DETECTION OF BLOOD VESSELS IN RETINAL IMAGES

2010 ◽  
Vol 10 (01) ◽  
pp. 57-72 ◽  
Author(s):  
HEJER JLASSI ◽  
KAMEL HAMROUNI
Keyword(s):  
Blood Vessels ◽  
Anisotropic Diffusion ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Retinal Images ◽  
Linear Filter ◽  
Vascular Tree ◽  
Morphological Reconstruction ◽  
Processing Steps ◽  
Better Than

This paper presents a method to segment blood vessels in retinal images. It is based on mathematical morphology and the anisotropic diffusion and is composed of four steps: image processing by using linear filter and morphological ones, details extraction by using top-hat transform, morphological reconstruction of vascular tree and post processing steps using anisotropic diffusion. Our method is tested on red-free retinal images, taken from two public database. Our results on both public databases were comparable in performance with other authors. The method achieves a good result by mean of the "receiver operating characteristic curve" (ROC). The results show that our method is significantly better than other rule-based methods.

scholarly journals Comparisons of QPFs Derived from Single- and Multicore Convection-Allowing Ensembles

2019 ◽  
Vol 34 (6) ◽  
pp. 1955-1964
Author(s):  
Adam J. Clark
Keyword(s):  
Operating Characteristic ◽  
Characteristic Curve ◽  
Skill Score ◽  
Ensemble Forecast ◽  
Grid Spacing ◽  
Forecast System ◽  
Relative Operating Characteristic ◽  
Core System ◽  
Testing And Evaluation ◽  
Better Than

Abstract This study compares ensemble precipitation forecasts from 10-member, 3-km grid-spacing, CONUS domain single- and multicore ensembles that were a part of the 2016 Community Leveraged Unified Ensemble (CLUE) that was run for the 2016 NOAA Hazardous Weather Testbed Spring Forecasting Experiment. The main results are that a 10-member ARW ensemble was significantly more skillful than a 10-member NMMB ensemble, and a 10-member MIX ensemble (5 ARW and 5 NMMB members) performed about the same as the 10-member ARW ensemble. Skill was measured by area under the relative operating characteristic curve (AUC) and fractions skill score (FSS). Rank histograms in the ARW ensemble were flatter than the NMMB ensemble indicating that the envelope of ensemble members better encompassed observations (i.e., better reliability) in the ARW. Rank histograms in the MIX ensemble were similar to the ARW ensemble. In the context of NOAA’s plans for a Unified Forecast System featuring a CAM ensemble with a single core, the results are positive and indicate that it should be possible to develop a single-core system that performs as well as or better than the current operational CAM ensemble, which is known as the High-Resolution Ensemble Forecast System (HREF). However, as new modeling applications are developed and incremental changes that move HREF toward a single-core system are made possible, more thorough testing and evaluation should be conducted.

scholarly journals Are Body Composition Parameters Better than Conventional Anthropometric Measures in Predicting Pediatric Hypertension?

2020 ◽  
Vol 17 (16) ◽  
pp. 5771
Author(s):  
Chih-Yu Hsu ◽  
Rong-Ho Lin ◽  
Yu-Ching Lin ◽  
Jau-Yuan Chen ◽  
Wen-Cheng Li ◽  
...  
Keyword(s):  
Body Composition ◽  
Receiver Operating Characteristic Curve ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Fat Free Mass ◽  
Z Score ◽  
Pediatric Hypertension ◽  
Anthropometric Measures ◽  
Operating Characteristic Curve ◽  
Better Than

Body composition (BC) parameters are associated with cardiometabolic diseases in children; however, the importance of BC parameters for predicting pediatric hypertension is inconclusive. This cross-sectional study aimed to compare the difference in predictive values of BC parameters and conventional anthropometric measures for pediatric hypertension in school-aged children. A total of 340 children (177 girls and 163 boys) with a mean age of 8.8 ± 1.7 years and mean body mass index (BMI) z-score of 0.50 ± 1.24 were enrolled (102 hypertensive children and 238 normotensive children). Significantly higher values of anthropometric measures (BMI, BMI z-score, BMI percentile, waist-to-height ratio) and BC parameters (body-fat percentage, muscle weight, fat mass, fat-free mass) were observed among the hypertensive subgroup compared to their normotensive counterparts. A prediction model combining fat mass ≥ 3.65 kg and fat-free mass ≥ 34.65 kg (area under the receiver operating characteristic curve = 0.688; sensitivity = 66.7%; specificity = 89.9%) performed better than BMI alone (area under the receiver operating characteristic curve = 0.649; sensitivity = 55.9%; specificity = 73.9%) in predicting hypertension. In conclusion, BC parameters are better than anthropometric measures in predicting pediatric hypertension. BC measuring is a reasonable approach for risk stratification in pediatric hypertension.

scholarly journals IoT information theft prediction using ensemble feature selection

2022 ◽  
Vol 9 (1) ◽  
Author(s):  
Joffrey L. Leevy ◽  
John Hancock ◽  
Taghi M. Khoshgoftaar ◽  
Jared M. Peterson
Keyword(s):  
Feature Selection ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Classification Performance ◽  
Feature Reduction ◽  
Security Risk ◽  
Precision Recall Curve ◽  
Iot Devices ◽  
Feature Selection Techniques ◽  
Better Than

AbstractThe recent years have seen a proliferation of Internet of Things (IoT) devices and an associated security risk from an increasing volume of malicious traffic worldwide. For this reason, datasets such as Bot-IoT were created to train machine learning classifiers to identify attack traffic in IoT networks. In this study, we build predictive models with Bot-IoT to detect attacks represented by dataset instances from the Information Theft category, as well as dataset instances from the data exfiltration and keylogging subcategories. Our contribution is centered on the evaluation of ensemble feature selection techniques (FSTs) on classification performance for these specific attack instances. A group or ensemble of FSTs will often perform better than the best individual technique. The classifiers that we use are a diverse set of four ensemble learners (Light GBM, CatBoost, XGBoost, and random forest (RF)) and four non-ensemble learners (logistic regression (LR), decision tree (DT), Naive Bayes (NB), and a multi-layer perceptron (MLP)). The metrics used for evaluating classification performance are area under the receiver operating characteristic curve (AUC) and Area Under the precision-recall curve (AUPRC). For the most part, we determined that our ensemble FSTs do not affect classification performance but are beneficial because feature reduction eases computational burden and provides insight through improved data visualization.

scholarly journals Conventional Laboratory Blood Indicators Are Valuable for Early Diagnosis of Colorectal Cancer

2021 ◽  
Author(s):  
Xia Gan ◽  
Zhi-Yong Chen ◽  
Zi-Hua Li ◽  
Jian-Ming Zhou ◽  
Ying Sun ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Early Diagnosis ◽  
Receiver Operating Characteristic Curve ◽  
Operating Characteristic ◽  
Clinical Laboratory ◽  
Characteristic Curve ◽  
Diagnostic Value ◽  
Imaging Data ◽  
Operating Characteristic Curve ◽  
Better Than

Abstract Objective: Some conventional laboratory indicators have been found to be of value for the diagnosis of colorectal cancer (CRC). The present study aimed to systematically analyze the diagnostic value of conventional laboratory blood indicators for CRC, especially for early CRC. Methods: A total of 505 patients with CRC (n=210), colorectal adenoma (CRA) (n=167) or polyp (CRP) (n=128) were retrospectively collected. Clinical, laboratory and imaging data available before treatment were extracted. The diagnostic performances of laboratory blood indicators for discriminating total and early CRCs from CRA and CRP (CRA&P) were evaluated.Results: Fifty-three of 76 (69.7%) laboratory blood indicators were significant for discriminating CRC from CRA&P with areas under the receiver operating characteristic curve (AUC) ranging within 0.554-0.819, of these indicators, 17 had AUC > 0.7, three had AUC > 0.8, and five had AUCs greater than that for carcinoembryonic antigen (CEA). Fifteen indicators had overall sensitivities comparable to CEA for the diagnosis of CRC (35.7-55.4% vs. 47.7%, all P>0.05) at a specificity of 90%, and they were not or weakly correlated with CEA (absolute r = 0.058-0.333). For differentiating early CRC (TNM stage I+II, n=102) from CRA&P, the sensitivities for the 15 indicators ranged within 30.4%-55.5% at a specificity of 90% and similar to stage III+IV CRC.Conclusion: Conventional laboratory blood indicators are valuable for early CRC diagnosis, and are comparable to or better than CEA.

scholarly journals Cerebellar Arteriovenous Malformations

Neurosurgery ◽  
2012 ◽  
Vol 71 (6) ◽  
pp. 1111-1124 ◽  
Author(s):  
◽  
Ana Rodríguez-Hernández ◽  
Helen Kim ◽  
Tony Pourmohamad ◽  
William L. Young ◽  
...  
Keyword(s):  
Arteriovenous Malformations ◽  
Operating Characteristic ◽  
Predictive Accuracy ◽  
Characteristic Curve ◽  
Venous Drainage ◽  
Martin Grade ◽  
Operating Characteristic Curve ◽  
Cerebral Avms ◽  
Cerebellar Anatomy ◽  
Better Than

ABSTRACT BACKGROUND: Anatomic diversity among cerebellar arteriovenous malformations (AVMs) calls for a classification that is intuitive and surgically informative. Selection tools like the Spetzler-Martin grading system are designed to work best with cerebral AVMs but have shortcomings with cerebellar AVMs. OBJECTIVE: To define subtypes of cerebellar AVMs that clarify anatomy and surgical management, to determine results according to subtypes, and to compare predictive accuracies of the Spetzler-Martin and supplementary systems. METHODS: From a consecutive surgical series of 500 patients, 60 had cerebellar AVMs, 39 had brainstem AVMs and were excluded, and 401 had cerebral AVMs. RESULTS: Cerebellar AVM subtypes were as follows: 18 vermian, 13 suboccipital, 12 tentorial, 12 petrosal, and 5 tonsillar. Patients with tonsillar and tentorial AVMs fared best. Cerebellar AVMs presented with hemorrhage more than cerebral AVMs (P < .001). Cerebellar AVMs were more likely to drain deep (P = .04) and less likely to be eloquent (P < .001). The predictive accuracy of the supplementary grade was better than that of the Spetzler-Martin grade with cerebellar AVMs (areas under the receiver-operating characteristic curve, 0.74 and 0.59, respectively). The predictive accuracy of the supplementary system was consistent for cerebral and cerebellar AVMs, whereas that of the Spetzler-Martin system was greater with cerebral AVMs. CONCLUSION: Patients with cerebellar AVMs present with hemorrhage more often than patients with cerebral AVMs, justifying an aggressive treatment posture. The supplementary system is better than the Spetzler-Martin system at predicting outcomes after cerebellar AVM resection. Key components of the Spetzler-Martin system such as venous drainage and eloquence are distorted by cerebellar anatomy in ways that components of the supplementary system are not.

Effect of Implementing Quantitative Blood Loss Assessment at the Time of Delivery

2019 ◽  
Vol 36 (13) ◽  
pp. 1332-1336
Author(s):  
Elizabeth Coviello ◽  
Sara Iqbal ◽  
Tetsuya Kawakita ◽  
Rebecca Chornock ◽  
Megan Cheney ◽  
...  
Keyword(s):  
Blood Transfusion ◽  
Blood Loss ◽  
Chart Review ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Vital Signs ◽  
Retrospective Chart Review ◽  
Loss Assessment ◽  
Estimated Blood Loss ◽  
Better Than

Objective To evaluate the ability of estimated blood loss (EBL) and quantitative blood loss (qBL) to predict need for blood transfusion in women with postpartum hemorrhage (PPH). Study Design This is a retrospective chart review that identified women with PPH (>1,000 mL for vaginal or cesarean delivery) between September 2014 and August 2015, reported by EBL (n = 92), and October 2015 and September 2016, reported by qBL (n = 374). The primary metric was the area under the receiver-operating characteristic curve for blood transfusion. Results The rate of PPH by EBL and qBL was 2.8 and 10.8%, respectively (p < 0.01). The rate of transfusion for women meeting criteria for PPH by EBL and QBL were 2% (66/3,307) and 2.7% (93/3,453), respectively (p = 0.06). Postpartum transfusion was predicted by an EBL of 1,450 mL with AUC 0.826 and qBL 1,519 mL with AUC 0.764, for all modes of delivery. Postpartum vital signs and change in pre- and postdelivery hematocrit were poor predictors for transfusion. Conclusion The rates of PPH increased with the implementation of qBL. Overall, qBL did not perform better than EBL in predicting the need for blood transfusion.

scholarly journals 2476

2017 ◽  
Vol 1 (S1) ◽  
pp. 19-19
Author(s):  
Samuel David Zetumer ◽  
Hobart Harris
Keyword(s):  
Operating Characteristic ◽  
Learning Algorithm ◽  
Characteristic Curve ◽  
High Sensitivity ◽  
Exploratory Laparotomy ◽  
Machine Learning Algorithm ◽  
Regression Algorithms ◽  
Study Population ◽  
Operating Characteristic Curve ◽  
Better Than

OBJECTIVES/SPECIFIC AIMS: Historically, logistic regression algorithms (LRAs) have failed to differentiate strangulated small bowel obstructions (SBOs) from nonstrangulated SBOs. Our hypothesis is that a machine learning algorithm (MLA) can differentiate strangulated from simple SBOs better than an LRA can. METHODS/STUDY POPULATION: We used records of patients presenting with acute SBO and managed with exploratory laparotomy to test and train algorithms. We compared MLA to LRA via area under the receiver operating characteristic curve (AUROC) and cut-off points maximizing sensitivity and specificity. RESULTS/ANTICIPATED RESULTS: With 192 patient records, the AUROC of the MLA was 0.85. At the sensitivity cutoff, the MLA had 100% sensitivity and 55% specificity. At the specificity cutoff, the MLA had 45% sensitivity and 100% specificity. We anticipate improvements as more records are incorporated, and that LRA will underperform MLA across all measures. DISCUSSION/SIGNIFICANCE OF IMPACT: Our MLA represents a significant improvement over past LRAs, and may provide decision assistance to surgeons managing SBO. If this MLA maintains its high sensitivity, it may be used in the future to prevent unnecessary surgeries.

Evaluation of PR3- and MPO-ANCA line and dot immunoassays in ANCA-associated vasculitis

Rheumatology ◽  
2020 ◽  
Author(s):  
Nina Kempiners ◽  
Juliane Mahrhold ◽  
Bernhard Hellmich ◽  
Elena Csernok
Keyword(s):  
Operating Characteristic ◽  
Characteristic Curve ◽  
Area Under The Curve ◽  
Test Method ◽  
Detection Methods ◽  
First Line ◽  
Anca Associated Vasculitis ◽  
Line Test ◽  
High Degree ◽  
Better Than

Abstract Objective This study was performed to evaluate the diagnostic accuracy of novel line and dot immunoassays for detection of MPO and PR3 ANCA. Methods Sera from 50 patients with ANCA-associated vasculitis (AAV), including granulomatosis with polyangiitis and microscopic polyangiitis, and from 45 disease controls were tested by IIF and for the presence of PR3-ANCA and MPO-ANCA by four different line or dot immunoassays, as well as by a chemiluminescence immunoassay. Results The area under the curve of the receiver operating characteristic curve to discriminate AAV from controls was 0.858 (95% CI 0.785–0.931) for the IIF method. For the antigen-specific immunoassays, the area under the curve varied between 0.869 (95% CI 0.797–0.941) and 0.936 (95% 0.886–0.985). Conclusions Our comparison of various ANCA detection methods showed a high degree of diagnostic precision for all of the PR3- and MPO-ANCA line and dot immunoassays investigated. The performance was equal to or better than the performance of IIF. These results indicate that novel line and dot immunoassays can serve as a first-line test method in patients with the suspected diagnosis of AAV.

Value of image-pro plus for assisting virtual touch tissue imaging in the diagnosis of thyroid nodules

2020 ◽  
pp. 1-9
Author(s):  
Kai-Mei Lian ◽  
Teng Lin
Keyword(s):  
Gold Standard ◽  
Diagnostic Performance ◽  
Operating Characteristic ◽  
Thyroid Nodules ◽  
Characteristic Curve ◽  
Diagnostic Value ◽  
Tissue Imaging ◽  
Operating Characteristic Curve ◽  
Virtual Touch Tissue Imaging ◽  
Better Than

Purpose: The value of virtual touch tissue imaging (VTI) with support of Image-Pro Plus (IPP) for diagnosing malignant thyroid tumors was assessed in the present study. Methods: In this retrospective study, we enrolled 160 patients with 198 thyroid nodules. TI-RADS, VTI grade, and VTI with support of IPP (VTI-IPP) were underwent for each nodule. With the pathological diagnosis as the gold standard, the receiver-operating characteristic curve (ROC) was drawn to evaluate the diagnostic performance of VTI-IPP, VTI, TI-RADS, VTI-IPP combinate with TI-RADS in thyroid carcinoma. Results: VTI-IPP score >2, VTI score >3, TI-RADS score >1, and VTI-IPP combine with TI-RADS score >4 expressed the highest diagnostic value for malignant thyroid nodules, the areas under the curve (AUC) were 0.939, 0.905, 0.925, and 0.967, respectively. The combination indicated the largest AUC, compared with VTI-IPP and TI-RADS, respectively (P = 0.0054 and 0.0009). The performance of VTI-IPP in diagnosing thyroid carcinomas was better than VTI (P = 0.0321). Conclusion: Compare with VTI, VTI-IPP exhibited more excellent value in distinguishing between benign and malignant thyroid nodules. The value of malignant thyroid nodules diagnosis can be improved when VTI-IPP combines with TI-RADS.

scholarly journals Beta-D-Glucan for Diagnosing Pneumocystis Pneumonia: a Direct Comparison between the Wako β-Glucan Assay and the Fungitell Assay

2019 ◽  
Vol 57 (6) ◽  
Author(s):  
Toine Mercier ◽  
Ellen Guldentops ◽  
Sofie Patteet ◽  
Kurt Beuselinck ◽  
Katrien Lagrou ◽  
...  
Keyword(s):  
Bronchoalveolar Lavage ◽  
Diagnostic Performance ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Pneumocystis Pneumonia ◽  
Radiological Findings ◽  
Sample Testing ◽  
Overall Performance ◽  
Operating Characteristic Curve ◽  
Better Than

ABSTRACT Measuring serum beta-d-glucan (BDG) is a useful tool for supporting a quantitative PCR (qPCR)-based diagnosis of suspected Pneumocystis pneumonia (PCP) with bronchoalveolar lavage (BAL) fluid. Since the 2000s, the Fungitell assay was the only BDG assay which was FDA cleared and Conformité Européenne (CE) marked. However, the Wako β-glucan test was also recently CE marked and commercialized. We analyzed archived sera from 116 PCP cases (who were considered to have PCP based on compatible clinical and radiological findings plus a BAL fluid qPCR threshold cycle value of ≤28) and 114 controls (those with a BAL fluid qPCR threshold cycle value of >45 and no invasive fungal infection) using the Fungitell and Wako assays in parallel and assessed their diagnostic performance using the manufacturer’s proposed cutoffs of 80 pg/ml and 11 pg/ml, respectively. We found the Wako assay to be more specific (0.98 versus 0.87, P < 0.001) and the Fungitell assay to be more sensitive (0.78 versus 0.85, P = 0.039) at the proposed cutoffs. Overall performance, as determined by the area under the receiver operating characteristic curve, was similar for both assays. We determined a new Wako assay cutoff (3.616 pg/ml) to match the sensitivity of the Fungitell assay (0.88 at a cutoff of ≥60 pg/ml). Using this newly proposed cutoff, the specificity of the Wako assay was significantly better than that of the Fungitell assay (0.89 versus 0.82, P = 0.011). In conclusion, the Wako assay performed excellently compared to the Fungitell assay for the diagnosis of presumed PCP based on qPCR. In addition, contrary to the Fungitell assay, the Wako assay allows for single-sample testing with lower inter- and intrarun variability. Finally, we propose an optimized cutoff for the Wako assay to reliably exclude PCP.

Sign in / Sign up

Export Citation Format

Share Document