Purpose To investigate relationships between computer-extracted breast magnetic resonance (MR) imaging phenotypes with multigene assays of MammaPrint, Oncotype DX, and PAM50 to assess the role of radiomics in evaluating the risk of breast cancer recurrence. Materials and Methods Analysis was conducted on an institutional review board–approved retrospective data set of 84 deidentified, multi-institutional breast MR examinations from the National Cancer Institute Cancer Imaging Archive, along with clinical, histopathologic, and genomic data from The Cancer Genome Atlas. The data set of biopsy-proven invasive breast cancers included 74 (88%) ductal, eight (10%) lobular, and two (2%) mixed cancers. Of these, 73 (87%) were estrogen receptor positive, 67 (80%) were progesterone receptor positive, and 19 (23%) were human epidermal growth factor receptor 2 positive. For each case, computerized radiomics of the MR images yielded computer-extracted tumor phenotypes of size, shape, margin morphology, enhancement texture, and kinetic assessment. Regression and receiver operating characteristic analysis were conducted to assess the predictive ability of the MR radiomics features relative to the multigene assay classifications. Results Multiple linear regression analyses demonstrated significant associations (R2 = 0.25–0.32, r = 0.5–0.56, P < .0001) between radiomics signatures and multigene assay recurrence scores. Important radiomics features included tumor size and enhancement texture, which indicated tumor heterogeneity. Use of radiomics in the task of distinguishing between good and poor prognosis yielded area under the receiver operating characteristic curve values of 0.88 (standard error, 0.05), 0.76 (standard error, 0.06), 0.68 (standard error, 0.08), and 0.55 (standard error, 0.09) for MammaPrint, Oncotype DX, PAM50 risk of relapse based on subtype, and PAM50 risk of relapse based on subtype and proliferation, respectively, with all but the latter showing statistical difference from chance. Conclusion Quantitative breast MR imaging radiomics shows promise for image-based phenotyping in assessing the risk of breast cancer recurrence.

Use of digital breast tomosynthesis for breast imaging may result in a substantial decrease in recall rate.

The introduction of computer-aided detection into this practice was not associated with statistically significant changes in recall and breast cancer detection rates, both for the entire group of radiologists and for the subset of radiologists who interpreted high volumes of mammograms.

In this small data set, FFDM appears to be slightly more sensitive than digital breast tomosynthesis for the detection of calcification. However, diagnostic performance as measured by area under the curve using BI-RADS was not significantly different. With improvements in processing algorithms and display, digital breast tomosynthesis could potentially be improved for this purpose.

The purpose of this study was to develop and test a method for selecting "visually similar" regions of interest depicting breast masses from a reference library to be used in an interactive computer-aided diagnosis (CAD) environment. A reference library including 1000 malignant mass regions and 2000 benign and CAD-generated false-positive regions was established. When a suspicious mass region is identified, the scheme segments the region and searches for similar regions from the reference library using a multifeature based k-nearest neighbor (KNN) algorithm. To improve selection of reference images, we added an interactive step. All actual masses in the reference library were subjectively rated on a scale from 1 to 9 as to their "visual margins speculations". When an observer identifies a suspected mass region during a case interpretation he/she first rates the margins and the computerized search is then limited only to regions rated as having similar levels of spiculation (within +/-1 scale difference). In an observer preference study including 85 test regions, two sets of the six "similar" reference regions selected by the KNN with and without the interactive step were displayed side by side with each test region. Four radiologists and five nonclinician observers selected the more appropriate ("similar") reference set in a two alternative forced choice preference experiment. All four radiologists and five nonclinician observers preferred the sets of regions selected by the interactive method with an average frequency of 76.8% and 74.6%, respectively. The overall preference for the interactive method was highly significant (p < 0.001). The study demonstrated that a simple interactive approach that includes subjectively perceived ratings of one feature alone namely, a rating of margin "spiculation," could substantially improve the selection of "visually similar" reference images.

Purpose To compare radiologists’ performance during interpretation of screening mammograms in the clinic to their performance when reading the same examinations in a retrospective laboratory study. Materials and Methods This study was conducted under an Institutional Review Board approved HIPAA compliant protocol where informed consent was waived. Nine experienced radiologists rated an enriched set of examinations that they personally had read in the clinic (“reader-specific”) mixed with an enriched “common” set of examinations that none of the participants had read in the clinic, using a screening BI-RADS rating scale. The original clinical recommendations to recall the women for a diagnostic workup, or not, for both reader-specific and common sets were compared with their recommendations during the retrospective experiment. The results are presented in terms of reader-specific and group averaged “sensitivity” and “specificity” levels and the dispersion (spread) of reader-specific performance estimates. Results On average radiologists performed significantly better in the clinic as compared with their performance in the laboratory (p=0.035). Inter reader dispersion of the computed performance levels was significantly lower during the clinical interpretations (p<0.01). Conclusion Retrospective laboratory experiments may not represent well either expected performance levels or inter- reader variability during clinical interpretations of the same set of examinations in the clinical environment.

Purpose:To compare the diagnostic performance of breast tomosynthesis versus supplemental mammography views in classification of masses, distortions, and asymmetries. Materials and Methods:Eight radiologists who specialized in breast imaging retrospectively reviewed 217 consecutively accrued lesions by using protocols that were HIPAA compliant and institutional review board approved in 182 patients aged 31-60 years (mean, 50 years) who underwent diagnostic mammography and tomosynthesis. The lesions in the cohort included 33% (72 of 217) cancers and 67% (145 of 217) benign lesions. Eighty-four percent (182 of 217) of the lesions were masses, 11% (25 of 217) were asymmetries, and 5% (10 of 217) were distortions that were initially detected at clinical examination in 8% (17 of 217), at mammography in 80% (173 of 217), at ultrasonography (US) in 11% (25 of 217), or at magnetic resonance imaging in 1% (2 of 217). Histopathologic examination established truth in 191 lesions, US revealed a cyst in 12 lesions, and 14 lesions had a normal follow-up. Each lesion was interpreted once with tomosynthesis and once with supplemental mammographic views; both modes included the mediolateral oblique and craniocaudal views in a fully crossed and balanced design by using a five-category Breast Imaging Reporting and Data System (BI-RADS) assessment and a probability-of-malignancy score. Differences between modes were analyzed with a generalized linear mixed model for BI-RADS-based sensitivity and specificity and with modified Obuchowski-Rockette approach for probability-of-malignancy-based area under the receiver operating characteristic (ROC) curve. Results:Average probability-of-malignancy-based area under the ROC curve was 0.87 for tomosynthesis versus 0.83 for supplemental views (P , .001). With tomosynthesis, the false-positive rate decreased from 85% (989 of 1160) to 74% (864 of 1160) (P , .01) for cases that were rated BI-RADS category 3 or higher and from 57% (663 of 1160) to 48% (559 of 1160) for cases rated BI-RADS category 4 or 5 (P , .01), without a meaningful change in sensitivity.With tomosynthesis, more cancers were classified as BI-RADS category 5 (39% [226 of 576] vs 33% [188 of 576]; P = .017) without a decrease in specificity. Conclusion:Tomosynthesis significantly improved diagnostic accuracy for noncalcified lesions compared with supplemental mammographic views.

Tomosynthesis-based breast imaging may have great potential, but much work is needed before its optimal role in the clinical environment is known.