ABSTRACT
An audit of a breast imaging practice must be based on data with accepted definitions and rules so that the comparisons between breast imaging facilities and interpretive staff are comparable. The four basic data points for calculating these metrics are true positive (TP), true negative (TN), false positive (FP), and false negative (FN). For mammography, the definition of "true" is the presence of a proven malignancy within a year of the exam. The presence or absence of breast cancer within a year of the exam and an increase in patient mobility between different facilities may render the calculation of sensitivity and specificity difficult for most facilities unless a regional cancer registry is available.Thus, the metrics that can be easily calculated within a facility are recall rate (all the positive interpretations divided by all the exams read), positive predictive value (PPV) 1 = percentage of abnormal screening exams that result in a diagnosis of cancer within a year, PPV2 = percentage of all diagnostic exams recommended for biopsy and cancer discovered within a year, PPV3 = benign tissue diagnosis and no cancer within a year, and the cancer detection rate (the true positive exams per one thousand exams). Intuitively, one may assume that accuracy (TP + TN/TP + FP + TN + FN) is the best metric for an interpreter. However, this can produce spurious results. The most accurate method to determine a reader's skills is the use of the receiver operating characteristic (ROC) curve, which clearly presents, in graphic form, the relationship between the four basic data points.
ABSTRACT
PURPOSE: To develop a set of accurate 2D models of compressed breasts undergoing mammography or breast tomosynthesis, based on objective analysis, to accurately characterize mammograms with few linearly independent parameters, and to generate novel clinically realistic paired cranio-caudal (CC) and medio-lateral oblique (MLO) views of the breast. METHODS: We seek to improve on an existing model of compressed breasts by overcoming detector size bias, removing the nipple and non-mammary tissue, pairing the CC and MLO views from a single breast, and incorporating the pectoralis major muscle contour into the model. The outer breast shapes in 931 paired CC and MLO mammograms were automatically detected with an in-house developed segmentation algorithm. From these shapes three generic models (CC-only, MLO-only, and joint CC/MLO) with linearly independent components were constructed via principal component analysis (PCA). The ability of the models to represent mammograms not used for PCA was tested via leave-one-out cross-validation, by measuring the average distance error (ADE). RESULTS: The individual models based on six components were found to depict breast shapes with accuracy (mean ADE-CC = 0.81 mm, ADE-MLO = 1.64 mm, ADE-Pectoralis = 1.61 mm), outperforming the joint CC/MLO model (P ≤ 0.001). The joint model based on 12 principal components contains 99.5% of the total variance of the data, and can be used to generate new clinically realistic paired CC and MLO breast shapes. This is achieved by generating random sets of 12 principal components, following the Gaussian distributions of the histograms of each component, which were obtained from the component values determined from the images in the mammography database used. CONCLUSION: Our joint CC/MLO model can successfully generate paired CC and MLO view shapes of the same simulated breast, while the individual models can be used to represent with high accuracy clinical acquired mammograms with a small set of parameters. This is the first step toward objective 3D compressed breast models, useful for dosimetry and scatter correction research, among other applications.
