Improving breast cancer diagnosis with computer-aided diagnosis

TL;DR: Semiautomated analysis of aortoiliac 3D CE-MRA has the same high accuracy for detection and quantification of stenoses as conventional readings of CE- MRA.

TL;DR: For the computerized classification scheme studied, the cluster geometry was more effective in differentiating benign from malignant clusters than was the shape of individual microcalcification.

TL;DR: Results indicate an accurate method, which could be utilized in computer-aided diagnosis schemes of microcalcification clusters, based on microCalcification scale-space signature estimation, enabling robust scale selection for initialization of multiscale active contours.

TL;DR: The computer technique appears to maintain consistently high performance in classifying calcifications in FFDMs as malignant or benign without requiring substantial modification from its initial development on SFMs and appears to be robust with respect to variations in radiologists' input.

TL;DR: In this article, several methods of estimating error rates in discriminant analysis are evaluated by sampling methods, and two methods in most common use are found to be significantly poorer than some new methods that are proposed.

TL;DR: The effects of sample size on feature selection and error estimation for several types of classifiers are discussed and an emphasis is placed on giving practical advice to designers and users of statistical pattern recognition systems.

TL;DR: Two new algorithms for fitting binormal ROC curves to continuously-distributed data are developed: a true ML algorithm (LABROC4) and a quasi-ML algorithm (LabROC5) that requires substantially less computation with large data sets.