
Publisher: MDPI AG
Date: 29-04-2023
DOI: 10.3390/MATH11092116
Abstract: The medical decision-making system is an advanced system for patients that can assist doctors in their medical work. Osteosarcoma is a primary malignant tumor of the bone, due to its specificity, such as its blurred borders, erse tumor morphology, and inconsistent scales. Diagnosis is quite difficult, especially for developing countries, where medical resources are inadequate per capita and there is a lack of professionals, and the time spent in the diagnosis process may lead to a gradual deterioration of the disease. To address these, we discuss an osteosarcoma-assisted diagnosis system (OSADS) based on small s les with multi-scale feature enhancement that can assist doctors in performing preliminary automatic segmentation of osteosarcoma and reduce the workload. We proposed a multi-scale feature enhancement network (MFENet) based on few-shot learning in OSADS. Global and local feature information is extracted to effectively segment the boundaries of osteosarcoma by feeding the images into MFENet. Simultaneously, a prior mask is introduced into the network to help it maintain a certain accuracy range when segmenting different shapes and sizes, saving computational costs. In the experiments, we used 5000 osteosarcoma MRI images provided by Monash University for testing. The experiments show that our proposed method achieves 93.1% accuracy and has the highest comprehensive evaluation index compared with other methods.
Publisher: Hindawi Limited
Date: 18-01-2022
DOI: 10.1155/2022/1489988
Abstract: The spread of seeds of rare and dangerous plants affects the regeneration, pattern, genetic structure, invasion, and settlement of plant populations. However, seed transmission is a relatively weak research link. The spread of plant seeds is not controlled by the communicator. Rather, this event results from the interaction between the host and the external environment determined by the mother. The way plants transmit and accept seeds is similar to how user nodes accept data transmission requests in social networks. Plants select the characteristics including seed size, maturity time, and gene matching, which are consistent with the size, delay, and keywords of the data received by the user. In this study, we selected rare and endangered Pterospermum heterophyllum as the research object and applied them to a social network. All plants were considered nodes and all seeds as transmitted data. This method avoids the influence of errors in actual s ling and statistical laws. By using historical information to record the reception of seeds, the Infection and Immunity Algorithm (IAIA) in opportunistic social networks was established. This method selects healthy plants through plant social populations and reduces the number of diseased plants. The experimental results show that the IAIA algorithm has a good effect in distinguishing dominant seedlings from seedlings with disease genes and realizes the selection of dominant plants in social networks.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2022
Publisher: MDPI AG
Date: 03-08-2020
DOI: 10.3390/SYM12081288
Abstract: Due to the rapid popularization of various short distance communication mobile devices, the use scenarios of opportunistic networks are increasing day by day. However, in opportunistic networks, because of the complexity of community structure, many methods lack of symmetry between application and theoretical research. Thus, the connection strength between nodes is different, and the degree of message diffusion is different. If the above factors cannot be accurately estimated and analyzed, and effective data forwarding and scheduling strategies cannot be formulated, the delivery ratio will be low, the delay will be relatively high, and the network overhead will be large. In light of improving symmetry problems in opportunistic networks, this paper establishes the message duplicate adaptive allocation and spray routing strategy (MDASRS) algorithm model, measures the connection strength between nodes through social pressure, and estimates the diffusion of current messages in the network through the probability of messages leaving the current node successfully, so as to develop the self-adaptive control replication transmission mode and achieve the effect of reducing the network burden and network overhead. This is done through experiments and comparison of social network algorithms, comparing the MDASRS with Epidemic, Spray and Wait, and EIMST algorithms. The experiment results showed that this method improves the cache utilization of nodes, reduces data transmission delay, and improves the network’s overall efficiency.
Publisher: MDPI AG
Date: 06-08-2018
DOI: 10.3390/A11080119
Abstract: The mobility of nodes leads to dynamic changes in topology structure, which makes the traditional routing algorithms of a wireless network difficult to apply to the opportunistic network. In view of the problems existing in the process of information forwarding, this paper proposed a routing algorithm based on the cosine similarity of data packets between nodes (cosSim). The cosine distance, an algorithm for calculating the similarity between text data, is used to calculate the cosine similarity of data packets between nodes. The data packet set of nodes are expressed in the form of vectors, thereby facilitating the calculation of the similarity between the nodes. Through the definition of the upper and lower thresholds, the similarity between the nodes is filtered according to certain rules, and finally obtains a plurality of relatively reliable transmission paths. Simulation experiments show that compared with the traditional opportunistic network routing algorithm, such as the Spray and Wait (S& W) algorithm and Epidemic algorithm, the cosSim algorithm has a better transmission effect, which can not only improve the delivery ratio, but also reduce the network transmission delay and decline the routing overhead.
Publisher: Springer Science and Business Media LLC
Date: 02-2017
Publisher: Hindawi Limited
Date: 06-06-2022
DOI: 10.1155/2022/7973404
Abstract: Osteosarcoma is one of the most common primary malignancies of bone in the pediatric and adolescent populations. The morphology and size of osteosarcoma MRI images often show great variability and randomness with different patients. In developing countries, with large populations and lack of medical resources, it is difficult to effectively address the difficulties of early diagnosis of osteosarcoma with limited physician manpower alone. In addition, with the proposal of precision medicine, existing MRI image segmentation models for osteosarcoma face the challenges of insufficient segmentation accuracy and high resource consumption. Inspired by transformer’s self-attention mechanism, this paper proposes a lightweight osteosarcoma image segmentation architecture, UATransNet, by adding a multilevel guided self-aware attention module (MGAM) to the encoder-decoder architecture of U-Net. We successively perform dataset classification optimization and remove MRI image irrelevant background. Then, UATransNet is designed with transformer self-attention component (TSAC) and global context aggregation component (GCAC) at the bottom of the encoder-decoder architecture to perform integration of local features and global dependencies and aggregation of contexts to learned features. In addition, we apply dense residual learning to the convolution module and combined with multiscale jump connections, to improve the feature extraction capability. In this paper, we experimentally evaluate more than 80,000 osteosarcoma MRI images and show that our UATransNet yields more accurate segmentation performance. The IOU and DSC values of osteosarcoma are 0.922 ± 0.03 and 0.921 ± 0.04, respectively, and provide intuitive and accurate efficient decision information support for physicians.
Publisher: MDPI AG
Date: 17-09-2018
DOI: 10.3390/S18093140
Abstract: Mobile Edge Computing (MEC) has evolved into a promising technology that can relieve computing pressure on wireless devices (WDs) in the Internet of Things (IoT) by offloading computation tasks to the MEC server. Resource management and allocation are challenging because of the unpredictability of task arrival, wireless channel status and energy consumption. To address such a challenge, in this paper, we provide an energy-efficient joint resource management and allocation (ECM-RMA) policy to reduce time-averaged energy consumption in a multi-user multi-task MEC system with hybrid energy harvested WDs. We first formulate the time-averaged energy consumption minimization problem while the MEC system satisfied both the data queue stability constraint and energy queue stability constraint. To solve the stochastic optimization problem, we turn the problem into two deterministic sub-problems, which can be easily solved by convex optimization technique and linear programming technique. Correspondingly, we propose the ECM-RMA algorithm that does not require priori knowledge of stochastic processes such as channel states, data arrivals and green energy harvesting. Most importantly, the proposed algorithm achieves the energy consumption-delay trade-off as [ O ( 1 / V ) , O ( V ) ] . V, as a non-negative weight, which can effectively control the energy consumption-delay performance. Finally, simulation results verify the correctness of the theoretical analysis and the effectiveness of the proposed algorithm.
Publisher: Springer Science and Business Media LLC
Date: 31-10-2018
Publisher: Institution of Engineering and Technology (IET)
Date: 15-07-2022
DOI: 10.1049/CMU2.12458
Publisher: Hindawi Limited
Date: 10-05-2022
DOI: 10.1155/2022/4601696
Abstract: Assessing the extent of cancer spread by histopathological analysis of sentinel axillary lymph nodes is an important part of breast cancer staging. With the maturity and prevalence of deep learning technology, building auxiliary medical systems can help to relieve the burden of pathologists and increase the diagnostic precision and accuracy during this process. However, such histopathological images have complex patterns that are difficult for ordinary people to understand and require professional medical practitioners to annotate. This increases the cost of constructing such medical systems. To reduce the cost of annotating and improve the performance of the model as much as possible, in other words, using as few labeled s les as possible to obtain a greater performance improvement, we propose a deep learning framework with a three-stage query strategy and novel model update strategy. The framework first trains an auto-encoder with all the s les to obtain a global representation in a low-dimensional space. In the query stage, the unlabeled s les are first selected according to uncertainty, and then, coreset-based methods are employed to reduce s le redundancy. Finally, distribution differences between labeled s les and unlabeled s les are evaluated and s les that can quickly eliminate the distribution differences are selected. This method achieves faster iterative efficiency than the uncertainty strategies, representative strategies, or hybrid strategies on the lymph node slice dataset and other commonly used datasets. It reaches the performance of training with all data, but only uses 50% of the labeled. During the model update process, we randomly freeze some weights and only train the task model on new labeled s les with a smaller learning rate. Compared with fine-tuning task model on new s les, large-scale performance degradation is avoided. Compared with the retraining strategy or the replay strategy, it reduces the training cost of updating the task model by 79.87% and 90.07%, respectively.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2021
Publisher: MDPI AG
Date: 10-05-2018
DOI: 10.3390/SYM10050152
Publisher: MDPI AG
Date: 04-02-2019
DOI: 10.3390/INFO10020049
Abstract: Due to the dynamic change of the opportunistic network topology and the lack of stable information transmission paths between nodes, the traditional topology-based routing algorithm cannot achieve the desired routing performance. To address of this problem, this paper proposes a routing algorithm based on trajectory prediction (RATP). The routing protocol based on trajectory prediction can efficiently and quickly adapt to the network link quality instability and the dynamic changes of network topology. RATP algorithm constructs a node mobility model by analyzing the historical mobility characteristics of the nodes. According to the node prediction information, the metric value of the candidate node is calculated, and the node with the smaller metric value is selected as the data forwarding node, which can effectively reduce the packet loss rate and avoids excessive consumption. Simulation results show that compared with other algorithms, the proposed algorithm has higher data delivery ratio, and end-to-end data delay and routing overhead are significantly reduced.
Publisher: Springer Science and Business Media LLC
Date: 16-04-2018
Publisher: MDPI AG
Date: 02-07-2021
DOI: 10.3390/ELECTRONICS10131595
Abstract: With the fast development of IoT and 5G technologies, opportunity social networks composed of portable mobile devices have become a hot research topic in recent years. However, arbitrary node movement in opportunity networks and the absence of end-to-end pathways make node communication unstable. At the same time, the problem of ignoring human social preferences and relying on wrong message relay nodes lead to a low data transmission rate and high network overhead. Based on the above issues, we propose a time-varying relationship groups-based routing query algorithm for mobile opportunity networks (Time-varying Relationship Groups, TVRGs). Firstly, we construct the relationship groups based on the time-varying characteristics according to the intimacy between users. Secondly, we calculate the importance of nodes by their connectivity time and communication frequency. Finally, we find the suitable message relay nodes according to the similarity of node weights and their action trajectories and design the routing query algorithm accordingly. The simulation results show that the algorithm can vastly improve the message query success rate, effectively improve the data transmission efficiency, and reduce the average delay and system overhead compared with the existing routing algorithms.
Publisher: Springer Singapore
Date: 2017
Publisher: MDPI AG
Date: 14-08-2018
DOI: 10.3390/A11080125
Abstract: With the popularization of mobile communication equipment, human activities have an increasing impact on the structure of networks, and so the social characteristics of opportunistic networks become increasingly obvious. Opportunistic networks are increasingly used in social situations. However, existing routing algorithms are not suitable for opportunistic social networks, because traditional opportunistic network routing does not consider participation in human activities, which usually causes a high ratio of transmission delay and routing overhead. Therefore, this research proposes an effective data transmission algorithm based on social relationships (ESR), which considers the community characteristics of opportunistic mobile social networks. This work uses the idea of the faction to ide the nodes in the network into communities, reduces the number of inefficient nodes in the community, and performs another contraction of the structure. Simulation results show that the ESR algorithm, through community transmission, is not only faster and safer, but also has lower transmission delay and routing overhead compared with the spray and wait algorithm, SCR algorithm and the EMIST algorithm.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Hindawi Limited
Date: 11-02-2020
DOI: 10.1155/2020/3576542
Abstract: With the advent of 5G communication standards, the number of 5G base stations increases steadily, and the number of mobile terminals and IoT (Internet of Things) devices increases sharply, which sharps a large number of IoT devices and forms a complex network. These devices can take as nodes of a community in the opportunistic social network. However, in the environment of traditional opportunistic network algorithm and mass data transmission, information transmission is only carried out at several source nodes in the community, which usually leads to transmission delay, excessive energy consumption, and source node death. Therefore, we propose an effective data delivery based on the multiperceived domain algorithm, which recombines communities based on the correlation degree of nodes, and new communities assist source nodes to transmit information in solving these problems. The comparison between the experiment and the classical opportunistic network algorithm shows that the method has outstanding performance in reducing the resource consumption of data transmission and improving the efficiency of information transmission.
Publisher: Wiley
Date: 02-11-2021
DOI: 10.1002/ETT.4389
Abstract: The introduction of the 5G Internet and big data communication into human society underpins the opportunistic social networks (OSNs) to survive. The storage‐carry‐forward mechanism refers to a data transmission strategy of OSNs, seeking any data transmission opportunities to communicate in the mobile process. Accordingly, identifying influential nodes is considered critical to OSNs and an essential prerequisite for developing efficient collaborative transmission algorithms. According to conventional OSNs, however, the node identification methods exhibit several defects (eg, low recognition accuracy, high time complexity, and poor performance in complexity networks). To address the mentioned defects, this study builds a relationship matrix resolving model to identify vital nodes by complying with community, which is capable of effectively identifying influential nodes in the network. The proposed model iterates by drawing upon the community features in the network to yield the optimal solution that satisfies the set condition, that is, the influential nodes in the community. As revealed from the experimental results, the method exhibits high performance.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Institution of Engineering and Technology (IET)
Date: 26-09-2023
DOI: 10.1049/IPR2.12941
Publisher: Elsevier BV
Date: 06-2018
DOI: 10.1016/J.CMPB.2018.03.004
Abstract: Non-small cell lung cancer (NSCLC) is a high risk cancer and is usually scanned by PET-CT for testing, predicting and then give the treatment methods. However, in the actual hospital system, at least 640 images must be generated for each patient through PET-CT scanning. Especially in developing countries, a huge number of patients in NSCLC are attended by doctors. Artificial system can predict and make decision rapidly. According to explore and research artificial medical system, the selection of artificial observations also can result in low work efficiency for doctors. In this study, data information of 2,789,675 patients in three hospitals in China are collected, compiled, and used as the research basis these data are obtained through image acquisition and diagnostic parameter machine decision-making method on the basis of the machine diagnosis and medical system design model of adjuvant therapy. By combining image and diagnostic parameters, the machine decision diagnosis auxiliary algorithm is established. Experimental result shows that the accuracy has reached 77% in NSCLC.
Publisher: Springer Singapore
Date: 2017
Publisher: MDPI AG
Date: 18-11-2022
DOI: 10.3390/HEALTHCARE10112313
Abstract: Osteosarcoma is a malignant tumor derived from primitive osteogenic mesenchymal cells, which is extremely harmful to the human body and has a high mortality rate. Early diagnosis and treatment of this disease is necessary to improve the survival rate of patients, and MRI is an effective tool for detecting osteosarcoma. However, due to the complex structure and variable location of osteosarcoma, cancer cells are highly heterogeneous and prone to aggregation and overlap, making it easy for doctors to inaccurately predict the area of the lesion. In addition, in developing countries lacking professional medical systems, doctors need to examine mass of osteosarcoma MRI images of patients, which is time-consuming and inefficient, and may result in misjudgment and omission. For the sake of reducing labor cost and improve detection efficiency, this paper proposes an Attention Condenser-based MRI image segmentation system for osteosarcoma (OMSAS), which can help physicians quickly locate the lesion area and achieve accurate segmentation of the osteosarcoma tumor region. Using the idea of AttendSeg, we constructed an Attention Condenser-based residual structure network (ACRNet), which greatly reduces the complexity of the structure and enables smaller hardware requirements while ensuring the accuracy of image segmentation. The model was tested on more than 4000 s les from two hospitals in China. The experimental results demonstrate that our model has higher efficiency, higher accuracy and lighter structure for osteosarcoma MRI image segmentation compared to other existing models.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2021
Publisher: MDPI AG
Date: 07-11-2017
DOI: 10.3390/INFO8040140
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2022
Publisher: Springer Science and Business Media LLC
Date: 27-12-2018
Publisher: Institution of Engineering and Technology (IET)
Date: 18-05-2023
DOI: 10.1049/CMU2.12628
Abstract: The network transmission speed has been greatly improved, thanks to the power of 5G technology. The millisecond‐level communication delay has made a qualitative leap in communication quality. However, the sharp increase in the number of nodes connected to the internet has resulted in an explosion of traffic. Ensuring stable network transmission in the face of large data volumes has become an urgent problem to be solved. Existing research mainly optimizes for low data volumes of nodes, and cannot dynamically adapt to node transmission load to cope with explosive growth. This is because the node's cache is always at a high level, which causes community communication to be blocked. To address this issue, the authors have designed an effective data communication community establishment scheme. By adding a data information flow (DIF) attribute to each user and using the dynamic feedback adjustment (DFA) mechanism, the authors can combine the entire communication community and control the user's data information flow concentration at a relatively low level. This degree of optimization ensures that the user node maintains a relatively stable state for fast communication. The authors design an effective data communication community establishment scheme. By adding a data information flow (DIF) attribute to each user, using the dynamic feedback adjustment mechanism and combining the entire communication community, the user's data information flow concentration is controlled at a relatively low level.
Publisher: Hindawi Limited
Date: 30-07-2022
DOI: 10.1155/2022/3881833
Abstract: Osteosarcoma is one of the most common bone tumors that occurs in adolescents. Doctors often use magnetic resonance imaging (MRI) through biosensors to diagnose and predict osteosarcoma. However, a number of osteosarcoma MRI images have the problem of the tumor shape boundary being vague, complex, or irregular, which causes doctors to encounter difficulties in diagnosis and also makes some deep learning methods lose segmentation details as well as fail to locate the region of the osteosarcoma. In this article, we propose a novel boundary-aware grid contextual attention net (BA-GCA Net) to solve the problem of insufficient accuracy in osteosarcoma MRI image segmentation. First, a novel grid contextual attention (GCA) is designed to better capture the texture details of the tumor area. Then the statistical texture learning block (STLB) and the spatial transformer block (STB) are integrated into the network to improve its ability to extract statistical texture features and locate tumor areas. Over 80,000 MRI images of osteosarcoma from the Second Xiangya Hospital are adopted as a dataset for training, testing, and ablation studies. Results show that our proposed method achieves higher segmentation accuracy than existing methods with only a slight increase in the number of parameters and computational complexity.
Publisher: Hindawi Limited
Date: 08-06-2020
DOI: 10.1155/2020/3721579
Abstract: In opportunistic complex networks, information transmission between nodes is inevitable through broadcast. The purpose of broadcasting is to distribute data from source nodes to all nodes in the network. In opportunistic complex networks, it is mainly used for routing discovery and releasing important notifications. However, when a large number of nodes in the opportunistic complex networks are transmitting information at the same time, signal interference will inevitably occur. Therefore, we propose a low-latency broadcast algorithm for opportunistic complex networks based on successive interference cancellation techniques to improve propagation delay. With this kind of algorithm, when the social network is broadcasting, this algorithm analyzes whether the conditions for successive interference cancellation are satisfied between the broadcast links on the assigned transmission time slice. If the conditions are met, they are scheduled at the same time slice, and interference avoidance scheduling is performed when conditions are not met. Through comparison experiments with other classic algorithms of opportunistic complex networks, this method has outstanding performance in reducing energy consumption and improving information transmission efficiency.
Publisher: Springer Science and Business Media LLC
Date: 25-07-2018
Publisher: Springer Science and Business Media LLC
Date: 11-09-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2022
Publisher: Korean Society for Internet Information (KSII)
Date: 31-03-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2017
Publisher: Hindawi Limited
Date: 14-11-2022
DOI: 10.1155/2022/9990092
Abstract: One of the most prevalent malignant bone tumors is osteosarcoma. The diagnosis and treatment cycle are long and the prognosis is poor. It takes a lot of time to manually identify osteosarcoma from osteosarcoma magnetic resonance imaging (MRI). Medical image processing technology has greatly alleviated the problems faced by medical diagnoses. However, MRI images of osteosarcoma are characterized by high noise and blurred edges. The complex features increase the difficulty of lesion area identification. Therefore, this study proposes an osteosarcoma MRI image segmentation method (OSTransnet) based on Transformer and U-net. This technique primarily addresses the issues of fuzzy tumor edge segmentation and overfitting brought on by data noise. First, we optimize the dataset by changing the precise spatial distribution of noise and the data-increment image rotation process. The tumor is then segmented based on the model of U-Net and Transformer with edge improvement. It compensates for the limitations of U-semantic Net by using channel-based transformers. Finally, we also add an edge enhancement module (BAB) and a combined loss function to improve the performance of edge segmentation. The method’s accuracy and stability are demonstrated by the detection and training results based on more than 4,000 MRI images of osteosarcoma, which also demonstrate how well the method works as an adjunct to clinical diagnosis and treatment.
Publisher: Springer Science and Business Media LLC
Date: 03-01-2022
Publisher: MDPI AG
Date: 07-08-2020
DOI: 10.3390/ELECTRONICS9081271
Abstract: 5G has brought a huge increase in data, and the number of nodes and types of messages are becoming more and more complex. The Internet of things has become a large and complex network. More and more devices can be used as nodes in opportunistic social networks. The attitude of nodes to messages is different and changeable. However, in the previous opportunistic network algorithm and mass data transmission environment, due to the lack of effective information selection and management means, it was easy to lead to transmission delay and high consumption. Therefore, we propose Effective Data Selection and Management (EDSM). EDSM uses the current state of the node as the basis for forwarding messages. When the cache space is insufficient, EDSM will perform cache replacement based on the message cache value and delete the information with the lowest cache value. Simulation results show that the algorithm has good performance in terms of delivery rate and latency.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2022
Publisher: MDPI AG
Date: 04-08-2022
DOI: 10.3390/HEALTHCARE10081468
Abstract: Osteosarcoma is a bone tumor which is malignant. There are many difficulties when doctors manually identify patients’ MRI images to complete the diagnosis. The osteosarcoma in MRI images is very complex, making its recognition and segmentation resource-consuming. Automatic osteosarcoma area segmentation can solve these problems to a certain extent. However, existing studies usually fail to balance segmentation accuracy and efficiency. They are either sensitive to noise with low accuracy or time-consuming. So we propose an auxiliary segmentation method based on denoising and local enhancement. The method first optimizes the osteosarcoma images, including removing noise using the Edge Enhancement based Transformer for Medical Image Denoising (Eformer) and using a non-parameter method to localize and enhance the tumor region in MRI images. Osteosarcoma was then segmented by Deep Feature Aggregation for Real-Time Semantic Segmentation (DFANet). Our method achieves impressive segmentation accuracy. Moreover, it is efficient in both time and space. It can provide information about the location and extent of the osteosarcoma as a basis for further diagnosis.
Publisher: Elsevier BV
Date: 12-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Elsevier BV
Date: 06-2019
DOI: 10.1016/J.COMPBIOMED.2019.04.021
Abstract: The uneven distribution of medical resources is a serious problem in developing countries. Those seeking timely treatment have difficulty choosing the right hospital. To found sustainable development with medical system, this paper establishes a model of the hospital confidence evaluation index by combining national evaluation and a third-party evaluation. The model is applied to a social network. Users from any region can use the model through APP in IoT, a hospital analysis index query, which selects the best hospital for diagnosis and treatment. The model can locate different personnel characteristics by modifying the control variables. Establishing a medical system with big data provides good model characteristics. Effective data analysis through large data users in the s le is established to provide the most effective hospital recommendation, which is a good solution to the selectivity problem. The contributions in this works are: (1) Models of initial trust and hospital evaluations are established by combining national and third-party assessments (2) the initial trust evaluation model is modified and optimized by establishing control variables (3) the trust evaluation mechanism of users in social networks is obtained through big data s ling and model analysis, and the balanced distribution of the medical staff is realized.
Publisher: Hindawi Limited
Date: 03-08-2022
DOI: 10.1155/2022/7285600
Abstract: Among primary bone cancers, osteosarcoma is the most common, peaking between the ages of a child’s rapid bone growth and adolescence. The diagnosis of osteosarcoma requires observing the radiological appearance of the infected bones. A common approach is MRI, but the manual diagnosis of MRI images is prone to observer bias and inaccuracy and is rather time consuming. The MRI images of osteosarcoma contain semantic messages in several different resolutions, which are often ignored by current segmentation techniques, leading to low generalizability and accuracy. In the meantime, the boundaries between osteosarcoma and bones or other tissues are sometimes too ambiguous to separate, making it a challenging job for inexperienced doctors to draw a line between them. In this paper, we propose using a multiscale residual fusion network to handle the MRI images. We placed a novel subnetwork after the encoders to exchange information between the feature maps of different resolutions, to fuse the information they contain. The outputs are then directed to both the decoders and a shape flow block, used for improving the spatial accuracy of the segmentation map. We tested over 80,000 osteosarcoma MRI images from the PET-CT center of a well-known hospital in China. Our approach can significantly improve the effectiveness of the semantic segmentation of osteosarcoma images. Our method has higher F1, DSC, and IOU compared with other models while maintaining the number of parameters and FLOPS.
Publisher: MDPI AG
Date: 13-08-2018
DOI: 10.3390/SYM10080338
Abstract: At the dawn of big data and 5G networks, end-to-end communication with large amounts of data between mobile devices is difficult to be implemented through the traditional face-to-face transmission mechanism in social networks. Consequently, opportunistic social networks proposed that message applications should choose proper relay nodes to perform effective data transmission processes. At present, several routing algorithms, based on node similarity, attempt to use the contextual information related to nodes and the special relationships between them to select a suitable relay node among neighbors. However, when evaluating the similarity degree between a pair of nodes, most existing algorithms in opportunistic social networks pay attention to only a few similar factors, and even ignore the importance of mobile similarity in the data transmission process. To improve the transmission environment, this study establishes a fuzzy routing-forwarding algorithm (FCNS) exploiting comprehensive node similarity (the mobile and social similarities) in opportunistic social networks. In our proposed scheme, the transmission preference of the node is determined through the fuzzy evaluation of mobile and social similarities. The suitable message delivery decision is made by collecting and comparing the transmission preference of nodes, and the sustainable and stable data transmission process is performed through the feedback mechanism. Through simulations and the comparison of social network algorithms, the delivery ratio in the proposed algorithm is 0.85 on average, and the routing delay and network overhead of this algorithm are always the lowest.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: MDPI AG
Date: 11-05-2021
DOI: 10.3390/ELECTRONICS10101138
Abstract: With the rapid popularization of 5G communication and internet of things technologies, the amount of information has increased significantly in opportunistic social networks, and the types of messages have become more and more complex. More and more mobile devices join the network as nodes, making the network scale increase sharply, and the tremendous amount of datatransmission brings a more significant burden to the network. Traditional opportunistic social network routing algorithms lack effective message copy management and relay node selection methods, which will cause problems such as high network delay and insufficient cache space. Thus, we propose an opportunistic social network routing algorithm based on user-adaptive data transmission. The algorithm will combine the similarity factor, communication factor, and transmission factor of the nodes in the opportunistic social network and use information entropy theory to adaptively assign the weights of decision feature attributes in response to network changes. Also, edge nodes are effectively used, and the nodes are ided into multiple communities to reconstruct the community structure. The simulation results show that the algorithm demonstrates good performance in improving the information transmission’s success rate, reducing network delay, and caching overhead.
Publisher: Elsevier BV
Date: 11-2021
Publisher: Springer Science and Business Media LLC
Date: 17-02-2018
Publisher: MDPI AG
Date: 10-10-2023
Publisher: MDPI AG
Date: 16-06-2022
DOI: 10.3390/MATH10122099
Abstract: Osteosarcoma is a malignant osteosarcoma that is extremely harmful to human health. Magnetic resonance imaging (MRI) technology is one of the commonly used methods for the imaging examination of osteosarcoma. Due to the large amount of osteosarcoma MRI image data and the complexity of detection, manual identification of osteosarcoma in MRI images is a time-consuming and labor-intensive task for doctors, and it is highly subjective, which can easily lead to missed and misdiagnosed problems. AI medical image-assisted diagnosis alleviates this problem. However, the brightness of MRI images and the multi-scale of osteosarcoma make existing studies still face great challenges in the identification of tumor boundaries. Based on this, this study proposed a prior guidance-based assisted segmentation method for MRI images of osteosarcoma, which is based on the few-shot technique for tumor segmentation and fine fitting. It not only solves the problem of multi-scale tumor localization, but also greatly improves the recognition accuracy of tumor boundaries. First, we preprocessed the MRI images using prior generation and normalization algorithms to reduce model performance degradation caused by irrelevant regions and high-level features. Then, we used a prior-guided feature abdominal muscle network to perform small-s le segmentation of tumors of different sizes based on features in the processed MRI images. Finally, using more than 80,000 MRI images from the Second Xiangya Hospital for experiments, the DOU value of the method proposed in this paper reached 0.945, which is at least 4.3% higher than other models in the experiment. We showed that our method specifically has higher prediction accuracy and lower resource consumption.
Publisher: MDPI AG
Date: 10-03-2023
DOI: 10.3390/DIAGNOSTICS13061063
Abstract: Bone malignant tumors are metastatic and aggressive. The manual screening of medical images is time-consuming and laborious, and computer technology is now being introduced to aid in diagnosis. Due to a large amount of noise and blurred lesion edges in osteosarcoma MRI images, high-precision segmentation methods require large computational resources and are difficult to use in developing countries with limited conditions. Therefore, this study proposes an artificial intelligence-aided diagnosis scheme by enhancing image edge features. First, a threshold screening filter (TSF) was used to pre-screen the MRI images to filter redundant data. Then, a fast NLM algorithm was introduced for denoising. Finally, a segmentation method with edge enhancement (TBNet) was designed to segment the pre-processed images by fusing Transformer based on the UNet network. TBNet is based on skip-free connected U-Net and includes a channel-edge cross-fusion transformer and a segmentation method with a combined loss function. This solution optimizes diagnostic efficiency and solves the segmentation problem of blurred edges, providing more help and reference for doctors to diagnose osteosarcoma. The results based on more than 4000 osteosarcoma MRI images show that our proposed method has a good segmentation effect and performance, with Dice Similarity Coefficient (DSC) reaching 0.949, and show that other evaluation indexes such as Intersection of Union (IOU) and recall are better than other methods.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Location: Australia
No related grants have been discovered for Jia WU.