True Positive Detection Rate Research Articles

Radiographs demonstrate poor accuracy for evaluation of postoperative osseous integration of osteochondral allografts in the knee

PurposeTo evaluate the interrater reliability and accuracy of radiographs in assessing healing of osteochondral allografts (OCA) in the knee compared to computed tomography (CT) imaging. MethodsA retrospective review patients who underwent OCA transplantation of the knee was conducted. Postoperatively, knee radiographs were obtained at three and six months, and CT scans were obtained at six months. Three board-eligible orthopaedic surgeons independently graded postoperative radiographs, utilizing the grading scale established by Oladeji et al 2017, and the CT scans utilizing the grading scale established by Gelber et al 2021. Their consensus measurements served as a comparative gold standard. ResultsAmong 44 prospectively imaged grafts, 13 (29.5%) had radiographs at three months and 28 (63.6%) had radiographs available for evaluation at six months. Assessment of radiographic integration demonstrated low reliability (ICC: -0.02 to 0.14). On CT scan, this improved to fair reliability (k=0.29, p<0.001). However, Spearman rho between CT and XR grading demonstrated poor correlation (ρ = -0.23, p=0.04). Among six-month postoperative radiographs, accuracy of cyst identification was negatively correlated to greater degree of cystic changes from 90.9% (30/33 correct; no cystic changes) to 19.4% (7/36 correct; small cystic changes) and 33.3% (5/15 correct; large cystic changes). Overall true positive cyst detection rates on radiographs were 27.8% to 46.7%. ConclusionRadiographs demonstrate poor interrater reliability and accuracy in evaluation of healing after OCA transplantation of the knee. Notably, there was a high rate of missed cystic changes on radiographic analysis, as well as poor correlation of integration assessment with CT scan findings.

ST-LaneNet: Lane Line Detection Method Based on Swin Transformer and LaneNet

The advancement of autonomous driving heavily relies on the ability to accurate lane lines detection. As deep learning and computer vision technologies evolve, a variety of deep learning-based methods for lane line detection have been proposed by researchers in the field. However, owing to the simple appearance of lane lines and the lack of distinctive features, it is easy for other objects with similar local appearances to interfere with the process of detecting lane lines. The precision of lane line detection is limited by the unpredictable quantity and diversity of lane lines. To address the aforementioned challenges, we propose a novel deep learning approach for lane line detection. This method leverages the Swin Transformer in conjunction with LaneNet (called ST-LaneNet). The experience results showed that the true positive detection rate can reach 97.53% for easy lanes and 96.83% for difficult lanes (such as scenes with severe occlusion and extreme lighting conditions), which can better accomplish the objective of detecting lane lines. In 1000 detection samples, the average detection accuracy can reach 97.83%, the average inference time per image can reach 17.8 ms, and the average number of frames per second can reach 64.8 Hz. The programming scripts and associated models for this project can be accessed openly at the following GitHub repository: https://github.com/Duane711/Lane-line-detection-ST-LaneNet.

Automatic detection of Opisthorchis viverrini egg in stool examination using convolutional-based neural networks.

Human opisthorchiasis is a dangerous infectious chronic disease distributed in many Asian areas in the water-basins of large rivers, Siberia, and Europe. The gold standard for human opisthorchiasis laboratory diagnosis is the routine examination of Opisthorchis spp. eggs under a microscope. Manual detection is laborious, time-consuming, and dependent on the microscopist's abilities and expertise. Automatic screening of Opisthorchis spp. eggs with deep learning techniques is a useful diagnostic aid. Herein, we propose a convolutional neural network (CNN) for classifying and automatically detecting O. viverrini eggs from digitized images. The image data acquisition was acquired from infected human feces and was processed using the gold standard formalin ethyl acetate concentration technique, and then captured under the microscope digital camera at 400x. Microscopic images containing artifacts and O.viverrini egg were augmented using image rotation, filtering, noising, and sharpening techniques. This augmentation increased the image dataset from 1 time to 36 times in preparation for the training and validation step. Furthermore, the overall dataset was subdivided into a training-validation and test set at an 80:20 ratio, trained with a five-fold cross-validation to test model stability. For model training, we customized a CNN for image classification. An object detection method was proposed using a patch search algorithm to detect eggs and their locations. A performance matrix was used to evaluate model efficiency after training and IoU analysis for object detection. The proposed model, initially trained on non-augmented data of artifacts (class 0) and O. viverrini eggs (class 1), showed limited performance with 50.0% accuracy, 25.0% precision, 50.0% recall, and a 33.0% F1-score. After implementing data augmentation, the model significantly improved, reaching 100% accuracy, precision, recall, and F1-score. Stability assessments using 5-fold cross-validation indicated better stability with augmented data, evidenced by an ROC-AUC metric improvement from 0.5 to 1.00. Compared to other models such as ResNet50, InceptionV3, VGG16, DenseNet121, and Xception, the proposed model, with a smaller file size of 2.7 MB, showed comparable perfect performance. In object detection, the augmented data-trained model achieved an IoU score over 0.5 in 139 out of 148 images, with an average IoU of 0.6947. This study demonstrated the successful application of CNN in classifying and automating the detection of O. viverrini eggs in human stool samples. Our CNN model's performance metrics and true positive detection rates were outstanding. This innovative application of deep learning can automate and improve diagnostic precision, speed, and efficiency, particularly in regions where O. viverrini infections are prevalent, thereby possibly improving infection sustainable control and treatment program.

A System to Detect Oilwell Anomalies Using Deep Learning and Decision Diagram Dual Approach

Summary Detecting unexpected events is a field of interest in oil and gas companies to improve operational safety and reduce costs associated with nonproductive time (NPT) and failure repair. This work presents a system for real-time monitoring of unwanted events using the production sensor data from oil wells. It uses a combination of long short-term memory (LSTM) autoencoder and a rule-based analytic approach to perform the detection of anomalies from sensor data. Initial studies are conducted to determine the behavior and correlations of pressure and temperature values for the most common combinations of well valve states. The proposed methodology uses pressure and temperature sensor data, from which a decision diagram (DD) classifies the well status, and this response is applied to the training of neural networks devoted to anomaly detection. Data sets related to several operations in wells located at different oil fields are used to train and validate the dual approach presented. The combination of the two techniques enables the deep neural network to evolve constantly through the normal data collected by the analytical method. The developed system exhibits high accuracy, with true positive detection rates exceeding 90% in the early stages of anomalies identified in both simulated and actual well production scenarios. It was implemented in more than 20 floating production, storage, and offloading (FPSO) vessels, monitoring more than 250 production/injection subsea wells, and can be applied both in real-time operation and in testing scenarios.

Metastatic prostate cancer is associated with distinct higher frequency of genetic mutations at diagnosis

Introduction and ObjectivesWe explored characteristic genetic mutations associated with metastatic prostate cancer (PCa) by comparing next generation sequencing (NGS) data between men with or without metastatic disease at diagnosis. MethodsWe queried the American Association for Cancer Research Project Genomics Evidence Neoplasia Information Exchange (GENIE) registry for men diagnosed with PCa. Patients were categorized into with (M1) or without metastatic disease (M0) groups. The difference in the frequency of genetic mutations between the two groups and the prognostic significance of the mutations were analyzed using SPSS V28. We included frequency rate of > 5% and P values < 0.05 were considered statistically significant to maintain over 95% true positive detection rate. ResultsOf a total of 10,580 patients with diagnosis of PCa in the dataset, we selected a study cohort of 1268 patients without missing data; 700 (55.2%) had nonmetastatic PCa, 421 (33.2%) and 147 (11.6%) patients had metastatic castration sensitive and resistant PCa respectively. The median age at diagnosis and serum prostate specific antigen (PSA) level for the entire cohort was 62.8 years (IQR 56.3–68.4) and 8.0 ng/ml (IQR 4.9–20.9) respectively. A vast majority of the cohort were of Caucasian ancestry (89.1%). Of a total of 561 genes sequenced, there were mutations in 79 genes (14.1%). The mutation frequency was significantly higher in M1PCa compared to M0PCa, 35.7% and 23.3%, respectively (P = <0.001). The median tumor mutational burden was also significantly higher in the samples from M1PCa (2.59 mut/MB) compared to M0PCa (1.96 mut/MB) (P < 0.001). Compared to M0PCa patients, M1PCa patients demonstrated significantly higher rate of genetic mutations; TP53 (38.73% vs. 17.71% P < 0.001), PTEN (25.70% vs. 11.71% P < 0.001), AR (17.25% vs. 1.43% P < 0.001), APC (11.8% vs. 4.43% P < 0.001), TMPRSS2 (31.5% vs. 11.14% P < 0.001), ERG (23.59% vs. 13.13% P < 0.001), FOXA1 (17.43% vs. 6.33% P < 0.001), MYC (8.45% vs. 2.29% P < 0.001), RB1 (10.39% vs. 2.43% P < 0.001) and CDK12 (8.45% vs. 1.31% P < 0.001). Of the various cellular signaling pathways, the androgen receptor signaling pathway was most often impacted. In the cohort with M1 disease, compared to men without genetic mutations the men with genetic mutations demonstrated worse survival (P = <0.001, log rank test). Compared to castration sensitive M1 patients, AR (57% vs. 4% P < 0.001), TP53 (50.7% vs. 34% P < 0.001), PTEN (35.2% vs. 22.1% P < 0.001), RB1(23.9% vs. 4.75% P < 0.001) were significantly more frequently mutated in castration resistant M1 patients. In contrast, mutations of SPOP (13.3% vs. 7.9% P < 0.001), FOXA1 (17.6% vs. 5.3% P < 0.001) and CDK12 (12% vs. 6.45% P < 0.001) were significantly more frequently found in castration sensitive M1 patients compared to castration resistant patients. ConclusionPatients with M1PCa demonstrated characteristic genetic mutations compared to M0PCa, which most often influenced androgen receptor signaling and is associated with worse survival. In addition, we identified distinct genetic mutations between castration sensitive and resistant M1PCa. These findings may be used to further our understanding and management of men with PCa.

Baldur: Bayesian Hierarchical Modeling for Label-Free Proteomics with Gamma Regressing Mean-Variance Trends

Label-free proteomics is a fast-growing methodology to infer abundances in mass spectrometry proteomics. Extensive research has focused on spectral quantification and peptide identification. However, research toward modeling and understanding quantitative proteomics data is scarce. Here we propose a Bayesian hierarchical decision model (Baldur) to test for differences in means between conditions for proteins, peptides, and post-translational modifications. We developed a Bayesian regression model to characterize local mean-variance trends in data, to estimate measurement uncertainty and hyperparameters for the decision model. A key contribution is the development of a new gamma regression model that describes the mean-variance dependency as a mixture of a common and a latent trend—allowing for localized trend estimates. We then evaluate the performance of Baldur, limma-trend, and t test on six benchmark datasets: five total proteomics and one post-translational modification dataset. We find that Baldur drastically improves the decision in noisier post-translational modification data over limma-trend and t test. In addition, we see significant improvements using Baldur over the other methods in the total proteomics datasets. Finally, we analyzed Baldur’s performance when increasing the number of replicates and found that the method always increases precision with sample size, while showing robust control of the false positive rate. We conclude that our model vastly improves over popular data analysis methods (limma-trend and t test) in several spike-in datasets by achieving a high true positive detection rate, while greatly reducing the false-positive rate.

Digital Rectal Examination Is Not a Useful Screening Test for Prostate Cancer

BackgroundAnnual digital rectal examination (DRE) is recommended as a stand-alone screening test for prostate cancer (PCa) in Germany for 45+ yr olds. DRE diagnostic performance in men as young as 45 yr old has not been proved by a screening trial. ObjectiveTo determine DRE diagnostic performance in a screening trial. Design, setting, and participantsThis analysis was conducted within the multicentric, randomized PROBASE trial, which enrolled >46 000 men at age 45 to test risk-adapted prostate-specific antigen (PSA) screening for PCa. Intervention(1) DRE was analyzed as a one-time, stand-alone screening offer at age 45 in 6537 men in one arm of the trial and (2) PCa detection by DRE was evaluated at the time of PSA-screen–driven biopsies (N = 578). Outcome measurements and statistical analysis(1) True-/false-positive detection rates of DRE as compared with PSA screening and (2) DRE outcome at the time of a prostate biopsy were evaluated. Results and limitations(1) A prospective analysis of 57 men with suspicious DRE at age 45 revealed three PCa. Detection rate by DRE was 0.05% (three of 6537) as compared with a four-fold higher rate by PSA screening (48 of 23 301, 0.21%). The true-positive detection rate by DRE relative to screening by PSA was 0.22 (95% confidence interval [CI] = [0.07–0.72]) and the false-positive detection rate by DRE was 2.2 (95% CI = [1.50–3.17]). (2) Among PSA-screen–detected PCa cases, 86% had unsuspicious DRE (sensitivity relative to PSA was 14%), with the majority of these tumors (86%) located in the potentially accessible zones of the prostate as seen by magnetic resonance imaging. ConclusionsThe performance of stand-alone DRE to screen for PCa is poor. DRE should not be recommended as a PCa screening test in young men. Furthermore, DRE does not improve the detection of PSA-screen–detected PCa. Patient summaryOur report demonstrated the poor diagnostic performance of digital rectal examination in the screening for prostate cancer in young men.

Importance of Blood Glucose Management Before 18F-FDG PET/CT in 322 Patients with Bacteremia of Unknown Origin.

We investigated the effects of blood glucose levels on the performance of 18F-FDG PET/CT for detecting an infection focus in patients with bacteremia. Methods: A total of 322 consecutive patients with bacteremia who underwent 18F-FDG PET/CT between 2010 and 2021 were included. Logistic regression analysis was performed to evaluate the association between finding a true-positive infection focus on 18F-FDG PET/CT and blood glucose level, type of diabetes, and use of hypoglycemic medication. C-reactive protein, leukocyte count, duration of antibiotic treatment, and type of isolated bacteria were considered as well. Results: Blood glucose level (odds ratio, 0.76 per unit increase; P = <0.001) was significantly and independently associated with 18F-FDG PET/CT outcome. In patients with a blood glucose level between 3.0 and 7.9 mmol/L (54-142 mg/dL), the true-positive detection rate of 18F-FDG PET/CT varied between 61% and 65%, whereas in patients with a blood glucose level between 8.0 and 10.9 mmol/L (144-196 mg/dL), the true-positive detection rate decreased to 30%-38%. In patients with a blood glucose level greater than 11.0 mmol/L (200 mg/dL), the true-positive detection rate was 17%. In addition to C-reactive protein (odds ratio, 1.004 per point increase; P = 0.009), no other variables were independently associated with 18F-FDG PET/CT outcome. Conclusion: In patients with moderate to severe hyperglycemia, 18F-FDG PET/CT was much less likely to identify the focus of infection than in normoglycemic patients. Although current guidelines recommend postponing 18F-FDG PET/CT only in cases of severe hyperglycemia with glucose levels greater than 11 mmol/L (200 mg/dL), a lower blood glucose threshold seems to be more appropriate in patients with bacteremia of unknown origin and other infectious diseases.

PD10-11 DISTINCT CLINICAL GENOMIC VARIATIONS AMONG MEN WITH LOCALIZED VS METASTATIC PROSTATE CANCER

You have accessJournal of UrologyCME1 Apr 2023PD10-11 DISTINCT CLINICAL GENOMIC VARIATIONS AMONG MEN WITH LOCALIZED VS METASTATIC PROSTATE CANCER Ahmed El-shafie, Mohammed Al-Toubat, Allison H. Feibus, SeyedBehzad Jazayeri, Soroush Bazargani, Devon Thomas, Mark Bandyk, and K.C. Balaji Ahmed El-shafieAhmed El-shafie More articles by this author , Mohammed Al-ToubatMohammed Al-Toubat More articles by this author , Allison H. FeibusAllison H. Feibus More articles by this author , SeyedBehzad JazayeriSeyedBehzad Jazayeri More articles by this author , Soroush BazarganiSoroush Bazargani More articles by this author , Devon ThomasDevon Thomas More articles by this author , Mark BandykMark Bandyk More articles by this author , and K.C. BalajiK.C. Balaji More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003250.11AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Our objective was to identify unique genetic mutations associated with metastatic prostate cancer (PCa) by comparing next generation sequencing (NGS) data between men with localized and metastatic disease METHODS: We queried the American Association for Cancer Research Project Genomics Evidence Neoplasia Information Exchange (GENIE) registry for men diagnosed with PCa. Patients were categorized into localized (m0) and metastatic (m1) groups. The difference in the frequency of genetic mutations between the two groups and the prognostic significance of the differentially expressed genes were analysed using SPSS V24. We included frequency rates of >5% and p values <0.05 were considered statistically significant to maintain over 95% true positive detection rate. RESULTS: A total of 1,027 patients, with localized (n=459) and metastatic PCa (n=568) were included in the study. Patients were mostly non-Hispanic White men (89%) with a median age of 61 years (IQR 56-66 years). 421 (41%) of our cohort had Gleason grade group (GG) 2 disease, 277 (27%) had GG3 disease, and 267 (26%) had GG4 or GG5 disease. We identified alterations in 89 genes in our analyses. Patients with M1PCa had significantly higher genomic aberrations in TMPRSS2 (31.51% vs 11.14%, p<0.001); ERG fusion (23.59% vs 13.13%, p<0.001); PTEN loss (25.7% vs 16.16%, p<0.001); TP53 mutation (38.73% vs 12.23%, p<0.001); FOXA1 (17.43% vs 6.33%, p<0.001); KMT2C (9.51% vs 6.11%, p=0.02) (Figure 1). We then isolated the signalling pathways most likely to be affected by these mutations, and found that the androgen receptor was most often impacted (Figure 2). Patients with alterations in all 6 of the genes listed above had the worst progression-free survival (p = <0.01, log rank test) (Figure 1). CONCLUSIONS: In M1PCa, patients had significantly higher frequency of TMPRSS2, ERG, PTEN loss, TP53, FOXA1, and KMT2C somatic gene mutations compared to samples from patients with m0PCa. Additionally, patients who had mutations in all 6 of these genes harboured more aggressive cancer and poorer outcomes. Source of Funding: None © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e330 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Ahmed El-shafie More articles by this author Mohammed Al-Toubat More articles by this author Allison H. Feibus More articles by this author SeyedBehzad Jazayeri More articles by this author Soroush Bazargani More articles by this author Devon Thomas More articles by this author Mark Bandyk More articles by this author K.C. Balaji More articles by this author Expand All Advertisement PDF downloadLoading ...

MP46-02 LYMPHOVASCULAR INVASION IN NON-METASTATIC MUSCLE INVASIVE BLADDER CANCER IS ASSOCIATED WITH CHARACTERISTIC GENETIC MUTATIONS

You have accessJournal of UrologyCME1 Apr 2023MP46-02 LYMPHOVASCULAR INVASION IN NON-METASTATIC MUSCLE INVASIVE BLADDER CANCER IS ASSOCIATED WITH CHARACTERISTIC GENETIC MUTATIONS Mohammed Al-Toubat, Ahmed El-Shafie, Allison H. Feibus, Seyedbehzad Jazayeri, Naser Mubarak, Khalid Mohammed, and Mark Bandyk K. C. Balaji Mohammed Al-ToubatMohammed Al-Toubat More articles by this author , Ahmed El-ShafieAhmed El-Shafie More articles by this author , Allison H. FeibusAllison H. Feibus More articles by this author , Seyedbehzad JazayeriSeyedbehzad Jazayeri More articles by this author , Naser MubarakNaser Mubarak More articles by this author , Khalid MohammedKhalid Mohammed More articles by this author , and Mark Bandyk K. C. BalajiMark Bandyk K. C. Balaji More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003292.02AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Lymphovascular invasion (LVI) in invasive bladder cancer is strongly associated with metastatic disease. We aim to identify the genes that could be the potential drivers of LVI in non-metastatic lymph node negative muscle invasive bladder cancer (M0N0MIBC). METHODS: We queried the American Association for Cancer Research Project Genomics Evidence Neoplasia Information Exchange (GENIE) registry. Key genes were identified in respect to LVI status in 316 patients with M0N0MIBC. The relationships among LVI-associated genomic subtypes, clinicopathological features and patient outcomes were explored. All patients had imaging and pathologic evaluation to ensure M0 and N0 status. We included frequency rates of > 5% and p/q values <0.05 were considered statistically significant to maintain >95% true positive detection rate. SPSS V24 was used for analyses. RESULTS: A total of 316 patients were included in our study cohort, all of which had M0N0MIBC disease. Overall, 112 (35.4%) patients had LVI-positive and 204 (64.6%) patients were LVI-negative. Male patients constituted the majority of the cohort [230 (72.8%)]. 248 men (78.5%) in the cohort were Caucasian. Median age was 70 years (65-75 IQR). At the time of the analysis, 312 (98%) patients had not received any systemic treatment. LVI was associated with a higher T stage and more aggressive grade (p=0.02). We identified alterations in 56 genes. Patients with LVI had significantly higher mutation alterations rate in 7 genes (p<0.001) - CDKN2A, CDKN2ADT, CDKN2B, MTAP, HMCN1, DMRTA1, KMT2D. There was downregulation of 3 genes - RB1, SOX4 and CDKAL1 among those with LVI (Figure 1). Patients with LVI had a shorter overall survival (p<0.001) and a shorter 5 year progression-free survival (p<0.001) (Figure 2). CONCLUSIONS: Imbalance between genetic expression of extracellular matrix components (HMCN1) and cell-cycle regulators (CDK family) could initiate LVI in association with disease progression in patients with N0M0MIBC. Source of Funding: None © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e630 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Mohammed Al-Toubat More articles by this author Ahmed El-Shafie More articles by this author Allison H. Feibus More articles by this author Seyedbehzad Jazayeri More articles by this author Naser Mubarak More articles by this author Khalid Mohammed More articles by this author Mark Bandyk K. C. Balaji More articles by this author Expand All Advertisement PDF downloadLoading ...

Network based Intrusion Detection System using the SPSS Method

An invasion detection system (NIDS) that makes use of networks can spot malicious activities on a network. For NIDS to inspect each and every packet of communication, including unicast traffic, invalid network access is often required. Along with being small structures that don't block traffic, NIDS are able to keep an eye on usernames and passwords, check for any signs of odd activity in the file integrity logs, port logs, mysql database file storage, etc. and alert the part of implementing as necessary. Since NIDS keeps an eye on live data, it can spot problems as they happen. On the other hand, HIDS uses historical data to identify skilled hackers who employ cutting-edge methods that are difficult to detect in real-time. A monitoring system called an intrusion notification system (IDS) looks for abnormal activity and sends out alarms when it does. A Counter Terrorism Center (SOC) analyst senior incident handler can look into the issue and take the necessary steps to resolve the threat based on these notifications. Every incoming packets are read by an NIDS, which scans them for any anomalous activity. Depending on the gravity of the danger, steps can be taken, such as alerting system administrators or preventing the initial IP address from connecting to the network. In the past decades, due to developments Increased use of networking techniques and internet, digital. Contacts entered into everything that happens on the world market. The hacker penetration attempts are taking place in parallel with these advances. Networks are expanding as well. Without permission, they attempted to modify some network data or increase network traffic in order to launch a denial-of-service attack. Intrusion prevention systems (IDS) are also favoured, especially for detecting malicious within a network system, even though a firewall may appear like an useful solution to avoid this type of attack. Machine learning algorithms have helped IDS become more successful in recent years, depending on the consequences of the training/learning process. Knowing what is important is very difficult and the learning algorithm is fast according to the problem Type. The complexity of the task, the size of the data sets, the number of nodes, the network design, the intended error rate, etc. all affect the choice of algorithm. Examine several network training functions in artificial neural networks with numerous layers created to provide effective intrusion detection systems. test outcomes The study provides evidence of the usefulness of the approach. Considering their speed and true-positive detection rates Death Penalty. SPSS statistics is multivariate analytics, business intelligence, and criminal investigation data management, advanced analytics, developed by IBM for a statistical software package. A long time, spa inc. Was created by, IBM purchased it in 2009. The brand name for the most recent versions is IBM SPSS statistics. Network Security, Intrusion Detection System, Neural Networks and Training Functions. The Cronbach's Alpha Reliability result. The overall Cronbach's Alpha value for the model is .860which indicates 86% reliability. From the literature review, the above 50% Cronbach's Alpha value model can be considered for analysis. Emotional Intelligence the Cronbach's Alpha Reliability result. The overall Cronbach's Alpha value for the model is .860which indicates 86% reliability. From the literature review, the above 50% Cronbach's Alpha value model can be considered for analysis.

Evaluating a Non-platform-specific OCR/NLP system to detect Online Grooming

Online Grooming is a social engineering attack in which the attacking party uses deceptive practices for sexual gratification. The targets of these attacks can vary in demographics however in most cases the target is children, with most of these attacks occurring on social media platforms. As well as the illegality of these attacks in the UK and US, children who experience these attacks are at a higher risk of self-harm or having suicidal thoughts. Due to the deployment of new social media platforms/features any implementation that is made specific to a certain feature/platform is likely to be outdated/ineffective upon release, due to the volatility of the methods/tactics used. Therefore a non-platform specific implementation has been considered within this investigation. From a preliminary analysis, it was concluded that there was an average true positive detection rate of 71% from using optical recognition and natural language processing across three different social media platforms. It is suggested that implementing this text extraction and processing method alongside a 'category-based' machine learning algorithm, a solution that can identify online grooming can be developed that considers the 'real world complexities' of this attack.

Detecting network-based internet censorship via latent feature representation learning

Internet censorship is a phenomenon of societal importance and attracts investigation from multiple disciplines. Several research groups, such as Censored Planet, have deployed large scale Internet measurement platforms to collect network reachability data. However, existing studies generally rely on manually designed rules (i.e., using censorship fingerprints) to detect network-based Internet censorship from the data. While this rule-based approach yields a high true positive detection rate, it suffers from several challenges: it requires human expertise, is laborious, and cannot detect any censorship not captured by the rules. Seeking to overcome these challenges, we design and evaluate a classification model based on latent feature representation learning and an image-based classification model to detect network-based Internet censorship. To infer latent feature representations from network reachability data, we propose a sequence-to-sequence autoencoder to capture the structure and the order of data elements in the data. To estimate the probability of censorship events from the inferred latent features, we rely on a densely connected multi-layer neural network model. Our image-based classification model encodes a network reachability data record as a gray-scale image and classifies the image as censored or not using a dense convolutional neural network. We compare and evaluate both approaches using data sets from Censored Planet via a hold-out evaluation. Both classification models are capable of detecting network-based Internet censorship as we were able to identify instances of censorship not detected by the known fingerprints. Latent feature representations likely encode more nuances in the data since the latent feature learning approach discovers a greater quantity, and a more diverse set, of new censorship instances.

Artificial intelligence-based recognition for variant pathogenicity of BRCA1 using AlphaFold2-predicted structures.

With the surge of the high-throughput sequencing technologies, many genetic variants have been identified in the past decade. The vast majority of these variants are defined as variants of uncertain significance (VUS), as their significance to the function or health of an organism is not known. It is urgently needed to develop intelligent models for the clinical interpretation of VUS. State-of-the-art artificial intelligence (AI)-based variant effect predictors only learn features from primary amino acid sequences, leaving out information about the most important three-dimensional structure that is more related to its function. Methods: We proposed a deep convolutional neural network model named variant effect recognition network for BRCA1 (vERnet-B) to recognize the clinical pathogenicity of missense single-nucleotide variants in the BRCT domain of BRCA1. vERnet-B learned features associated with the pathogenicity from the tertiary protein structures of variants predicted by AlphaFold2. Results: After performing a series of validation and analyses on vERnet-B, we discovered that it exhibited significant advances over previous works. Recognizing the phenotypic consequences of VUS is one of the most daunting challenges in genetic informatics; however, we achieved 85% accuracy in recognizing disease BRCA1 variants with an ideal balance of false-positive and true-positive detection rates. vERnet-B correctly recognized the pathogenicity of variant A1708E, which was poorly predicted by AlphaFold2 as previously described. The vERnet-B web server is freely available from URL: http://ai-lab.bjrz.org.cn/vERnet. Conclusions: We applied protein tertiary structures to successfully recognize the pathogenic missense SNVs, which were difficult to be addressed by classical approaches based on sequences. Our work demonstrated that AlphaFold2-predicted structures were expected to be used for rich feature learning and revealed unique insights into the clinical interpretation of VUS in disease-related genes, using vERnet-B as a discovery tool.

Uncertainty Quantification for Full-Flight Data Based Engine Fault Detection with Neural Networks

Current state-of-the-art engine condition monitoring is based on a minimum of one steady-state data point per flight. Due to the scarcity of available data points, there are difficulties distinguishing between random scatter and an underlying fault introducing a detection latency of several flights. Today’s increased availability of data acquisition hardware in modern aircraft provides continuously sampled in-flight measurements, so-called full-flight data. These full-flight data give access to sufficient data points to detect faults within a single flight, significantly improving the availability and safety of aircraft. Artificial neural networks are considered well suited for the timely analysis of an extensive amount of incoming data. This article proposes uncertainty quantification for artificial neural networks, leading to more reliable and robust fault detection. An existing approach for approximating the aleatoric uncertainty was extended by an Out-of-Distribution Detection in order to take the epistemic uncertainty into account. The method was statistically evaluated, and a grid search was performed to evaluate optimal parameter combinations maximizing the true positive detection rates. All test cases were derived based on in-flight measurements of a commercially operated regional jet. Especially when requiring low false positive detection rates, the true positive detections could be improved 2.8 times while improving response times by approximately 6.9 compared to methods only accounting for the aleatoric uncertainty.

Preoperative Imaging with [18F]-Fluorocholine PET/CT in Primary Hyperparathyroidism.

Primary hyperparathyroidism (pHPT) is a common endocrine disorder due to hyperfunctioning parathyroid glands. To date, the only curing therapy is surgical removal of the dysfunctional gland, making correct detection and localization crucial in order to perform a minimally invasive parathyroidectomy. 18F-Fluorocholine positron emission tomography/computed tomography (18F-FCH PET/CT) has shown promising results for the detection of pHPT, suggesting superiority over conventional imaging with ultrasounds or scintigraphy. A total of 33 patients with pHPT who had negative or equivocal findings in conventional imaging received 18F-FCH PET/CT preoperatively and were retrospectively included. A pathological hyperfunctional parathyroid gland was diagnosed in 24 cases (positive PET, 72.7%), 4 cases showed equivocal choline uptake (equivocal PET, 12.1%), and in 5 cases, no enhanced choline uptake was evident (negative PET, 15.2%). Twelve of the twenty-four detected adenoma patients underwent surgery, and in all cases, a pathological parathyroid adenoma was resected at the site detected by PET/CT. Two of the six patients without pathological choline uptake who received a parathyroidectomy revealed no evidence of parathyroid adenoma tissue in the histopathological evaluation. This retrospective study analyzes 18F-FCH PET/CT in a challenging patient cohort with pHPT and negative or equivocal conventional imaging results and supports the use of 18F-FCH for the diagnosis of hyperfunctional parathyroid tissue, especially in this patient setting, with a 100% true positive and true negative detection rate. Our study further demonstrates the importance of 18F-FCH PET/CT for successful surgical guidance.

Diagnostic evaluation of implantable loop recorder devices associated with remote monitoring: a retrospective multicentric study

Abstract Funding Acknowledgements Type of funding sources: None. It has been proven that Implantable Loop Recorders (ILRs) and remote monitoring could improve diagnostic rate, shorten time-to-diagnosis and thus better patient’s clinical outcome. Medical indications to ILRs have been lately extended, and many technical improvements have been achieved in the last few years. Nowadays many different ILRs are available, therefore choosing the best device, according to the patient’s clinical features, could help to reach an optimal patient management. Aim of this retrospective multicentric study is to compare which is best between 2nd generation ILR Medtronic Reveal™ LINQ (MRL) or St. Jude Medical Confirm™ RX (SCX), both associated with remote monitoring, in terms of overall accuracy rate (OAR), true positive detection rate (TPDR) and arrhythmias-free survival (AFS). Patients included in the study required an ILR implant for syncope, non-recurring heartbeat, suspect AF, Brugada Syndrome, post-ablation AF monitoring and non-stustained ventricular tachycardia. Medtronic Reveal™ LINQ (n=436, mean age 66±15, mean BMI 30±5) and St. Jude Medical Confirm™ RX (n=98, mean age 64±14, BMI 27.5±4) implanted patients underwent a weekly remote and a six-monthly outpatient follow-up. Every transmission was judged by two different cardiologists. The final diagnosis was set only in case of agreement, conversely, the transmission was discussed either considered non-diagnostic. Patients were studied for atrial fibrillation (AF), pauses (Ps), bradycardias (Bs) and tachycardias (Ts). MRL transmitted 5585 times, SCX 7545 (monthly transmission/patient ratio 25.5±45.6 vs 0.9±1.1 respectively). MRL had statistically significant better OAR for AF (61% vs 14%, p&amp;lt;0,001), Ps (20% vs 7%, p&amp;lt;0.001) and Bs (72% vs 20%, p&amp;lt;0.001). SCX had statistically better OAR for Ts (84% vs 56%, p&amp;lt;0.001). MRL had statistically significant better TPDR for AF alone (82% vs 48%, p&amp;lt;0.001) and non-statistically significant better TPDR for Ps (32% vs 28%, p=0.117), Bs (48% vs 38%, p=0.133) and Ts (69% vs 69%, p=0.505). Patient with MRL had better AFS at a six-months follow-up (72% vs 20%, p&amp;lt;0.001). The overall accuracy rate for every arrhythmic episode was better in MRL implanted patients than in the SCX implanted ones (43% vs 16%, p=0.001). Transmission rate was higher in SCX, even though MRL had a better accuracy in detecting real arrhythmic events. The overall accuracy rate of arrhythmic events in both groups is sub-optimal, therefore further engineering research is required to improve diagnostic accuracy of ILRs.

Assessment of two statistical approaches for variance genome-wide association studies in plants.

Genomic loci that control the variance of agronomically important traits are increasingly important due to the profusion of unpredictable environments arising from climate change. The ability to identify such variance-controlling loci in association studies will be critical for future breeding efforts. Two statistical approaches that have already been used in the variance genome-wide association study (vGWAS) paradigm are the Brown-Forsythe test (BFT) and the double generalized linear model (DGLM). To ensure that these approaches are deployed as effectively as possible, it is critical to study the factors that influence their ability to identify variance-controlling loci. We used genome-wide marker data in maize (Zea mays L.) and Arabidopsis thaliana to simulate traits controlled by epistasis, genotype by environment (GxE) interactions, and variance quantitative trait nucleotides (vQTNs). We then quantified true and false positive detection rates of the BFT and DGLM across all simulated traits. We also conducted a vGWAS using both the BFT and DGLM on plant height in a maize diversity panel. The observed true positive detection rates at the maximum sample size considered (N = 2815) suggest that both of these vGWAS approaches are capable of identifying epistasis and GxE for sufficiently large sample sizes. We also noted that the DGLM decisively outperformed the BFT for simulated traits controlled by vQTNs at sample sizes of N = 500. Although we conclude that there are still certain aspects of vGWAS approaches that need further refinement, this study suggests that the BFT and DGLM are capable of identifying variance-controlling loci in current state-of-the-art plant or agronomic data sets.

Aquifer heterogeneity controls to quality monitoring network performance for the protection of groundwater production wells

A groundwater monitoring network surrounding a pumping well (such as a public water supply) allows for early contaminant detection and mitigation where possible contaminant source locations are often unknown. This numerical study investigates how the contaminant detection probability of a hypothetical sentinel-well monitoring network consisting of one to four monitoring wells is affected by aquifer spatial heterogeneity and dispersion characteristics, where the contaminant source location is randomized. This is achieved through a stochastic framework using a Monte Carlo approach. A single production well is considered that results in converging non-uniform flow close to the well. Optimal network arrangements are obtained by maximizing a weighted risk function that considers true and false positive detection rates, sampling frequency, early detection, and contaminant travel time uncertainty. Aquifer dispersivity is found to be the dominant parameter for the quantification of network performance. For the range of parameters considered, a single monitoring well screening the full aquifer thickness is expected to correctly and timely identify at least 12% of all incidents resulting in contaminants reaching the production well. This proportion increases to a global maximum of 96% for a network consisting of four wells and very dispersive transport conditions. Irrespective of network size and sampling frequency, more dispersive transport conditions result in higher detection rates. Increasing aquifer heterogeneity and decreasing aquifer spatial continuity also lead to higher detection rates, though these effects are diminished for networks of 3 or more wells. Statistical anisotropy has no effect on the network performance. Earlier detection, which is critical for remedial action and supply safety, comes with a significant cost in terms of detection rate, and should be carefully considered when a monitoring network is being designed.

Semi-Supervised Learning for Anomaly Classification Using Partially Labeled Subsets

Abstract Machine learning and other data-driven methods have developed at a prolific rate for industrial applications due to the advent of industrial big data. However, industrial datasets may not be especially well-suited to supervised learning approaches that require extensive domain knowledge in the complete and accurate labeling of datasets. To address these challenges, a semi-supervised learning approach is proposed that makes use of partially labeled subsets. The proposed methodology is applied to high-dimensional in-process measurement data, utilizing a convolutional autoencoder (CAE) for unsupervised feature extraction. A multiclass extension for semi-supervised anomaly diagnosis is proposed that utilizes principal component analysis (PCA) as the basis for anomaly scoring, and the proposed approach intersects the results of targeted one-against-all phases on partially labeled sets to classify faults. Experiments in a case study on semiconductor manufacturing measurement data are performed to explore the relationship between latent features extracted and anomaly detection performance. The application of the proposed algorithm achieves a true positive detection rate of over 90% with false positive rate under 9% for both local and global anomaly types, with these results accomplished while reducing over 99% of the original input data dimensions. In addition, the approach also allows for positive samples to be identified that were previously undetected by human experts. These results are promising for the application of the proposed semi-supervised methodology in real industrial settings.