Mammogram Analysis using League Championship Algorithm Optimized Ensembled FCRN Classifier

2017 ◽  
Vol 5 (2) ◽  
pp. 451 ◽  
Author(s):  
Saraswathi D ◽  
Srinivasan E
Keyword(s):  
Roc Curve ◽  
Operating Characteristic ◽  
Diagnostic System ◽  
Texture Features ◽  
Cad System ◽  
Trade Offs ◽  
Good Classification ◽  
Mammogram Image ◽  
The Given ◽  
Complex Valued

An intelligent mammogram diagnosis system can be very helpful for radiologist in detecting the abnormalities earlier than typical screening techniques. This paper investigates a new classification approach for detection of breast abnormalities in digital mammograms using League Championship Algorithm Optimized Ensembled Fully Complex valued Relaxation Network (LCA-FCRN). The proposed algorithm is based on extracting curvelet fractal texture features from the mammograms and classifying the suspicious regions by applying a pattern classifier. The whole system includes steps for pre-processing, feature extraction, feature selection and classification to classify whether the given input mammogram image is normal or abnormal. The method is applied to MIAS database of 322 film mammograms. The performance of the CAD system is analysed using Receiver Operating Characteristic (ROC) curve. This curve indicates the trade-offs between sensitivity and specificity that is available from a diagnostic system, and thus describes the inherent discrimination capacity of the proposed system. The result shows that the area under the ROC curve of the proposed algorithm is 0.985 with a sensitivity of 98.1% and specificity of 92.105%. Experimental results demonstrate that the proposed method can form an effective CAD system, and achieve good classification accuracy.

scholarly journals Statistical Assessment of Discrimination Capabilities of a Fractional Calculus Based Image Watermarking System for Gaussian Watermarks

Entropy ◽  
2021 ◽  
Vol 23 (2) ◽  
pp. 255
Author(s):  
Mario Gonzalez-Lee ◽  
Hector Vazquez-Leal ◽  
Luis J. Morales-Mendoza ◽  
Mariko Nakano-Miyatake ◽  
Hector Perez-Meana ◽  
...  
Keyword(s):  
Fractional Calculus ◽  
Roc Curve ◽  
Gaussian Noise ◽  
False Positive ◽  
Operating Characteristic ◽  
Image Watermarking ◽  
Area Under The Curve ◽  
Statistical Assessment ◽  
Watermarking Scheme ◽  
Fractional Equation

In this paper, we explore the advantages of a fractional calculus based watermarking system for detecting Gaussian watermarks. To reach this goal, we selected a typical watermarking scheme and replaced the detection equation set by another set of equations derived from fractional calculus principles; then, we carried out a statistical assessment of the performance of both schemes by analyzing the Receiver Operating Characteristic (ROC) curve and the False Positive Percentage (FPP) when they are used to detect Gaussian watermarks. The results show that the ROC of a fractional equation based scheme has 48.3% more Area Under the Curve (AUC) and a False Positives Percentage median of 0.2% whilst the selected typical watermarking scheme has 3%. In addition, the experimental results suggest that the target applications of fractional schemes for detecting Gaussian watermarks are as a semi-fragile image watermarking systems robust to Gaussian noise.

scholarly journals Presepsin values and prognostic nutritional index predict mortality in intensive care unit patients with sepsis: a pilot study

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Yuichiro Shimoyama ◽  
Osamu Umegaki ◽  
Noriko Kadono ◽  
Toshiaki Minami
Keyword(s):  
Multivariate Analysis ◽  
Roc Curve ◽  
Operating Characteristic ◽  
Prognostic Nutritional Index ◽  
Early Mortality ◽  
Curve Analysis ◽  
Rank Test ◽  
Roc Curve Analysis ◽  
Log Rank Test ◽  
Nutritional Index

Abstract Objective Sepsis is a major cause of mortality for critically ill patients. This study aimed to determine whether presepsin values can predict mortality in patients with sepsis. Results Receiver operating characteristic (ROC) curve analysis, Log-rank test, and multivariate analysis identified presepsin values and Prognostic Nutritional Index as predictors of mortality in sepsis patients. Presepsin value on Day 1 was a predictor of early mortality, i.e., death within 7 days of ICU admission; ROC curve analysis revealed an AUC of 0.84, sensitivity of 89%, and specificity of 77%; and multivariate analysis showed an OR of 1.0007, with a 95%CI of 1.0001–1.0013 (p = 0.0320).

Wideband Absorbance in Ears with Retraction Pockets and Cholesteatomas: A Preliminary Study

2021 ◽  
Author(s):  
Sreedevi Aithal ◽  
Venkatesh Aithal ◽  
Joseph Kei ◽  
Shane Anderson
Keyword(s):  
Prospective Study ◽  
Roc Curve ◽  
Operating Characteristic ◽  
Peak Pressure ◽  
Clinical Sample ◽  
Ambient Pressure ◽  
Control Group ◽  
Retraction Pockets ◽  
Preliminary Study ◽  
The Difference

Abstract Objectives The objective of this study was to describe wideband absorbance (WBA) findings in patients with cholesteatomas and retraction pockets (RPs). Design In this prospective study, tympanometry, audiometry, and wideband tympanometry (WBT) were performed on 27 ears with an RP (eight with epitympanic RP and 19 ears with mesotympanic RP), 39 ears with a cholesteatoma (23 ears with epitympanic and 16 ears with mesotympanic cholesteatomas [MCs]), and 49 healthy ears serving as controls. Results Mean WBA at ambient pressure (WBAamb) of both experimental groups was reduced significantly between 0.8 and 5 kHz relative to the control group. The difference between mean WBAamb and mean WBA at tympanometric peak pressure (WBATPP) was greater for the RP (0.12–0.16 between 0.5 and 1.5 kHz) than for the cholesteatoma group (0.03–0.11 between 0.6 and 3 kHz). Mean WBAamb of both epitympanic RP (ERP) and epitympanic cholesteatoma (EC) subgroups was significantly lower than that of the control group. Mean WBATPP of the ERP subgroup attained normal levels as per the control group, while mean WBATPP of EC subgroup was significantly lower than that of the control group at 0.8 to 1.5 kHz and 4 to 5 kHz. In contrast, both mesotympanic RP and MC subgroups demonstrated similar mean WBAamb and WBATPP values. No significant differences in WBAamb and WBATPP results between the RP and cholesteatomas groups were observed. Receiver operating characteristic (ROC) analyses indicated that the area under the ROC curve for distinguishing between the RP and cholesteatomas groups ranged from 0.44 to 0.60, indicating low accuracy in separating the two groups. Conclusion While it is not possible to distinguish between the RP and cholesteatomas groups based on the WBAamb and WBATPP results, it is potentially feasible to differentiate between the EC and ERP conditions. Further study using a large clinical sample is recommended to determine the sensitivity and specificity of the WBA test to identify the EC and ERP conditions.

Time-related changes in the diagnostic utility of total lactate dehydrogenase, lactate dehydrogenase isoenzyme-1, and two lactate dehydrogenase isoenzyme-1 ratios in serum after myocardial infarction

1990 ◽  
Vol 36 (7) ◽  
pp. 1317-1322 ◽  
Author(s):  
L V Galbraith ◽  
F Y Leung ◽  
G Jablonsky ◽  
A R Henderson
Keyword(s):  
Myocardial Infarction ◽  
Lactate Dehydrogenase ◽  
Likelihood Ratio ◽  
Roc Curve ◽  
Operating Characteristic ◽  
Negative Likelihood Ratio ◽  
Diagnostic Utility ◽  
Time Intervals ◽  
Dehydrogenase Isoenzyme ◽  
Cardiac Care Unit

Abstract Using receiver-operating characteristic (ROC) curve and likelihood ratio analysis, we examined the diagnostic utility of total lactate dehydrogenase (LD; EC 1.1.1.27) activity (I). LD isoenzyme-1 activity (II), and the LD-1 percentage of total LD activity (III), LD-1 LD-2 (IV), and LD-1/LD-4 (V) in 347 persons admitted to the Cardiac Care Unit (of whom 173 were subsequently proven to have had myocardial infarction). Blood was sampled from these subjects at about 6-h intervals for up to 96 h from the onset of chest pain. Defining an "effective" test as one having an area under the ROC curve of greater than or equal to 0.9, we determined the ranked utility (greatest to least) of these tests as V = IV greater than III greater than II greater than I. Tests III, IV, and V had by this criterion, diagnostic effectiveness equivalent to measurements of creatine kinase-2 in serum but in samples obtained at later time intervals. The decision thresholds for both high (constant) test sensitivity and specificity varied with time, to differing extents, over the entire 96-h period, a finding with important diagnostic implications. We document positive and negative likelihood ratio values for each of these tests throughout the entire period of study.

scholarly journals Roll-over test in primigravidae attending a public primary care service

1997 ◽  
Vol 115 (5) ◽  
pp. 1533-1536
Author(s):  
Luiz Francisco Marcopito
Keyword(s):  
Blood Pressure ◽  
Primary Care ◽  
Roc Curve ◽  
Operating Characteristic ◽  
Care Setting ◽  
Care Service ◽  
Primary Care Service ◽  
Pregnancy Induced Hypertension ◽  
Predictive Values ◽  
Induced Hypertension

OBJECTIVE:To determine the roll-over test (ROT) performance in predicting pregnancy-induced hypertension (PIH) in primigravidae aged 15-29 years in a public primary care service. METHOD: Prospective cohort study enrolling 369 consecutive and initially normotensive primigravidae. The ROT was applied within 28-32 weeks of pregnancy. PIH was defined as diastolic blood pressure (DBP) 90 mm Hg or systolic blood pressure (SBP) 140 mm Hg, or a rise in DBP 15 mm Hg or a rise in SBP 30 mm Hg. The ROT prognostic properties were calculated, and a receiver operating characteristic (ROC) curve was constructed. RESULTS: For the 20 mm Hg cutoff point, sensitivity was 20% and specificity was 93%. Positive and negative predictive values were, respectively, 23% and 92%, for a PIH cumulative incidence of 9.5%. With other cutoff points, the ROC curve showed a poor discriminatory value of the test. CONCLUSION: The ROT was not useful for predicting PIH in a primary prenatal care setting.

scholarly journals Development and validation of a prognostic model to predict clinical deterioration in hospitalized patients with COVID-19

2021 ◽  
Author(s):  
Javid Azadbakht ◽  
Sina Rashedi ◽  
Soheil Kooraki ◽  
Hamed Kowsari ◽  
Elnaz Tabibian
Keyword(s):  
Roc Curve ◽  
Scoring System ◽  
Prognostic Model ◽  
Operating Characteristic ◽  
Clinical Laboratory ◽  
External Validation ◽  
Clinical Deterioration ◽  
Roc Curve Analysis ◽  
Prospective Multicenter Study ◽  
Development And Validation

Abstract Objectives We aimed to develop and validate a prognostic model to predict clinical deterioration defined as either death or intensive care unit admission of hospitalized COVID-19 patients.Methods This prospective, multicenter study investigated 172 consecutive hospitalized COVID-19 patients who underwent a chest computed tomography (CT) scan between March 20 and April 30, 2020 (development cohort), as well as an independent sample of 40 consecutive patients for external validation (validation cohort). The clinical, laboratory, and radiologic data were gathered, and logistic regression along with receiver operating characteristic (ROC) curve analysis was performed.Results The overall clinical deterioration rates of the development and validation cohorts were 28.4% (49 of 172) and 30% (12 of 40), respectively. Seven predictors were included in the scoring system with a total score of 15: CT severity score\(\ge\)15 (Odds Ratio (OR)=6.34, 4 points), pleural effusion (OR = 6.80, 2 points), symptom onset to admission ≤ 6 days (OR = 2.44, 2 points), age\(\ge\)70 years (OR = 2.44, 2 points), diabetes mellitus (OR = 2.24, 2 points), dyspnea (OR = 2.17, 1.5 points), and abnormal leukocyte count (OR = 1.89, 1.5 points). The area under the ROC curve for the scoring system in the development and validation cohorts was 0.823 (CI [0.751–0.895]) and 0.558 (CI [0.340–0.775]), respectively.Conclusion This study provided a new easy-to-calculate scoring system with external validation for hospitalized COVID-19 patients to predict clinical deterioration based on a combination of seven clinical, laboratory, and radiologic parameters.

scholarly journals Evaluation of Ocular Biomechanical Indices to Distinguish Normal from Keratoconus Eyes

2012 ◽  
Vol 1 (3) ◽  
pp. 145-150
Author(s):  
Bernardo Lopes ◽  
Allan Luz ◽  
Bruno Fontes ◽  
Isaac C Ramos ◽  
Fernando Correia ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Receiver Operating Characteristic ◽  
Linear Model ◽  
Roc Curve ◽  
Operating Characteristic ◽  
Predictive Accuracy ◽  
Corneal Resistance Factor ◽  
Corneal Deformation ◽  
Eye Examination ◽  
The Individual

ABSTRACT Purpose To compare and assess the ability of pressure-derived parameters and corneal deformation waveform signal-derived parameters of the ocular response analyzer (ORA) measurement to distinguish between keratoconus and normal eyes, and to develop a combined parameter to optimize the diagnosis of keratoconus. Materials and methods One hundred and seventy-seven eyes (177 patients) with keratoconus (group KC) and 205 normal eyes (205 patients; group N) were included. One eye from each subject was randomly selected for analysis. Patients underwent a complete clinical eye examination, corneal topography (Humphrey ATLAS), tomography (Pentacam Oculus) and biomechanical evaluations (ORA Reichert). Differences in the distributions between the groups were assessed using the Mann- Whitney test. The receiver operating characteristic (ROC) curve was used to identify cutoff points that maximized sensitivity and specificity in discriminating keratoconus from normal corneas. Logistic regression was used to identify a combined linear model (Fisher 1.0). Results Significant differences in all studied parameters were detected (p < 0.05), except for W2. For the corneal resistance factor (CRF): Area under the ROC curve (AUROC) 89.1%, sensitivity 81.36%, specificity 84.88%. For the p1area: AUROC 91.5%, sensitivity 87.1%, specificity 81.95%. Of the individual parameters, the highest predictive accuracy was for the Fisher 1.0, which represents the combination of all parameters (AUROC 95.5%, sensitivity 88.14%, specificity 93.17%). Conclusion Waveform-derived ORA parameters displayed greater accuracy than pressure-derived parameters for identifying keratoconus. Corneal hysteresis (CH) and CRF, a diagnostic linear model that combines different parameters, provided the greatest accuracy for differentiating keratoconus from normal corneas. How to cite this article Luz A, Fontes B, Ramos IC, Lopes B, Correia F, Schor P, Ambrósio R. Evaluation of Ocular Biomechanical Indices to Distinguish Normal from Keratoconus Eyes. Int J Kerat Ect Cor Dis 2012;1(3):145-150.

Sign in / Sign up

Export Citation Format

Share Document