Association between Breast Parenchymal Complexity and False-Positive Recall From Digital Mammography Versus Breast Tomosynthesis: Preliminary Investigation in the ACRIN PA 4006 Trial

Mammographically detected asymmetries in the era of artificial intelligence

Background

Proper assessment of mammographically detected asymmetries is essential to avoid unnecessary biopsies and missed cancers as they may be of a benign or malignant cause. According to ACR BIRADS atlas 2013, mammographically detected asymmetries are classified into asymmetry, focal asymmetry, global asymmetry, and developing asymmetry. We aimed to assess the diagnostic performance of artificial intelligence in mammographically detected asymmetries compared to breast ultrasound as well as combined mammography and ultrasound.

Results

This study was a prospective study that comprised 51 women with breast asymmetry found on screening as well as diagnostic mammography. All participants conducted full-field digital mammography and ultrasound. Then the obtained mammographic images were processed by the artificial intelligence software system. Mammography had a sensitivity of 100%, specificity of 73%, a positive predictive value of 56.52%, a negative predictive value of 100%, and diagnostic accuracy of 80%. The results of Ultrasound revealed a sensitivity of 100.00%, a specificity of 89.47%, a positive predictive value of 76.47%, a negative predictive value of 100.00%, and an accuracy of 92.16%. Combined mammography and breast ultrasound showed a sensitivity of 100.00%, a specificity of 86.84%, a positive predictive value of 72.22%, a negative predictive value of 100.00%, and an accuracy of 90.20%. Artificial intelligence results demonstrated a sensitivity of 84.62%, a specificity of 94.74%, a positive predictive value of 48.26%, a negative predictive value of 94.47%, and an accuracy of 92.16%.

Conclusions

Adding breast ultrasound in the assessment of mammographically detected asymmetries led to better characterization, so it reduced the false-positive results and improved the specificity. Also, Artificial intelligence showed better specificity compared to mammography, breast ultrasound, and combined Mammography and ultrasound, so AI can be used to decrease unnecessary biopsies as it increases confidence in diagnosis, especially in cases with no definite ultrasound suspicious abnormality.

Factors associated with false-positive mammography at first screen in an Asian population

Introduction

False-positive recall is an issue in national screening programmes. The aim of this study is to investigate the recall rate at first screen and to identify potential predictors of false-positive recall in a multi-ethnic Asian population-based breast cancer screening programme.

Methods

Women aged 50–64 years attending screening mammography for the first time (n = 25,318) were included in this study. The associations between potential predictors (sociodemographic, lifestyle and reproductive) and false-positive recall were evaluated using multivariable logistic regression models.

Results

The recall rate was 7.6% (n = 1,923), of which with 93.8% were false-positive. Factors independently associated with higher false-positive recall included Indian ethnicity (odds ratio [95% confidence interval]: 1.52 [1.25 to 1.84]), premenopause (1.23 [1.04 to 1.44]), nulliparity (1.85 [1.57 to 2.17]), recent breast symptoms (1.72 [1.31 to 2.23]) and history of breast lump excision (1.87 [1.53 to 2.26]). Factors associated with lower risk of false-positive recall included older age at screen (0.84 [0.73 to 0.97]) and use of oral contraceptives (0.87 [0.78 to 0.97]). After further adjustment of percent mammographic density, associations with older age at screening (0.97 [0.84 to 1.11]) and menopausal status (1.12 [0.95 to 1.32]) were attenuated and no longer significant.

Conclusion

For every breast cancer identified, 15 women without cancer were subjected to further testing. Efforts to educate Asian women on what it means to be recalled will be useful in reducing unnecessary stress and anxiety.

Breast density: why all the fuss?

The term "breast density" or mammographic density (MD) denotes those components of breast parenchyma visualised at mammography that are denser than adipose tissue. MD is composed of a mixture of epithelial and stromal components, notably collagen, in variable proportions. MD is most commonly assessed in clinical practice with the time-honoured method of visual estimation of area-based percent density (PMD) on a mammogram, with categorisation into quartiles. The computerised semi-automated thresholding method, Cumulus, also yielding area-based percent density, is widely used for research purposes; however, the advent of fully automated volumetric methods developed as a consequence of the widespread use of digital mammography (DM) and yielding both absolute and percent dense volumes, has resulted in an explosion of interest in MD recently. Broadly, the importance of MD is twofold: firstly, the presence of marked MD significantly reduces mammographic sensitivity for breast cancer, even with state-of-the-art DM. Recognition of this led to the formation of a powerful lobby group ('Are You Dense') in the US, as a consequence of which 32 states have legislated for mandatory disclosure of MD to women undergoing mammography. Secondly, it is now widely accepted that MD is in itself a risk factor for breast cancer, with a four-to sixfold increased relative risk in women with PMD in the highest quintile compared to those with PMD in the lowest quintile. Consequently, major research efforts are underway to assess whether use of MD could provide a major step forward towards risk-adapted, personalised breast cancer prevention, imaging, and treatment.