scholarly journals Study of classification of breast lesions using texture GLCM features obtained from the raw ultrasound signal

2020 ◽  
Author(s):  
Mariusz Nieniewski ◽  
Leszek J. Chmielewski
Keyword(s):  
Logistic Regression ◽  
Decision Trees ◽  
Regression Models ◽  
Confidence Region ◽  
Texture Features ◽  
Stepwise Logistic Regression ◽  
Breast Lesions ◽  
Operating Characteristics ◽  
Rf Signals

Most of the methods of classification of breast lesions in ultrasound (US) images have been tested on B-mode images from the commercial equipment.  The new possibility of further analysis of this  problem showed up with the availability of a public database containing original raw  radio frequency (RF) signals. In particular, it appeared  that the original texture might contain  diagnostic information which could be modified in the typical image processing and which is more difficult  to perceive than the  details of  lesion shape/contour. In this paper a  detailed analysis of the lesion texture is conducted by means of the decision trees and  logistic regression. The decision trees turned out  useful mainly for selecting texture features to be used in the stepwise logistic regression. The RF signals database of 200 breast lesions  was used for testing the performance of the benign vs malignant lesion classifier. The Gray Level Cooccurrence Matrix (GLCM)  was calculated with the vertical/horizontal offset of up to five pixels. For each of these matrices six features were calculated resulting in a total of 210 features. Using these features a sufficient number of decision trees were generated to calculate pseudo-Receiver Operating Characteristics (ROCs). The outcome of this  process is a collection of generated trees for which the employed features are known. These features were then used for generating  generalized linear model by means of stepwise logistic regression. The analyzed regression  models included the coefficients of up-to-the second degree terms. The texture features were further completed by a single shape feature,  that is tumor circularity (TC). The automatic procedure for finding the exact mask of a lesion is also provided for the conditions when the acoustic shadowing makes it impossible to obtain the entire contour reliably and a half-contour has to be used. The selected logistic regression models gave  ROCs with the Area Under Curve (AUC) of up to 0.83 and the 95 \% confidence region (0.63 0.96). Analyzing classification results one comes to the conclusion that the tumor circularity, which is the most informative  among shape/contour features, is not essential against the background of textural features. The reported study shows that a relatively straightforward procedure can be employed  to obtain  benign vs malignant  classifier comparable with that originally used for the database of the raw RF signals and based on the more complicated segmentation of the parameter maps of homodyned K distribution.

scholarly journals Classification of breast lesions in ultrasonography using sparse logistic regression and morphology-based texture features

2018 ◽  
Vol 45 (9) ◽  
pp. 4112-4124 ◽  
Author(s):  
Hoda Nemat ◽  
Hamid Fehri ◽  
Nasrin Ahmadinejad ◽  
Alejandro F. Frangi ◽  
Ali Gooya
Keyword(s):  
Logistic Regression ◽  
Texture Features ◽  
Breast Lesions ◽  
Sparse Logistic Regression

scholarly journals Risk Assessment Models for Wheat Fusarium Head Blight Epidemics Based on Within-Season Weather Data

2003 ◽  
Vol 93 (4) ◽  
pp. 428-435 ◽  
Author(s):  
E. D. De Wolf ◽  
L. V. Madden ◽  
P. E. Lipps
Keyword(s):  
Logistic Regression ◽  
Relative Humidity ◽  
Fusarium Head Blight ◽  
Prediction Accuracy ◽  
Regression Models ◽  
Weather Conditions ◽  
Predictor Variables ◽  
Stepwise Logistic Regression ◽  
Head Blight ◽  
Logistic Regression Models

Logistic regression models for wheat Fusarium head blight were developed using information collected at 50 location-years, including four states, representing three different U.S. wheat-production regions. Non-parametric correlation analysis and stepwise logistic regression analysis identified combinations of temperature, relative humidity, and rainfall or durations of specified weather conditions, for 7 days prior to anthesis, and 10 days beginning at crop anthesis, as potential predictor variables. Prediction accuracy of developed logistic regression models ranged from 62 to 85%. Models suitable for application as a disease warning system were identified based on model prediction accuracy, sensitivity, specificity, and availability of weather variables at crop anthesis. Four of the identified models correctly classified 84% of the 50 location-years. A fifth model that used only pre-anthesis weather conditions correctly classified 70% of the location-years. The most useful predictor variables were the duration (h) of precipitation 7 days prior to anthesis, duration (h) that temperature was between 15 and 30°C 7 days prior to anthesis, and the duration (h) that temperature was between 15 and 30°C and relative humidity was greater than or equal to 90%. When model performance was evaluated with an independent validation set (n = 9), prediction accuracy was only 6% lower than the accuracy for the original data sets. These results indicate that narrow time periods around crop anthesis can be used to predict Fusarium head blight epidemics.

scholarly journals Early detection of Alzheimer’s disease with a total score of the German CERAD

2010 ◽  
Vol 16 (5) ◽  
pp. 910-920 ◽  
Author(s):  
MICHAEL M. EHRENSPERGER ◽  
MANFRED BERRES ◽  
KIRSTEN I. TAYLOR ◽  
ANDREAS U. MONSCH
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Logistic Regression ◽  
Correct Classification ◽  
Operating Characteristics ◽  
Healthy Control ◽  
Neuropsychological Assessment Battery ◽  
State Examination

AbstractThe goal of the present study was to evaluate the diagnostic discriminability of three different global scores for the German version of the Consortium to Establish a Registry on Alzheimer’s Disease-Neuropsychological Assessment Battery (CERAD-NAB). The CERAD-NAB was administered to 1100 healthy control participants [NC; Mini-Mental State Examination (MMSE) mean = 28.9] and 352 patients with very mild Alzheimer’s disease (AD; MMSE mean = 26.1) at baseline and subsets of participants at follow-up an average of 2.4 (NC) and 1.2 (AD) years later. We calculated the following global scores: Chandler et al.’s (2005) score (summed raw scores), logistic regression on principal components analysis scores (PCA-LR), and logistic regression on demographically corrected CERAD-NAB variables (LR). Correct classification rates (CCR) were compared with areas under the receiver operating characteristics curves (AUC). The CCR of the LR score (AUC = .976) exceeded that of the PCA-LR, while the PCA-LR (AUC = .968) and Chandler (AUC = .968) scores performed comparably. Retest data improved the CCR of the PCA-LR and Chandler (trend) scores. Thus, for the German CERAD-NAB, Chandler et al.’s total score provided an effective global measure of cognitive functioning, whereby the inclusion of retest data tended to improve correct classification of individual cases. (JINS, 2010, 16, 910–920.)

Zone-specific logistic regression models improve classification of prostate cancer on multi-parametric MRI

2015 ◽  
Vol 25 (9) ◽  
pp. 2727-2737 ◽  
Author(s):  
Nikolaos Dikaios ◽  
Jokha Alkalbani ◽  
Mohamed Abd-Alazeez ◽  
Harbir Singh Sidhu ◽  
Alex Kirkham ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Logistic Regression ◽  
Regression Models ◽  
Logistic Regression Models

scholarly journals Hemodynamic–morphological discriminant models for intracranial aneurysm rupture remain stable with increasing sample size

2014 ◽  
Vol 8 (1) ◽  
pp. 104-110 ◽  
Author(s):  
Jianping Xiang ◽  
Jihnhee Yu ◽  
Kenneth V Snyder ◽  
Elad I Levy ◽  
Adnan H Siddiqui ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
Intracranial Aneurysm ◽  
Sample Size ◽  
Regression Models ◽  
Prediction Models ◽  
Flow Simulation ◽  
Aneurysm Rupture ◽  
Hemodynamic Parameters ◽  
Operating Characteristics

BackgroundWe previously established three logistic regression models for discriminating intracranial aneurysm rupture status based on morphological and hemodynamic analysis of 119 aneurysms. In this study, we tested if these models would remain stable with increasing sample size, and investigated sample sizes required for various confidence levels (CIs).MethodsWe augmented our previous dataset of 119 aneurysms into a new dataset of 204 samples by collecting an additional 85 consecutive aneurysms, on which we performed flow simulation and calculated morphological and hemodynamic parameters, as done previously. We performed univariate significance tests on these parameters, and multivariate logistic regression on significant parameters. The new regression models were compared against the original models. Receiver operating characteristics analysis was applied to compare the performance of regression models. Furthermore, we performed regression analysis based on bootstrapping resampling statistical simulations to explore how many aneurysm cases were required to generate stable models.ResultsUnivariate tests of the 204 aneurysms generated an identical list of significant morphological and hemodynamic parameters as previously (from the analysis of 119 cases). Furthermore, multivariate regression analysis produced three parsimonious predictive models that were almost identical to the previous ones, with model coefficients that had narrower CIs than the original ones. Bootstrapping showed that 10%, 5%, 2%, and 1% convergence levels of CI required 120, 200, 500, and 900 aneurysms, respectively.ConclusionsOur original hemodynamic–morphological rupture prediction models are stable and improve with increasing sample size. Results from resampling statistical simulations provide guidance for designing future large multi-population studies.

scholarly journals Untargeted Fecal Metabolomics to Investigate the Role of the Microbiome and Nutrients in Osteoarthritis

2021 ◽  
Vol 5 (Supplement_2) ◽  
pp. 47-47
Author(s):  
Blake Rushing ◽  
Susan McRitchie ◽  
Liubov Arbeeva ◽  
Amanda Nelson ◽  
M. Andrea Azcarate-Peril ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Regression Models ◽  
Intestinal Inflammation ◽  
Stepwise Logistic Regression ◽  
Microbial Metabolites ◽  
Leaky Gut ◽  
Microbial Composition ◽  
Fecal Samples ◽  
Logistic Regression Models

Abstract Objectives The objective of this study was to determine if perturbations in gut microbial composition and the gut metabolome could be linked to individuals with obesity and osteoarthritis (OA). Methods Fecal samples were collected from 92 participants with obesity recruited from the Johnston County Osteoarthritis Project. OA cases (n = 59) had radiographic hand plus knee OA, defined as involvement of at least 3 joints across both hands, and a Kellgren-Lawrence (KL) grade 2–4 in at least one knee. Controls (n = 33) were without hand OA and with KL grade 0–1 knees. Fecal metabolomes were analyzed by a UHPLC/Q Exactive HFx mass spectrometer. Microbiome composition was determined in fecal samples by 16S ribosomal RNA amplicon sequencing (rRNA-seq). Stepwise logistic regression models were built to determine predictors of OA status. Spearman correlations were performed to determine associations between metabolites and microbiota in OA or healthy individuals. Results Untargeted metabolomics analysis indicated that OA cases had significantly higher levels of di- and tri-peptides (P < 0.05), and significant perturbations (P < 0.1) in microbial metabolites. Pathway analysis revealed several significantly perturbed pathways (P < 0.05) associated with OA, including leukotriene metabolism, amino acid metabolism and fatty acid utilization. Logistic regression models selected metabolites associated with the microbiota and leaky gut syndrome as significant predictors of OA status, particularly when combined with the 16S rRNA sequencing data. Omega-3/6 polyunsaturated fatty acids (PUFAs) levels were significantly correlated with the phyla Bacteriodetes and Firmicutes. Conclusions Adults with obesity and OA have distinct fecal metabolomes characterized by perturbations in microbial metabolites, PUFAs, and protein digestion compared with healthy controls. These metabolic perturbations suggest a role of intestinal inflammation and leaky gut in OA. Funding Sources Supported by the Arthritis Foundation, the National Center for Advancing Translational Sciences (NCATS) (UL1TR002489), and the National Institute of Arthritis and Musculoskeletal and Skin Diseases (P30AR072580).

scholarly journals ANALYSIS OF SINGLE AND ENSEMBLE MACHINE LEARNING CLASSIFIERS FOR PHISHING ATTACKS DETECTION

2021 ◽  
Vol 7 (2) ◽  
pp. 44-49
Author(s):  
Oyelakin A. M ◽  
Alimi O. M ◽  
Mustapha I. O ◽  
Ajiboye I. K
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Random Forest ◽  
Decision Trees ◽  
Random Forest Algorithm ◽  
Ensemble Techniques ◽  
Learning Classifiers ◽  
Phishing Attacks ◽  
Ensemble Machine Learning

Phishing attacks have been used in different ways to harvest the confidential information of unsuspecting internet users. To stem the tide of phishing-based attacks, several machine learning techniques have been proposed in the past. However, fewer studies have considered investigating single and ensemble machine learning-based models for the classification of phishing attacks. This study carried out performance analysis of selected single and ensemble machine learning (ML) classifiers in phishing classification.The focus is to investigate how these algorithms behave in the classification of phishing attacks in the chosen dataset. Logistic Regression and Decision Trees were chosen as single learning classifiers while simple voting techniques and Random Forest were used as the ensemble machine learning algorithms. Accuracy, Precision, Recall and F1-score were used as performance metrics. Logistic Regression algorithm recorded 0.86 as accuracy, 0.89 as precision, 0.87 as recall and 0.81 as F1-score. Similarly, the Decision Trees classifier achieved an accuracy of 0.87, 0.83 for precision, 0.88 for recall and 0.81 for F1-score. In the voting ensemble, accuracy of 0.92 was achieved. 0.90 was obtained for precision, 0.92 for recall and 0.92 for F1-score. Random Forest algorithm recorded 0.98, 0.97, 0.98 and 0.97 as accuracy, precision, recall and F1-score respectively. From the experimental analyses, Random Forest algorithm outperformed simple averaging classifier and the two single algorithms used for phishing url detection. The study established that the ensemble techniques that were used for the experimentations are more efficient for phishing url identification compared to the single classifiers.  

Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models Based on Pre-Computation

2019 ◽  
Vol 16 (2) ◽  
pp. 217-230 ◽  
Author(s):  
Martine De Cock ◽  
Rafael Dowsley ◽  
Caleb Horst ◽  
Raj Katti ◽  
Anderson C. A. Nascimento ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Support Vector Machines ◽  
Decision Trees ◽  
Regression Models ◽  
Support Vector ◽  
Logistic Regression Models ◽  
Vector Machines

scholarly journals Regression Based Model for Prediction of Heart Disease Recumbent

2019 ◽  
Vol 8 (4) ◽  
pp. 6639-6642
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Heart Disease ◽  
Random Forest ◽  
Regression Models ◽  
The Other ◽  
Supervised Machine Learning ◽  
Input Output ◽  
Novel Method

Supervised Learning, a novel method that figures out how to anticipate the resultant of an input-output pair by inducting data under series of training and testing functions. Regression model is a sub classification of Supervised Machine Learning. In this paper various Regression models such as Logistic Regression, SVM, KNN, Naive Bayes and Random forest have been applied on Heart Disease dataset. The anticipated outcomes draw the deduction on the level of patients inclined to coronary illness dependent on the traits and qualities. In reference to the applied calculations both KNN and Random Forest beats the other relapse calculation with a precision of 88.52%

Sign in / Sign up

Export Citation Format

Share Document