Deep learning in breast cancer risk assessment: evaluation of convolutional neural networks on a clinical dataset of full-field digital mammograms

Abstract

To evaluate deep learning in the assessment of breast cancer risk in which convolutional neural networks (CNNs) with transfer learning are used to extract parenchymal characteristics directly from full-field digital mammographic (FFDM) images instead of using computerized radiographic texture analysis (RTA), 456 clinical FFDM cases were included: a "high-risk" BRCA1/2 gene-mutation carriers dataset (53 cases), a "high-risk" unilateral cancer patients dataset (75 cases), and a "low-risk dataset" (328 cases). Deep learning was compared to the use of features from RTA, as well as to a combination of both in the task of distinguishing between high- and low-risk subjects. Similar classification performances were obtained using CNN [area under the curve [Formula: see text]; standard error [Formula: see text]] and RTA ([Formula: see text]; [Formula: see text]) in distinguishing BRCA1/2 carriers and low-risk women. However, in distinguishing unilateral cancer patients and low-risk women, performance was significantly greater with CNN ([Formula: see text]; [Formula: see text]) compared to RTA ([Formula: see text]; [Formula: see text]). Fusion classifiers performed significantly better than the RTA-alone classifiers with AUC values of 0.86 and 0.84 in differentiating BRCA1/2 carriers from low-risk women and unilateral cancer patients from low-risk women, respectively. In conclusion, deep learning extracted parenchymal characteristics from FFDMs performed as well as, or better than, conventional texture analysis in the task of distinguishing between cancer risk populations.

Artificial intelligence in cancer imaging: Clinical challenges and applications

“…Advances in both imaging and computers have synergistically led to a rapid rise in the potential use of AI in various tasks in breast imaging, such as risk assessment, detection, diagnosis, prognosis, and response to therapy (Table ) …”

“…By using radiomic texture analysis, investigators have characterized the spatial distribution of the gray‐scale levels within regions on FFDM when a skewness measure was incorporated into the analysis of mammograms to describe the density variation . Others have used texture analysis and deep learning to discriminate BRCA1/BRCA2 gene mutation carriers (or women with breast cancer in the contralateral breast) from women at low risk of breast cancer and, using almost 500 cases, found that women at high risk of breast cancer have dense breasts with parenchymal patterns that are coarse and low in contrast (AUC, approximately 0.82) . Further efforts have applied texture analysis to breast tomosynthesis images to characterize the parenchyma pattern for ultimate use in breast cancer risk estimation, with preliminary results indicating that texture features correlated better with breast density on breast tomosynthesis ( P = .003 in regression analysis) than on digital mammograms …”

“…In a limited data set of 50 BRCA1/BRCA2 carriers, quantitative measures of BPE were associated with the presence of breast cancer, and relative changes in BPE percentages were predictive of breast cancer development after risk‐reducing salpingo‐oophorectomy ( P < .05) . Deep learning methods are increasingly being evaluated to assess breast density as well as parenchymal characterization, an example of which includes the performance assessment of transfer learning in the distinction between women at normal risk of breast cancer and those at high risk based on their BRCA1/BRCA2 status …”

Artificial intelligence in the interpretation of breast cancer on MRI

“… (a) Schematic diagram of radiomic texture analysis (RTA) and deep CNN‐based methods for breast cancer risk assessment (Ref. ). (b) Scatterplots show distributions of 60 low‐risk cases and 30 BRCA1 and BRCA2 mutation carriers in an age‐matched group in terms of radiomic features of (a) skewness vs. coarseness and (b) coarseness vs. contrast.…”

Comprehensive analysis of lung cancer pathology images to discover tumor shape features that predict survival outcome

“…Deep learning methods, such as convolution neural networks (CNNs), have been widely used in image segmentation, object classification and recognition [9][10][11] and are now being adapted in biomedical image analysis to facilitate cancer diagnosis. To some extent, the performances of deep learning algorithms are similar to, or sometimes even better than, those of humans 12,13 . For analysis of H&E-stained pathology images, deep learning methods have been developed to distinguish tumor regions 14 , detect metastasis 15 , predict mutation status 16 , and classify tumors 17 in breast cancer as well as in other cancers.…”