Abnormal Nodes Research Articles

Axillary lymph node recurrence following wire-directed sentinel lymph node dissection for breast cancer patients with biopsy-proven axillary metastases prior to neoadjuvant chemotherapy at a safety net medical center.

Although sentinel lymph node dissection (SLND) after neoadjuvant chemotherapy (NAC) is feasible, axillary management for patients with pretreatment biopsy-proven axillary metastases and who are clinically node-negative after NAC (ycN0) remains unclear. This retrospective study was performed to determine the rate of axillary lymph node recurrence for such patients who had wire-directed (WD) SLND. Patients treated with NAC from 2015 to 2020 had axillary nodes evaluated by pretreatment ultrasound. Core biopsies were done on abnormal nodes, and microclips were placed in nodes during biopsy. For patients with biopsy-proven node metastases who received NAC and were ycN0 by clinical exam, WD SLND was done. Patients with negative nodes on frozen section had WD SLND alone; those with positive nodes had WD SLND plus axillary lymph node dissection (ALND). Of 179 patients receiving NAC, 62 were biopsy-proven node-positive pre-NAC and ycN0 post-NAC. Thirty-five (56%) patients were node-negative on frozen section and had WD SLND alone. Twenty-seven (43%) patients had WD SLND + ALND. Forty-seven patients had postoperative regional node irradiation. With median follow-up of 40 months, there were recurrences in 4 (11%) of 35 patients having WD SLND and 5 (19%) of 27 having WD SLND + ALND, but there was only one axillary lymph node recurrence, identified by CT scan. Axillary node recurrence was very uncommon after WD SLND for patients who had pretreatment biopsy-proven node metastases and were ypN0 after NAC. These patients would be unlikely to derive clinical benefit from the addition of completion ALND to SLND.

Construction of an individualized brain metabolic network in patients with advanced non-small cell lung cancer by the Kullback-Leibler divergence-based similarity method: A study based on 18F-fluorodeoxyglucose positron emission tomography.

Lung cancer has one of the highest mortality rates of all cancers, and non-small cell lung cancer (NSCLC) accounts for the vast majority (about 85%) of lung cancers. Psychological and cognitive abnormalities are common in cancer patients, and cancer information can affect brain function and structure through various pathways. To observe abnormal brain function in NSCLC patients, the main purpose of this study was to construct an individualized metabolic brain network of patients with advanced NSCLC using the Kullback-Leibler divergence-based similarity (KLS) method. This study included 78 patients with pathologically proven advanced NSCLC and 60 healthy individuals, brain 18F-FDG PET images of these individuals were collected and all patients with advanced NSCLC were followed up (>1 year) to confirm their overall survival. FDG-PET images were subjected to individual KLS metabolic network construction and Graph theoretical analysis. According to the analysis results, a predictive model was constructed by machine learning to predict the overall survival of NSLCL patients, and the correlation with the real survival was calculated. Significant differences in the degree and betweenness distributions of brain network nodes between the NSCLC and control groups (p<0.05) were found. Compared to the normal group, patients with advanced NSCLC showed abnormal brain network connections and nodes in the temporal lobe, frontal lobe, and limbic system. The prediction model constructed using the abnormal brain network as a feature predicted the overall survival time and the actual survival time fitting with statistical significance (r=0.42, p=0.012). An individualized brain metabolic network of patients with NSCLC was constructed using the KLS method, thereby providing more clinical information to guide further clinical treatment.

A relatively high proportion of dogs with small apocrine gland anal sac adenocarcinoma (AGASACA) primary tumours present with locoregional lymph node metastasis.

Apocrine gland anal sac adenocarcinoma (AGASACA) is a highly relevant disease in dogs, with a high rate of lymph node (LN) metastasis during the course of disease. A recent study showed that risk for death and disease progression was significantly associated with primary tumour size less than 2 and 1.3cm, respectively. The objective of this study was to report the proportion of dogs that have primary tumours less than 2cm in diameter, that are diagnosed with LN metastasis at presentation. This was a single site retrospective study of dogs that underwent treatment for AGASACA. Dogs were included if physical examination primary tumour measurements were available, abdominal staging was performed, and confirmation of abnormal lymph nodes by cytology or histology was done. Over a 5-year period, 116 dogs were included for review with 53 (46%) having metastatic LN at presentation. The metastatic rate for dogs with primary tumours <2cm was 20% (9 of 46 dogs) compared to 63% (44 of 70 dogs) in dogs with primary tumours ≥2cm. The association between tumour size group (<2 vs. ≥2cm) and the presence of metastasis at presentation was significant (P < .0001) with an OR of 7.0 (95% CI: 2.9-15.7). Primary tumour size was significantly associated with LN metastasis at presentation but the proportion of dogs that presented with LN metastasis in the <2cm group was relatively high. This data suggests that dogs with small tumours may still have aggressive tumour biology.

EAGLE: Contrastive Learning for Efficient Graph Anomaly Detection

Graph anomaly detection is a popular and vital task in various real-world scenarios, which has been studied for several decades. Recently, many studies extending deep learning-based methods have shown preferable performance on graph anomaly detection. However, existing methods are lack of efficiency that is definitely necessary for embedded devices. Towards this end, we propose an Efficient Anomaly detection model on heterogeneous Graphs via contrastive LEarning (EAGLE) by contrasting abnormal nodes with normal ones in terms of their distances to the local context. The proposed method first samples instance pairs on meta path-level for contrastive learning. Then, a graph autoencoder-based model is applied to learn informative node embeddings in an unsupervised way, which will be further combined with the discriminator to predict the anomaly scores of nodes. Experimental results show that EAGLE outperforms the state-of-the-art methods on three heterogeneous network datasets.

Abnormal nodes sensing model in regional wireless networks based on convolutional neural network

AbstractThere are some problems in abnormal node sensing in regional wireless networks, such as low sensing accuracy and poor judgment results of abnormal states of sensing nodes. Therefore, this paper develops a method for abnormal node sensing in regional wireless networks based on convolutional neural network. In addition, we will analyze the structure of regional wireless network nodes and determine the distribution mode of wireless network nodes. The regional wireless network node data are extracted and the pivot quantity and two-dimensional Gaussian distribution state are constructed using the median to build the regional wireless network node deployment model according to the confidence interval of the data characteristics; analyze the basic principle of convolution neural network, determine the operation mode of convolution kernel, classify the regional wireless network node data using Bayesian network, set a safety distance to determine the abnormal node of the regional wireless network, train the determined abnormal data as the input data of convolutional neural network and input it into the constructed perception model of the abnormal node of the regional wireless network, the loss function is set to continuously update the iterative results to realize the perception of abnormal node in the regional wireless network. The simulation results show that the sensing range of this method is relatively consistent with the range set by the sample, and the sensing accuracy reaches more than 95%, and the abnormal state error of abnormal nodes in the evaluation sample area is always less than 2%, which verifies that this method improves the sensing accuracy, reduces the error, and has higher application value.

Persons with HIV Develop Spike-Specific Lymph Node Germinal Center Responses following SARS-CoV-2 Vaccination.

COVID-19 disproportionately affects persons with HIV (PWH) in worldwide locations with limited access to SARS-CoV-2 vaccines. PWH exhibit impaired immune responses to some, but not all, vaccines. Lymph node (LN) biopsies from PWH demonstrate abnormal LN structure, including dysregulated germinal center (GC) architecture. It is not clear whether LN dysregulation prevents PWH from mounting Ag-specific GC responses in the draining LN following vaccination. To address this issue, we longitudinally collected blood and draining LN fine needle aspiration samples before and after SARS-CoV-2 vaccination from a prospective, observational cohort of 11 PWH on antiretroviral therapy: 2 who received a two-dose mRNA vaccine series and 9 who received a single dose of the Ad26.COV2.S vaccine. Following vaccination, we observed spike-specific Abs, spike-specific B and T cells in the blood, and spike-specific GC B cell and T follicular helper cell responses in the LN of both mRNA vaccine recipients. We detected spike-specific Abs in the blood of all Ad26.COV2.S recipients, and one of six sampled Ad26.COV2.S recipients developed a detectable spike-specific GC B and T follicular helper cell response in the draining LN. Our data show that PWH can mount Ag-specific GC immune responses in the draining LN following SARS-CoV-2 vaccination. Due to the small and diverse nature of this cohort and the limited number of available controls, we are unable to elucidate all potential factors contributing to the infrequent vaccine-induced GC response observed in the Ad26.COV2.S recipients. Our preliminary findings suggest this is a necessary area of future research.

DOIDS: An Intrusion Detection Scheme Based on DBSCAN for Opportunistic Routing in Underwater Wireless Sensor Networks.

In Underwater Wireless Sensor Networks (UWSNs), data should be transmitted to data centers reliably and efficiently. However, due to the harsh channel conditions, reliable data transmission is a challenge for large-scale UWSNs. Thus, opportunistic routing (OR) protocols with high reliability, strong robustness, low end-to-end delay, and high energy efficiency are widely applied. However, OR in UWSNs is vulnerable to routing attacks. For example, sinkhole attack nodes can attract traffic from surrounding nodes by forging information such as the distance to the sink node. In order to reduce the negative impact of malicious nodes on data transmission, we propose an intrusion detection scheme (IDS) based on the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering algorithm for OR (DOIDS) in this paper. DOIDS is based on small-sample IDS and is suitable for UWSNs with sparse node deployment. In DOIDS, the local monitoring mechanism is adopted. Every node in the network running DOIDS can select the trusted next hop. Firstly, according to the behavior characteristics of common routing attack nodes and unreliable underwater acoustic channel characteristics, DOIDS selected the energy consumption, forwarding, and link quality information of candidate nodes as the detection feature values. Then, the collected feature information is used to detect potential abnormal nodes through the DBSCAN clustering algorithm. Finally, a decision function is defined according to the time decay function to reduce the false detection rate of DOIDS. It makes a final judgment on whether the potential abnormal node is malicious. The simulation results show that the algorithm can effectively improve the detection accuracy rate (3% to 15% for different scenarios) and reduce the false positive rate, respectively.

Selection of patients with symptomatic vagal-induced sinus node dysfunction: Who will be the best candidate for cardioneuroablation?

Sinus node dysfunction is a multifaceted disorder with variable manifestations, the prevalence of which increases with age. In a specific group of patients, excessive vagal activity may be the sole cause for this condition. These patients are characterized as having recurrent daytime symptoms attributed to bradyarrhythmia, no evidence of organic sinus node lesions, cardiac vagal overactivation, and are non-elderly. For sinus node dysfunction patients, a permanent pacemaker implantation appears to be the ultimate solution, although it is not an etiological treatment. Cardioneuroablation is a promising emerging therapy that can fundamentally eliminate symptoms in a highly selective sub-set of sinus node dysfunction patients by cardiac vagal nerve denervation. Denervation with ablation for vagal-induced sinus node dysfunction can effectively improve sinus bradycardia and reduce syncope. To date, guidelines for selection of suitable candidates for cardioneuroablation remain lacking. The primary objective of this study was to distinguish the nature of abnormal sinus node function and to find methods for quantifying vagal tone. Clear selection criteria could help physicians in identification of patients with autonomic imbalance, thereby maximizing patient benefits and the success rate of cardioneuroablations.

Added Value of Abnormal Lymph Nodes Detected with FDG-PET/CT in Suspected Vascular Graft Infection

Vascular graft and endograft infections (VGEI) cause a serious morbidity and mortality burden. 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) imaging is frequently used in the diagnostic workup, but the additional value of abnormal (18F-FDG active and/or enlarged) locoregional lymph nodes is unknown. In this retrospective study, the additional diagnostic value of abnormal locoregional lymph nodes on 18F-FDG PET/CT imaging for VGEI was evaluated, including 54 patients with a culture-proven VGEI (defined according to the Management of Aortic Graft Infection [MAGIC] group classification) and 25 patients without VGEI. 18F-FDG PET/CT was qualitatively and quantitatively assessed for tracer uptake and pattern at the location of the vascular graft, and locoregional lymph node uptake and enlargement (>10 mm). 18F-FDG uptake intensity and pattern independently predicted the presence of VGEI by logistic regression (Χ2: 46.19, p < 0.001), with an OR of 7.38 (95% CI [1.65, 32.92], p = 0.009) and 18.32 (95% CI [3.95, 84.88], p < 0.001), respectively. Single visual assessment of abnormal locoregional lymph nodes predicted the presence of VGEI with a sensitivity of 35%, specificity of 96%, PPV of 95%, and NPV of 41%. The visual assessment of abnormal lymph nodes after qualitative assessment of 18F-FDG uptake intensity and pattern at the vascular graft location did not independently predict the presence of VGEI by logistic regression (Χ2: 3.60, p = 0.058; OR: 8.25, 95% CI [0.74, 63.37], p = 0.096). In conclusion, detection of abnormal locoregional lymph nodes on 18F-FDG PET/CT has a high specificity (96%) and PPV (95%) for VGEI. However, it did not add to currently used 18F-FDG PET/CT interpretation criteria.

Integral mediastinal staging in patients with NON-SMALL cell lung cancer and risk factors for occult N2 disease

BackgroundIn patients with non-small cell lung cancer (NSCLC), the presence of abnormal hiliar lymph nodes (clinical N1; cN1), central tumor location and/or tumor size (diameter >3 cm) increases the risk of occult mediastinal metastasis (OMM). This study investigates prospectively the diagnostic value of an integral mediastinal staging (IMS) strategy that combines EndoBronchial Ultrasound-TransBronchial Needle Aspiration (EBUS-TBNA) and Video-Assisted Mediastinoscopy (VAM) in patients with NSCLC at risk of OMM. MethodsPatients with NSCLC and radiologically normal mediastinum assessed non-invasively by positron emission tomography and computed tomography of the chest (PET-CT), and OMM risk factors (cN1, central tumor and/or >3 cm) underwent EBUS-TBNA followed by VAM if the former was negative. Those with negative IMS underwent resection surgery of the tumor. ResultsEBUS-TBNA identified OMM in 2 out of the 49 patients evaluated (4%) and VAM in 1 of the 47 patients with negative EBUS (2%). Two patients with a negative IMS had OMM at surgery. Overall, the prevalence of OMM was 10%. EBUS-TBNA has a sensitivity of 40%, a negative predictive value (NPV) of 93.6%, and negative likelihood ratio of 0.60 (95%CI:0.30–1.16). The risk of not diagnosing OMM after EBUS was 6% and after IMS was 4.4%. ConclusionIntegral mediastinal staging in patients with NSCLC and clinical risk factors for OMM, does not seem to provide added diagnostic value to that of EBUS-TBNA, except perhaps in patients with cN1 disease who deserve further research.

A Task Planning Method for UAV Swarm Dynamic Reconstruction Based on a Fourth-Order Motif

The primary purpose of task allocation is to build each equipment platform and quickly complete integration planning at the actual combat speed to achieve efficient management of the entire task. In this process, higher requirements are put forward for dynamic, cooperative, and highly adaptive drone colony organization. In this paper, the scheduling problem of hybrid unmanned aerial vehicle (UAV) systems is studied under an uncertain environment. First, the system-capability-task organizational structure is defined and quantified, which lays a foundation for dynamic adjustment of the organizational structure in the future. Then, combined with the theory of flexible network and elastic network management, the model is calculated, and the linear transformation function and fuzzy theory are used to stratify and cluster the capability layers. On this basis, four motif structures are introduced for abnormal nodes in the process of dynamic adjustment, and a dynamic group reconstruction algorithm (DRA-M) is established. Finally, the time and communication load indexes are determined, and the alternative strategy is designed for the failure point. The performance of the classical scheduling algorithm is evaluated by benchmarking it under different conditions. The results show that the algorithm has a good dynamic adjustment ability in the event of a UAV swarm emergency, which is a bright light for the future study of highly adaptive UAV cluster organization.

Difficult situation in treatment of medullary thyroid carcinoma in patient with multiple endocrine neoplasia type 2 B(MEN2B)

Abstract Introduction Multiple endocrine neoplasia type 2B (also known as ‘MEN2B’,‘Multiple endocrine neoplasia type 3′ or ‘Wagenmann–Froboese syndrome’) is a genetic disease characterized by the presence of medullary carcinoma of the thyroid, pheochromocytoma, mucosal neuromas, marfanoid features and multiple skeletal abnormalities such as kyphoscoliosis and pes cavus. Clinical Case A 16 years male presented with neck swelling and dysmorphic feature in the form of marfanoid habitus, including multiple tongue and oral mucosal swelling with mucosal neuromas on the anterior third of the tongue, the lips and the inner eyelid. Lips are thickened and bumpy. Visible neck swelling, palpable solid neck mass, high arm span to height ratio at &amp;gt;1.05, elongated fingers, pes cavus and positive wrist sign which is defined as when the distal phalanges of the thumb and fifth finger overlap on encircling the opposite wrist, were present. Ultrasound of the neck revealed a left solid irregular mass (57mmx33mm), that is hypoechoic, has coarse calcification, hypervascularity, that is mostly central, Multiple cervical lymph node(abnormal nodes include shape (round), absent hilum, intranodal necrosis, reticulation, calcification, peripheral vascularity),Investigation at beginning, Normal thyroid function test and biochemical and electrolyte were observed, Chest x ray was normal, FNAC done for thyroid nodule that showed multiple clumps of large hyperchromatic oval cells picture suggesting high suspicion of thyroid malignancy, thyroid biopsy advised, The patient was referred the FDEMC center for further evaluation and investigation prior to the surgery. During investigation at FDEMC center, thyroid function test normal, biochemistry normal, including PTH and electrolytes, Calcitonin was very high 465 pg/mL (0.2–27.7 pg/mL),GH under GTT was normal, IGF 1 182µg/L (150–350),Plasma metanephrine 40 pg/ml(&amp;lt;90pg/ml),and Plasma normetanephrine 27pg/ml(&amp;lt;196pg/ml) were normal. The patient referred to surgery, total thyroidectomy with radical neck dissection with multiple lymph node resection was performed. The biopsy revealed medullary thyroid carcinoma with cervical lymph node secondaries (bilateral multiple foci in both lobes). The patient kept on levothyroxine tab 100mcg.The follow up of the patient after one month by ultrasound and calcitonin level revealed residual thyroid tissue and two large cervical LN in the the ultrasound and a calcitonin level of 322 pg/mL Another surgical neck dissection to the metastatic LN &amp;lt;multiple LN 7×5cm, multiple suprasternal mass dissection 3×2.5cm,remnant of thyroid tissue 0.8cm,Follow up the patient after one month by ultrasound and calcitonin level still showed that there is residual pathological cervical LN, while the calcitonin level still high 412 pg/mL. PET scan done for him showed there is uptake in the head, neck and chest. The calcitonin was repeatedly was high.

Region Anomaly Detection via Spatial and Semantic Attributed Graph in Human Monitoring.

This paper proposes a graph-based deep framework for detecting anomalous image regions in human monitoring. The most relevant previous methods, which adopt deep models to obtain salient regions with captions, focus on discovering anomalous single regions and anomalous region pairs. However, they cannot detect an anomaly involving more than two regions and have deficiencies in capturing interactions among humans and objects scattered in multiple regions. For instance, the region of a man making a phone call is normal when it is located close to a kitchen sink and a soap bottle, as they are in a resting area, but abnormal when close to a bookshelf and a notebook PC, as they are in a working area. To overcome this limitation, we propose a spatial and semantic attributed graph and develop a Spatial and Semantic Graph Auto-Encoder (SSGAE). Specifically, the proposed graph models the "context" of a region in an image by considering other regions with spatial relations, e.g., a man sitting on a chair is adjacent to a white desk, as well as other region captions with high semantic similarities, e.g., "a man in a kitchen" is semantically similar to "a white chair in the kitchen". In this way, a region and its context are represented by a node and its neighbors, respectively, in the spatial and semantic attributed graph. Subsequently, SSGAE is devised to reconstruct the proposed graph to detect abnormal nodes. Extensive experimental results indicate that the AUC scores of SSGAE improve from 0.79 to 0.83, 0.83 to 0.87, and 0.91 to 0.93 compared with the best baselines on three real-world datasets.

Evaluation of 18FDG PET-CT-positive mediastinal-hilar lymph nodes in extrathoracic malignancies by EBUS-TBNA; correlation of SUVmax, and short-axis diameter with the final diagnosis.

Intrathoracic lymph node metastasis from extrathoracic neoplasms are rare. Primary malignancies that metastasize to mediastinal-hilar lymph nodes are head and neck , carcinoma breast ,and genitourinary. Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA)/endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) is currently the preferred modality for mediastinal lymph node sampling. Fifty seven patients with extrathoracic malignancies with maximum standardized uptake value (SUVmax) of mediastinal-hilar lymph nodes greater than or equal to 2.5 were taken up for EBUS-TBNA. The histo-cytopathological results obtained from EBUS-TBNA were compared with SUVmax value and short-axis diameter of a lymph node as noted on EBUS. Out of 74 sampled nodes, 49 (66.2%) were benign and 25 (33.8%) were malignant. The SUVmax range of benign nodes was 2.8-13 as compared to 3-18 of malignant nodes. The size range of malignant and benign nodes were 8-35 mm and 8-30 mm, respectively. The mean size of abnormal nodes (metastatic + granulomatous) was 17.5 (8-35 mm) and the mean SUVmax was 9.1 (3.4-18), and it was a statistically significant difference when compared to reactive (normal) nodes. At SUVmax cut-off 7.5, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) were 78.5%, 81.2%, 84.6%, and 74.2%, respectively for detecting abnormal nodes. At 13 mm size cut-off, sensitivity, specificity, PPV, NPV were 75.5%, 65%, 75%, and 72%, respectively, for detecting abnormal nodes. The majority of mediastinal-hilar nodes with increased metabolic activity are benign in nature. Size and SUVmax are poor predictors of metastasis in tuberculosis endemic region. There should be a restrictive attitude toward invasive diagnostic testing for mediastinal-hilar nodes in extrathoracic malignancies.

MVAD HAN: A Multi-View Based Anomaly Detection Method for Heterogeneous Attributed Networks

With the frequent occurrence of network security incidents in recent years, it has become very important to detect anomalous behaviour in networks as early and accurately as possible. Anomaly detection can improve the security of complex network systems by detecting abnormal and unreliable nodes, and thus it has become a hot research direction that has attracted wide attention. At present, abstracting real complex systems into complex networks for anomaly detection is the mainstream research method. However, the existing methods still have challenges in extracting network heterogeneity information and attribute information, so we propose a multi-view based anomaly detection method for heterogeneous attributed networks, MVAD HAN. This method can better extract the heterogeneous structural information and rich attribute information of the network to model heterogeneous attributed networks. Our method adopts an encoder-decoder architecture. First, in the encoder part, we use the Heterogeneous Graph Transformer with multiple views to learn node embeddings that fuse the heterogeneous information of the network. In the decoder part, we use an inner product decoder to reconstruct the network topology, a multilayer perceptron-based decoder to better reconstruct the network attribute information, and a linear projection to reconstruct the node type information of the network. Finally, we compute an anomaly score for each node using three reconstruction errors: network structure, attributes and node type. The higher the reconstruction error of a node, the higher the anomaly score and the higher the probability of an anomaly. Finally, anomalous nodes are identified by ranking the anomaly scores and setting a threshold. We validate the effectiveness of the proposed method on four real-world datasets. The experimental results show that this method outperforms several of the baseline methods and has a good performance in anomaly detection.

An Abnormal Pattern Detection Scheme Based on GCN and DBSCAN in a Large-Scale Graph

In recent decades, anomaly detection has undoubtedly become one of the most important areas of research. This is because applications such as financial transactions, medical fraud, and anomaly detection can be used to solve a wide range of real-life problems. Data from these applications can be modeled using large graphs of many different nodes and edges. Because of the size and heterogeneity of the data contained in the graph, it is a very difficult task to detect abnormal patterns. In this paper, we proposed a method for detecting abnormal patterns in a large homogeneous graph. The proposed method consisted of two steps. In the first step, the graph was transformed into a vector using a semi-supervised graph neural network (GCN). The second step was based on DBSCAN, an unsupervised clustering method. Various performance evaluations were performed to show the superiority of the proposed method. Experimental results showed that the proposed method could detect abnormal nodes with high accuracy in homogeneous static graphs.

Selective forwarding attack detection and network recovery mechanism based on cloud-edge cooperation in software-defined wireless sensor network

A software-defined wireless sensor network can dynamically configure the nodes in a network according to the demand of the application layer. In practical applications, such as environmental monitoring, the nodes in a wireless sensor network(WSN) are deployed in the field environment on a large scale, and the data rely on multihop transmission to reach the sink node. The data extremely easy to selective forwarding attacks during data transmission. Therefore, this study analyzes the models of selective forwarding attacks and proposes an abnormal node detection method, which includes a node behavior measurement scheme and trust-value evaluation mechanism. In addition, the application of a software-defined network (SDN) presents increasing network delay. Hence, herein a network recovery mechanism was designed based on cloud-edge cooperation to ensure the rapid recovery of the network after identifying the abnormal nodes. Moreover, experiments were conducted using simulation software and actual hardware. We verified the effectiveness of the proposed scheme. The experimental results revealed that the proposed method can effectively identify abnormal nodes, reduce the packet dropping ratio and shorten the network recovery delay by 77.2%. The research in this paper solves the security problem of SDWSN.

Unsupervised Identification of Abnormal Nodes and Edges in Graphs

Much of today’s data are represented as graphs, ranging from social networks to bibliographic citations. Nodes in such graphs correspond to records that generally represent entities, while edges represent relationships between these entities. Both nodes and edges in a graph can have attributes that characterize the entities and their relationships. Relationships are either explicitly known (like friends in a social network), or they are inferred using link prediction (such as two babies are siblings because they have the same mother). Any graph representing real-world data likely contains nodes and edges that are abnormal, and identifying these can be important for outlier detection in applications ranging from crime and fraud detection to viral marketing. We propose a novel approach to the unsupervised detection of abnormal nodes and edges in graphs. We first characterize nodes and edges using a set of features, and then employ a one-class classifier to identify abnormal nodes and edges. We extract patterns of features from these abnormal nodes and edges, and apply clustering to identify groups of patterns with similar characteristics. We finally visualize these abnormal patterns to show co-occurrences of features and relationships between those features that mostly influence the abnormality of nodes and edges. We evaluate our approach on datasets from diverse domains, including historical birth certificates, COVID patient records, e-mails, books, and movies. This evaluation demonstrates that our approach is well suited to identify both abnormal nodes and edges in graphs in an unsupervised way, and it can outperform several baseline anomaly detection techniques.

Improvement of the PBFT Algorithm Based on Grouping and Reputation Value Voting

An improved practical Byzantine fault tolerance (Practical Byzantine Fault Tolerant consensus algorithm based on reputation, RPBFT) algorithm based on grouping and reputation value voting is proposed for the problems of high communication complexity, poor scalability, and random selection of master nodes of the practical Byzantine fault tolerance (PBFT) consensus algorithm of the consortium chain. First, the consistency process is optimized to take the response speed of nodes to each group leader as the basis of grouping, and the intragroup consensus is performed. The group leader then takes the result of intragroup consensus and participates in extra-group consensus to reduce the frequency and time of internode communication. Second, the reputation model and voting mechanism are proposed, and the group leader is generated by node reputation value voting, which enhances the initiative and reliability of trusted nodes and reduces the abnormal nodes as group leader. Finally, a simulation and performance testing system based on this improved scheme is built to prove the effectiveness as well as the usability of the scheme through simulation experiments. The experimental results show that when the number of network nodes is 36, the throughput of the RPBFT algorithm is six times that of PBFT. Therefore, the consensus delay is reduced by 91.7%, and the communication overhead is reduced by 37.8%.

Magnetic resonance imaging evaluation of single axillary lymph node metastasis in breast cancer: Emphasis on the location of lymph nodes

To evaluate the frequency and location of abnormal lymph nodes (LNs) in breast cancer patients with a single axillary lymph node (ALN) metastasis on breast magnetic resonance imaging (MRI). We retrospectively reviewed the MRI findings of 219 consecutive patients with breast cancer with single ALN metastasis who were surgically confirmed at our institution between January 2018 and December 2018. The morphological features and locations of the abnormal LN on MRI were analyzed. Pathology reports were reviewed to evaluate the size of the metastases and whether they were sentinel LNs (SLNs). Of the 219 patients with a single ALN metastasis, 56 (25.6%) showed abnormal MRI findings. Of these, 54 (96.4%) had either the lowest or second-lowest LN in the level I axilla. In 184 (91.5%) of 201 patients who underwent SLN biopsy, the metastatic LN were SLN. Macrometastases were found more frequently in cases with abnormal LNs than in those with normal-looking LNs (P = .004). The most frequent morphological feature of metastatic ALNs was a diffuse cortical thickening of 3 to 5 mm (37.5%). Although MRI findings of single ALN metastasis in breast cancer patients are none or minimal, abnormalities are observed in the lowest or second-lowest LN in the lower axilla when present, suggesting the location of the SLNs.