Some practical issues of experimental design and data analysis in radiological ROC studies.
ABSTRACT Receiver operating characteristic (ROC) analysis has been used in a broad variety of medical imaging studies during the past 15 years, and its advantages over more traditional measures of diagnostic performance are now clearly established. But despite the essential simplicity of the approach, workers in the field often find--sometimes only after an ROC study is under way--that a number of subtle issues related to experimental design and data analysis must be confronted in practice. Many of these issues have not been discussed in the literature in detail, and most are not well known. The purposes of this paper are to make users of ROC methodology in medical imaging aware of potential problems that should be confronted before an ROC study is begun and to indicate, at least broadly, how those problems may be dealt with, given the present state of the art. Some of the issues raised here can be addressed adequately by easily prescribed techniques, whereas others remain difficult and will be resolved fully only by new methodologic developments.
- SourceAvailable from: Gary S Collins[Show abstract] [Hide abstract]
ABSTRACT: Different methods of evaluating diagnostic performance when comparing diagnostic tests may lead to different results. We compared two such approaches, sensitivity and specificity with area under the Receiver Operating Characteristic Curve (ROC AUC) for the evaluation of CT colonography for the detection of polyps, either with or without computer assisted detection.PLoS ONE 01/2014; 9(10):e107633. · 3.53 Impact Factor
- [Show abstract] [Hide abstract]
ABSTRACT: IntroductionMammographic density is similar among women at risk of either sporadic or BRCA1/2-related breast cancer. It has been suggested that digitized mammographic images contain computer-extractable information within the parenchymal pattern, which may contribute to distinguishing between BRCA1/2 mutation carriers and non-carriers.Methods We compared mammographic texture pattern features in digitized mammograms from women with deleterious BRCA1/2 mutations (n¿=¿137) versus non-carriers (n¿=¿100). Subjects were stratified into training (107 carriers, 70 non-carriers) and testing (30 carriers, 30 non-carriers) datasets. Masked to mutation status, texture features were extracted from a retro-areolar region-of-interest in each subject¿s digitized mammogram. Stepwise linear regression analysis of the training dataset identified variables to be included in a radiographic texture analysis (RTA) classifier model aimed at distinguishing BRCA1/2 carriers from non-carriers. The selected features were combined using a Bayesian Artificial Neural Network (BANN) algorithm, which produced a probability score rating the likelihood of each subject¿s belonging to the mutation-positive group. These probability scores were evaluated in the independent testing dataset to determine whether their distribution differed between BRCA1/2 mutation carriers and non-carriers. A receiver operating characteristic analysis was performed to estimate the model¿s discriminatory capacity.ResultsIn the testing dataset, a one standard deviation (SD) increase in the probability score from the BANN-trained classifier was associated with a two-fold increase in the odds of predicting BRCA1/2 mutation status: unadjusted odds ratio (OR)¿=¿2.00, 95% confidence interval (CI): 1.59, 2.51, P¿=¿0.02; age-adjusted OR¿=¿1.93, 95% CI: 1.53, 2.42, P¿=¿0.03. Additional adjustment for percent mammographic density did little to change the OR. The area under the curve for the BANN-trained classifier to distinguish between BRCA1/2 mutation carriers and non-carriers was 0.68 for features alone and 0.72 for the features plus percent mammographic density.Conclusions Our findings suggest that, unlike percent mammographic density, computer-extracted mammographic texture pattern features are associated with carrying BRCA1/2 mutations. Although still at an early stage, our novel RTA classifier has potential for improving mammographic image interpretation by permitting real-time risk stratification among women undergoing screening mammography.Breast cancer research: BCR 08/2014; 16(4):424. · 5.87 Impact Factor
- [Show abstract] [Hide abstract]
ABSTRACT: The most efficient imaging techniques for the early detection and diagnosis of breast cancer in woman is mammography. Microcalcification is the earliest sign of breast carcinomas and their detection is one of the key issues for breast cancer control. Their small size makes their detection complex for the radiologist. This brings in the role of CAD (Computer Aided Diagnosis) which serves as an assistant to the radiologist. One of the most powerful computing methods is the use of multiresolution analysis of digitized mammogram images with wavelet transform as foundation tool. The proposed Microcalcification detection method involves image denoising using wavelet-based multiscale product thresholding, image enhancement by adaptive operator integrated in the wavelet domain and Microcalcification detection using neural network has been combined with wavelet. Preliminary results indicate that the possible Microcalcifications are detected precisely and efficiently.