Prediction of Near-Term Breast Cancer Occurrence using Subtraction of Temporally Sequential Digital Mammograms.

Breast cancer remains one of the leading cancers for women worldwide. Fortunately, with the introduction of mammography, the mortality rate has significantly decreased. However, earlier breast cancer prediction could effectively increase the survival rates, improve patient outcomes, and avoid unnecessary biopsies. For that purpose, prediction of breast cancer, using subtraction of temporally sequential digital mammograms and machine learning, is proposed. A new dataset was collected with 192 images from 32 patients (three screening rounds, with two views of each breast). This dataset included precise annotation of each individual malignant mass, present in the most recent mammogram, with the two priors being radiologically evaluated as normal. The most recent mammogram was considered as the "future" screening round and provided the location of the mass as the ground truth for the training. The two previous mammograms, the "current" and the "prior", were processed and a new, difference image was formed for the prediction. Ninety-six features were extracted and five feature selection algorithms were combined to identify the most important features. Ten classifiers were tested in leave-one-patient-out and k-fold-patient cross-validation (k = 4 and 8). Ensemble Voting achieved the highest performance in the prediction of the development of breast mass in the next screening round, with 85.7% sensitivity, 83.7% specificity, 83.7% accuracy and 0.85 AUC. The proposed methodology could lead to a new mammography-based model that could predict the short-term risk for developing a malignancy, thus providing an earlier diagnosis.

Identification and Classification of Benign and Malignant Masses based on Subtraction of Temporally Sequential Digital Mammograms.

Breast cancer remains the leading cause of cancer deaths and the second highest cause of death, in general, among women worldwide. Fortunately, over the last few decades, with the introduction of mammography, the mortality rate of breast cancer has significantly decreased. However, accurate classification of breast masses in mammograms is especially challenging. Various Computer-Aided Diagnosis (CAD) systems are being developed to assist radiologists with the accurate classification of breast abnormalities. In this study, classification of benign and malignant masses, based on the subtraction of temporally sequential digital mammograms and machine learning, is proposed. The performance of the algorithm was evaluated on a dataset created for the purposes of this study. In total, 196 images from 49 patients, with precisely annotated mass locations and biopsy confirmed malignant cases, were included. Ninety-six features were extracted and five feature selection algorithms were employed to identify the most important features. Ten classifiers were tested using leave-one-patient-out and 7-fold cross-validation. Neural Networks, achieved the highest classification performance with 90.85% accuracy and 0.91 AUC, an improvement compared to the state-of-the-art. These results demonstrate the effectiveness of the subtraction of temporally consecutive mammograms for the classification of breast masses as benign or malignant.

Clinical Validation of EndoPredict in Pre-Menopausal Women with ER-Positive, HER2-Negative Primary Breast Cancer.

PURPOSE: The EndoPredict prognostic assay is validated to predict distant recurrence and response to chemotherapy primarily in post-menopausal women with estrogen receptor-positive (ER+), HER2- breast cancer. This study evaluated the performance of EndoPredict in pre-menopausal women. EXPERIMENTAL DESIGN: Tumor samples from 385 pre-menopausal women with ER+, HER2- primary breast cancer (pT1-3, pN0-1) who did not receive chemotherapy in addition to endocrine therapy were tested with EndoPredict to produce a 12-gene EP molecular score and an integrated EPclin score that includes pathologic tumor size and nodal status. Associations of molecular and EPclin scores with 10-year distant recurrence-free survival (DRFS) were evaluated by Cox proportional hazards models and Kaplan-Meier analysis. RESULTS: After a median follow-up of 9.7 years, both the EP molecular score and the molecular-clinicopathologic EPclin score were associated with increased risk of distant recurrence [HR, 1.33; 95% confidence interval (CI), 1.18-1.50; P = 7.2 × 10-6; HR, 3.58; 95% CI, 2.26-5.66; P = 9.8 × 10-8, respectively]. Both scores remained significant after adjusting for clinical factors in multivariate analysis. Patients with low-risk EPclin scores (64.7%) had significantly improved DRFS compared with high-risk patients (HR, 4.61; 95% CI, 1.40-15.17; P = 4.2 × 10-3). At 10 years, patients with low-risk and high-risk EPclin scores had a DRFS of 97% (95% CI, 93%-99%) and 76% (95% CI, 67%-82%), respectively. CONCLUSIONS: The EPclin score is strongly associated with DRFS in pre-menopausal women who received adjuvant endocrine therapy alone. On the basis of these data, pre-menopausal women with EPclin low-risk breast cancer may be treated with endocrine therapy only and safely forgo adjuvant chemotherapy.