Diagnostic accuracy of automated ACR BI-RADS breast density classification using deep convolutional neural networks

Abstract

Objectives High breast density is a well-known risk factor for breast cancer. This study aimed to develop and adapt two (MLO, CC) deep convolutional neural networks (DCNN) for automatic breast density classification on synthetic 2D tomosynthesis reconstructions. Methods In total, 4605 synthetic 2D images (1665 patients, age: 57 ± 37 years) were labeled according to the ACR (American College of Radiology) density (A-D). Two DCNNs with 11 convolutional layers and 3 fully connected layers each, were trained with 70% of the data, whereas 20% was used for validation. The remaining 10% were used as a separate test dataset with 460 images (380 patients). All mammograms in the test dataset were read blinded by two radiologists (reader 1 with two and reader 2 with 11 years of dedicated mammographic experience in breast imaging), and the consensus was formed as the reference standard. The inter- and intra-reader reliabilities were assessed by calculating Cohen’s kappa coefficients, and diagnostic accuracy measures of automated classification were evaluated. Results The two models for MLO and CC projections had a mean sensitivity of 80.4% (95%-CI 72.2–86.9), a specificity of 89.3% (95%-CI 85.4–92.3), and an accuracy of 89.6% (95%-CI 88.1–90.9) in the differentiation between ACR A/B and ACR C/D. DCNN versus human and inter-reader agreement were both “substantial” (Cohen’s kappa: 0.61 versus 0.63). Conclusion The DCNN allows accurate, standardized, and observer-independent classification of breast density based on the ACR BI-RADS system. Key Points • A DCNN performs on par with human experts in breast density assessment for synthetic 2D tomosynthesis reconstructions. • The proposed technique may be useful for accurate, standardized, and observer-independent breast density evaluation of tomosynthesis.

Automated Breast Density Assessment in MRI Using Deep Learning and Radiomics: Strategies for Reducing Inter‐Observer Variability

“…The same pattern was also observed among radiologists and in other studies. 27,35 The primary cause of this disparity was the distribution of BI-RADS densities, which were almost equal in dense and non-dense, but highly imbalanced between the four categories. The limited training data also restricted the classifier's capabilities.…”

Artificial Intelligence Applications in Breast Imaging: Current Status and Future Directions

“…Other models have also demonstrated high levels of agreement in clinical use in the binary categorization of dense and non-dense breasts, with 94% agreement amongst radiologists with a DL algorithm when evaluating more than 10,000 mammography examinations [40]. Diagnostic accuracy can be maintained in algorithms assessing breast density in synthetic mammograms, demonstrating an accuracy of 89.6% when differentiating dense and non-dense breasts [41]. However, the possibility for altered performance of automated breast density assessments exists when moving from FFDM images to synthetic mammography, including complex potential interactions with ethnicity and body mass index that require awareness and attention [42].…”

Breast Density Transformations Using CycleGANs for Revealing Undetected Findings in Mammograms

“…Breast density cannot be detected through physical examination but only through mammography, and it is an important variable that affects the sensitivity of mammography [3][4][5][6]. Over 40% of women with dense breast tissue are characterized as heterogeneously dense (ACR-C) or extremely dense (ACR-D).…”

“…Due to its impact on the accurate detection of cancer in mammograms, the problem of automatic breast tissue recognition has been extensively studied over the last decade, with a large number of papers published in this area proposing systems that use either traditional machine learning techniques or, more recently, deep learning networks and architectures [4][5][6][7]13,15,16]. However, to our knowledge, none of them proposes a method to "transform" breast density to lower density levels and thus enhance the diagnostic accuracy of CAD systems.…”