Learn More
  • C E Metz
  • 1978
The limitations of diagnostic "accuracy" as a measure of decision performance require introduction of the concepts of the "sensitivity" and "specificity" of a diagnostic test. These measures and the related indices, "true positive fraction" and "false positive fraction," are more meaningful than "accuracy," yet do not provide a unique description of(More)
We show that truth-state runs in rank-ordered data constitute a natural categorization of continuously-distributed test results for maximum likelihood (ML) estimation of ROC curves. On this basis, we develop two new algorithms for fitting binormal ROC curves to continuously-distributed data: a true ML algorithm (LABROC4) and a quasi-ML algorithm (LABROC5)(More)
If the performance of a diagnostic imaging system is to be evaluated objectively and meaningfully, one must compare radiologists' image-based diagnoses with actual states of disease and health in a way that distinguishes between the inherent diagnostic capacity of the radiologists' interpretations of the images, and any tendencies to "under-read" or(More)
The authors investigated the potential utility of artificial neural networks as a decision-making aid to radiologists in the analysis of mammographic data. Three-layer, feed-forward neural networks with a back-propagation algorithm were trained for the interpretation of mammograms on the basis of features extracted from mammograms by experienced(More)
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(More)
The authors propose a new generalized method for ROC-curve fitting and statistical testing that allows researchers to utilize all of the data collected in an experimental comparison of two diagnostic modalities, even if some patients have not been studied with both modalities. Their new algorithm, ROCKIT, subsumes previous algorithms as special cases. It(More)
We present a new technique based on the method developed by Metz and Fencil for estimation of the 3D imaging geometry and 3D object configurations from biplane angiographic acquisitions. The new method employs the 3D configuration of points calculated by the Metz-Fencil technique as an initial estimate. A 3D Procrustes algorithm is employed to translate,(More)
Relatively simple, but important, detection tasks in radiology are nearing accessibility to computer-aided diagnostic (CAD) methods. The authors have studied one such task, the detection of clustered microcalcifications on mammograms, to determine whether CAD can improve radiologists' performance under controlled but generally realistic circumstances. The(More)
PURPOSE To evaluate, by using computer image analysis, the mammographic density patterns of women with germ-line mutations in BRCA1 and BRCA2 genes in comparison with those of women at low risk of developing breast cancer. MATERIALS AND METHODS Mammograms from 30 carriers of BRCA1 and BRCA2 mutations and from 142 low-risk women were collected(More)