Elizabeth S. Burnside

The ACR BI-RADS® Experience: Learning From History

The Breast Imaging Reporting and Data System (BI-RADS) initiative, instituted by the ACR, was begun in the late 1980s to address a lack of standardization and uniformity in mammography practice reporting. An important component of the BI-RADS initiative is the lexicon, a dictionary of descriptors of specific imaging features. The BI-RADS lexicon has always been data driven, using descriptors that previously had been shown in the literature to be predictive of benign and malignant disease. Once established, the BI-RADS lexicon provided new opportunities for quality assurance, communication, research, and improved patient care. The history of this lexicon illustrates a series of challenges and instructive successes that provide a valuable guide for other groups that aspire to develop similar lexicons in the future.

Toward Best Practices in Radiology Reporting

The goals and current efforts of the Radiological Society of North America Radiology Reporting Committee are described. The committees charter provides an opportunity to improve the organization, content, readability, and usefulness of the radiology report and to advance the efficiency and effectiveness of the reporting process.

Probabilistic Computer Model Developed from Clinical Data in National Mammography Database Format to Classify Mammographic Findings

PURPOSE To determine whether a Bayesian network trained on a large database of patient demographic risk factors and radiologist-observed findings from consecutive clinical mammography examinations can exceed radiologist performance in the classification of mammographic findings as benign or malignant. MATERIALS AND METHODS The institutional review board exempted this HIPAA-compliant retrospective study from requiring informed consent. Structured reports from 48 744 consecutive pooled screening and diagnostic mammography examinations in 18 269 patients from April 5, 1999 to February 9, 2004 were collected. Mammographic findings were matched with a state cancer registry, which served as the reference standard. By using 10-fold cross validation, the Bayesian network was tested and trained to estimate breast cancer risk by using demographic risk factors (age, family and personal history of breast cancer, and use of hormone replacement therapy) and mammographic findings recorded in the Breast Imaging Reporting and Data System lexicon. The performance of radiologists compared with the Bayesian network was evaluated by using area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. RESULTS The Bayesian network significantly exceeded the performance of interpreting radiologists in terms of AUC (0.960 vs 0.939, P = .002), sensitivity (90.0% vs 85.3%, P < .001), and specificity (93.0% vs 88.1%, P < .001). CONCLUSION On the basis of prospectively collected variables, the evaluated Bayesian network can predict the probability of breast cancer and exceed interpreting radiologist performance. Bayesian networks may help radiologists improve mammographic interpretation.

An integrated approach to learning bayesian networks of rules

Inductive Logic Programming (ILP) is a popular approach for learning rules for classification tasks. An important question is how to combine the individual rules to obtain a useful classifier. In some instances, converting each learned rule into a binary feature for a Bayes net learner improves the accuracy compared to the standard decision list approach [3,4,14]. This results in a two-step process, where rules are generated in the first phase, and the classifier is learned in the second phase. We propose an algorithm that interleaves the two steps, by incrementally building a Bayes net during rule learning. Each candidate rule is introduced into the network, and scored by whether it improves the performance of the classifier. We call the algorithm SAYU for Score As You Use. We evaluate two structure learning algorithms Naive Bayes and Tree Augmented Naive Bayes. We test SAYU on four different datasets and see a significant improvement in two out of the four applications. Furthermore, the theories that SAYU learns tend to consist of far fewer rules than the theories in the two-step approach.

Optimal Breast Biopsy Decision-Making Based on Mammographic Features and Demographic Factors

Breast cancer is the most common non-skin cancer affecting women in the United States, where every year more than 20 million mammograms are performed. Breast biopsy is commonly performed on the suspicious findings on mammograms to confirm the presence of cancer. Currently, 700,000 biopsies are performed annually in the U.S.; 55%-85% of these biopsies ultimately are found to be benign breast lesions, resulting in unnecessary treatments, patient anxiety, and expenditures. This paper addresses the decision problem faced by radiologists: When should a woman be sent for biopsy based on her mammographic features and demographic factors? This problem is formulated as a finite-horizon discrete-time Markov decision process. The optimal policy of our model shows that the decision to biopsy should take the age of patient into account; particularly, an older patients risk threshold for biopsy should be higher than that of a younger patient. When applied to the clinical data, our model outperforms radiologists in the biopsy decision-making problem. This study also derives structural properties of the model, including sufficiency conditions that ensure the existence of a control-limit type policy and nondecreasing control-limits with age.

Informatics in Radiology: Comparison of Logistic Regression and Artificial Neural Network Models in Breast Cancer Risk Estimation

Computer models in medical diagnosis are being developed to help physicians differentiate between healthy patients and patients with disease. These models can aid in successful decision making by allowing calculation of disease likelihood on the basis of known patient characteristics and clinical test results. Two of the most frequently used computer models in clinical risk estimation are logistic regression and an artificial neural network. A study was conducted to review and compare these two models, elucidate the advantages and disadvantages of each, and provide criteria for model selection. The two models were used for estimation of breast cancer risk on the basis of mammographic descriptors and demographic risk factors. Although they demonstrated similar performance, the two models have unique characteristics-strengths as well as limitations-that must be considered and may prove complementary in contributing to improved clinical decision making.

Information Extraction for Clinical Data Mining: A Mammography Case Study

Breast cancer is the leading cause of cancer mortality in women between the ages of 15 and 54. During mammography screening, radiologists use a strict lexicon (BI-RADS) to describe and report their findings. Mammography records are then stored in a well-defined database format (NMD). Lately, researchers have applied data mining and machine learning techniques to these databases. They successfully built breast cancer classifiers that can help in early detection of malignancy. However, the validity of these models depends on the quality of the underlying databases. Unfortunately, most databases suffer from inconsistencies, missing data, inter-observer variability and inappropriate term usage. In addition, many databases are not compliant with the NMD format and/or solely consist of text reports. BI-RADS feature extraction from free text and consistency checks between recorded predictive variables and text reports are crucial to addressing this problem. We describe a general scheme for concept information retrieval from free text given a lexicon, and present a BI-RADS features extraction algorithm for clinical data mining. It consists of a syntax analyzer, a concept finder and a negation detector. The syntax analyzer preprocesses the input into individual sentences. The concept finder uses a semantic grammar based on the BI-RADS lexicon and the experts’ input. It parses sentences detecting BI-RADS concepts. Once a concept is located, a lexical scanner checks for negation. Our method can handle multiple latent concepts within the text, filtering out ultrasound concepts. On our dataset, our algorithm achieves 97.7% precision, 95.5% recall and an F1-score of 0.97. It outperforms manual feature extraction at the 5% statistical significance level.

Quantitative MRI radiomics in the prediction of molecular classifications of breast cancer subtypes in the TCGA/TCIA data set.

Using quantitative radiomics, we demonstrate that computer-extracted magnetic resonance (MR) image-based tumor phenotypes can be predictive of the molecular classification of invasive breast cancers. Radiomics analysis was performed on 91 MRIs of biopsy-proven invasive breast cancers from National Cancer Institute’s multi-institutional TCGA/TCIA. Immunohistochemistry molecular classification was performed including estrogen receptor, progesterone receptor, human epidermal growth factor receptor 2, and for 84 cases, the molecular subtype (normal-like, luminal A, luminal B, HER2-enriched, and basal-like). Computerized quantitative image analysis included: three-dimensional lesion segmentation, phenotype extraction, and leave-one-case-out cross validation involving stepwise feature selection and linear discriminant analysis. The performance of the classifier model for molecular subtyping was evaluated using receiver operating characteristic analysis. The computer-extracted tumor phenotypes were able to distinguish between molecular prognostic indicators; area under the ROC curve values of 0.89, 0.69, 0.65, and 0.67 in the tasks of distinguishing between ER+ versus ER−, PR+ versus PR−, HER2+ versus HER2−, and triple-negative versus others, respectively. Statistically significant associations between tumor phenotypes and receptor status were observed. More aggressive cancers are likely to be larger in size with more heterogeneity in their contrast enhancement. Even after controlling for tumor size, a statistically significant trend was observed within each size group (P=0.04 for lesions ⩽2 cm; P=0.02 for lesions >2 to ⩽5 cm) as with the entire data set (P-value=0.006) for the relationship between enhancement texture (entropy) and molecular subtypes (normal-like, luminal A, luminal B, HER2-enriched, basal-like). In conclusion, computer-extracted image phenotypes show promise for high-throughput discrimination of breast cancer subtypes and may yield a quantitative predictive signature for advancing precision medicine.

Effects of Screening and Systemic Adjuvant Therapy on ER-Specific US Breast Cancer Mortality

BACKGROUND Molecular characterization of breast cancer allows subtype-directed interventions. Estrogen receptor (ER) is the longest-established molecular marker. METHODS We used six established population models with ER-specific input parameters on age-specific incidence, disease natural history, mammography characteristics, and treatment effects to quantify the impact of screening and adjuvant therapy on age-adjusted US breast cancer mortality by ER status from 1975 to 2000. Outcomes included stage-shifts and absolute and relative reductions in mortality; sensitivity analyses evaluated the impact of varying screening frequency or accuracy. RESULTS In the year 2000, actual screening and adjuvant treatment reduced breast cancer mortality by a median of 17 per 100000 women (model range = 13-21) and 5 per 100000 women (model range = 3-6) for ER-positive and ER-negative cases, respectively, relative to no screening and no adjuvant treatment. For ER-positive cases, adjuvant treatment made a higher relative contribution to breast cancer mortality reduction than screening, whereas for ER-negative cases the relative contributions were similar for screening and adjuvant treatment. ER-negative cases were less likely to be screen-detected than ER-positive cases (35.1% vs 51.2%), but when screen-detected yielded a greater survival gain (five-year breast cancer survival = 35.6% vs 30.7%). Screening biennially would have captured a lower proportion of mortality reduction than annual screening for ER-negative vs ER-positive cases (model range = 80.2%-87.8% vs 85.7%-96.5%). CONCLUSION As advances in risk assessment facilitate identification of women with increased risk of ER-negative breast cancer, additional mortality reductions could be realized through more frequent targeted screening, provided these benefits are balanced against screening harms.

Circulating serum xenoestrogens and mammographic breast density.

IntroductionHumans are widely exposed to estrogenically active phthalates, parabens, and phenols, raising concerns about potential effects on breast tissue and breast cancer risk. We sought to determine the association of circulating serum levels of these chemicals (reflecting recent exposure) with mammographic breast density (a marker of breast cancer risk).MethodsWe recruited postmenopausal women aged 55 to 70 years from mammography clinics in Madison, Wisconsin (N = 264). Subjects completed a questionnaire and provided a blood sample that was analyzed for mono-ethyl phthalate, mono-butyl phthalate, mono-benzyl phthalate, butyl paraben, propyl paraben, octylphenol, nonylphenol, and bisphenol A (BPA). Percentage breast density was measured from mammograms by using a computer-assisted thresholding method.ResultsSerum BPA was positively associated with mammographic breast density after adjusting for age, body mass index, and other potentially confounding factors. Mean percentage density was 12.6% (95% confidence interval (CI), 11.4 to 14.0) among the 193 women with nondetectable BPA levels, 13.7% (95% CI, 10.7 to 17.1) among the 35 women with detectable levels below the median (<0.55 ng/ml), and 17.6% (95% CI, 14.1 to 21.5) among the 34 women with detectable levels above the median (>0.55 ng/ml; Ptrend = 0.01). Percentage breast density was also elevated (18.2%; 95% CI, 13.4 to 23.7) among the 18 women with serum mono-ethyl phthalate above the median detected level (>3.77 ng/ml) compared with women with nondetectable BPA levels (13.1%; 95% CI, 11.9 to 14.3; Ptrend = 0.07). No other chemicals demonstrated associations with percentage breast density.ConclusionsPostmenopausal women with high serum levels of BPA and mono-ethyl phthalate had elevated breast density. Further investigation of the impact of BPA and mono-ethyl phthalate on breast cancer risk by using repeated serum measurements or other markers of xenoestrogen exposure are needed.