Combined texture analysis and machine learning in suspicious calcifications detected by mammography: Potential to avoid unnecessary stereotactical biopsies.

OBJECTIVES: To investigate whether combined texture analysis and machine learning can distinguish malignant from benign suspicious mammographic calcifications, to find an exploratory rule-out criterion to potentially avoid unnecessary benign biopsies. METHODS: Magnification views of 235 patients which underwent vacuum-assisted biopsy of suspicious calcifications (BI-RADS 4) during a two-year period were retrospectively analyzed using the texture analysis tool MaZda (Version 4.6). Microcalcifications were manually segmented and analyzed by two readers, resulting in 249 image features from gray-value histogram, gray-level co-occurrence and run-length matrices. After feature reduction with principal component analysis (PCA), a multilayer perceptron (MLP) artificial neural network was trained using histological results as the reference standard. For training and testing of this model, the dataset was split into 70 % and 30 %. ROC analysis was used to calculate diagnostic performance indices. RESULTS: 226 patients (150 benign, 76 malignant) were included in the final analysis due to missing data in 9 cases. Feature selection yielded nine image features for MLP training. Area under the ROC-curve in the testing dataset (n = 54) was 0.82 (95 %-CI: 0.70-0.94) and 0.832 (95 %-CI 0.72-0.94) for both readers, respectively. A high sensitivity threshold criterion was identified in the training dataset and successfully applied to the testing dataset, demonstrating the potential to avoid 37.1-45.7 % of unnecessary biopsies at the cost of one false-negative for each reader. CONCLUSION: Combined texture analysis and machine learning could be used for risk stratification in suspicious mammographic calcifications. At low costs in terms of false-negatives, unnecessary biopsies could be avoided.

Transforming growth factor beta 1 serum levels in patients with preinvasive and invasive lesions of the breast.

Transforming growth factor beta (TGF-beta)1 is thought to be involved in breast carcinogenesis. TGF-beta1 acts in an antiproliferative manner in the early stages of breast carcinogenesis, but promotes tumor progression and metastases in the advanced stages of the disease. No data have been published on serum TGF-beta1 in breast cancer. We investigated TGF-beta1 serum levels in patients with breast cancer (n=135), ductal carcinoma in situ (DCIS) I to III (n=67) or fibroadenoma (n=35), and in healthy women (n=40) to determine its value as a differentiation marker between malignant, pre-invasive and benign diseases and as a predictive marker for metastatic spread. Median (range) TGF-beta1 serum levels in patients with breast cancer, DCIS I-III or benign breast lesions and in healthy women were 48.8 (18-82.4) pg/mL, 45.3 (26.9-58.3) pg/mL, 47.2 (17.2-80.5) pg/mL and 51.6 (30.9-65.1) pg/mL, respectively (p=0.2). In breast cancer patients TGF-beta1 serum levels showed no statistically significant correlation with tumor stage, lymph node involvement, histological grade, estrogen receptor status and progesterone receptor status. Our data fail to indicate any correlation between serum TGF-beta1 levels and clinicopathological parameters of breast diseases. Serum TGF-beta1 levels do not provide clinical information in addition to established tumor markers.