Mammographic density is the main correlate of tumors detected on ultrasound but not on mammography

Abstract

Although mammography screening programs do not include ultrasound examinations, some diagnostic units do provide women with both mammography and ultrasonography. This article is concerned with estimating the risk of a breast cancer patient diagnosed in a hospital-based mammography unit having a tumor that is visible on ultrasound but not on mammography. A total of 1,399 women with invasive breast cancer from a hospital-based diagnostic mammography unit were included in this retrospective study. For inclusion, mammograms from the time of the primary diagnosis had to be available for computer-assisted assessment of percentage mammographic density (PMD), as well as Breast Imaging Reporting and Data System (BIRADS) assessment of mammography. In addition, ultrasound findings were available for the complete cohort as part of routine diagnostic procedures, regardless of any patient or imaging characteristics. Logistic regression analyses were conducted to identify predictors of mammography failure, defined as BIRADS assessment 1 or 2. The probability that the visibility of a tumor might be masked at diagnosis was estimated using a regression model with the identified predictors. Tumors were only visible on ultrasound in 107 cases (7.6%). PMD was the strongest predictor for mammography failure, but age, body mass index and previous breast surgery also influenced the risk, independently of the PMD. Risk probabilities ranged from 1% for a defined low-risk group up to 40% for a high-risk group. These findings might help identify women who should be offered ultrasound examinations in addition to mammography.

Diagnostic Accuracy of Breast Medical Tactile Examiners (MTEs): A Prospective Pilot Study

“…On the patients' side, breast morphology and medical history have a strong influence on diagnostic accuracy. BMI, age, previous operations, breast composition, and breast density have been described as having an influence on the predictive value of mammography, ultrasound, and CBEs [16,31,32,54,55]. An association between age, BMI, and mammographic breast density has been described in numerous studies [56,57,58].…”

“…Breast cancer screening and early cancer detection programs include breast self-examination [7,8,9], clinical breast examination (CBE) [10,11,12,13,14,15,16,17,18,19], mammography [14,15,16,19,20,21,22,23,24], ultrasonography [14,23,24,25,26], and magnetic resonance imaging [23,27]. Although there has been constant progress in the understanding of risk factors and genetic dispositions for breast cancer [28,29,30,31,32,33,34,35,36], the majority of breast cancer cases still occur without known predictors. This study is concerned with the introduction of vision-impaired medical tactile examiners (MTEs) for performing CBE in a diagnostic breast unit in order to assess the feasibility, acceptance, and diagnostic value of this approach.…”

Using automated texture features to determine the probability for masking of a tumor on mammography, but not ultrasound

“…The primary aim of the study was to generate a continuous variable that predicts PMD from texture features (“predicted PMD”) and could replace the semi-automatically determined predictor PMD (“observed PMD”) in the prediction model for masking proposed in a previous study [2]. …”

“…The new PMD predictors based on univariate selection, lasso, boosting and random forest, respectively, were each entered into a logistic regression model on the training data, together with the clinical predictors from the previously proposed prediction model for masking, i.e., age (continuous), BMI (continuous), previous breast surgery (yes/no), HRT status and menopausal status (premenopausal, postmenopausal and no HRT usage, postmenopausal and HRT usage), and imaging technique (digital/analog) [2]. …”

“…A recent study investigated risk factors for masking of invasive breast tumors on mammograms [2]. The authors showed that the probability of a tumor being detected on ultrasound but not on mammography (mammography failure) depended on the patient’s age, body mass index (BMI), previous breast surgery, and percentage mammographic density (PMD).…”