The so called “Triple Negative Breast Cancer” (TNBC) represents approximately 15-20% of breast cancers. This acronym simply means that the tumour does not express oestrogen receptor (ER) and progesterone receptor (PR) and does not exhibit amplification of the human epidermal growth factor receptor 2 (HER2) gene. Despite this unambiguous definition, TNBCs are an heterogeneous group of tumours with just one common clinical feature: a distinctly aggressive nature with higher rates of relapse and shorter overall survival in the metastatic setting compared with other subtypes of breast cancer. Because of the absence of well-defined molecular targets, cytotoxic chemotherapy is currently the only treatment option for TNBC.

Background: Findings from our previously published phase II study showed a high pathologic complete remission (pCR) rate in patients with triple-negative large operable breast cancer after the administration of eight cisplatin–epirubicin–paclitaxel (PET) weekly cycles. The safety and efficacy data of the initial population were updated, with inclusion of additional experience with the same therapy. Methods: Patients with triple-negative large operable breast cancer (T2–T3 N0–1; T > 3 cm) received eight preoperative weekly cycles of cisplatin 30 mg/m², epirubicin 50 mg/m², paclitaxel (Taxol) 120 mg/m², with granulocyte colony-stimulating factor (5 μg/kg days 3–5) support. Results: Overall 74 consecutive patients (T2/T3 = 35/39; N0/N+ = 26/48) were treated, from May 1999 to May 2008. At pathological assessment, 46 women (62%; 95% confidence interval 50–73) showed pCR in both breast and axilla. At a 41-month median follow-up (range 3–119), 13 events (nine distant metastases) had occurred, 5-year projected disease-free survival (DFS) and distant disease-free survival being 76% and 84%, respectively. Five-year DFS was 90% and 56% in pCRs and non-pCRs, respectively. Severe neutropenia and anemia occurred in 23 (31%) and eight (10.8%) patients, respectively. Severe non-hematological toxicity was recorded in <20% of patients. Peripheral neuropathy was quite frequent but never severe. Conclusions: Eight weekly PET cycles are a highly effective primary treatment in women with triple-negative large operable breast cancer. This approach results in a very promising long-term DFS in this poor prognosis population. This triplet regimen is worthy of evaluation in phase III trials.

Background: The present article reports the updated survival outcome of the 200 patients enrolled in the Southern Italy Cooperative Oncology Group 9908 trial, which compared 12 weekly cycles of cisplatin–epirubicin–paclitaxel (PET) with 4 triweekly (once every 3 weeks) cycles of epirubicin–paclitaxel (ET) in patients with locally advanced breast cancer (LABC). Methods: The effects of treatment, pathologically documented response (pathological response), pre- and post-treatment biomarkers on relapse-free survival (RFS), distant metastasis-free survival (DMFS), and overall survival (OS) are analysed. Results: At a median follow-up of 74 (range 48–105 months) months, the 5-year RFS, DMFS, and OS were 64 % versus 53% (P = 0.11), 73% versus 55% (P = 0.04), and 82% versus 69% (P = 0.07) in PET and ET, respectively. At multivariate analysis, after adjusting treatment effect for pretreatment biomarkers, PET independently predicted better DMFS (P = 0.018) and OS (P = 0.03), whereas the impact on RFS was of borderline significance (0.057). PET treatment was significantly better than ET treatment only in high-grade or highly proliferating tumours. The better outcome in PET arm was the results of both the higher rate of patients with optimal pathological response and the lower rate of patients with biologically aggressive residual tumour. Conclusions: The PET weekly regimen significantly improves both DMFS and OS in LABC patients, compared with the triweekly ET combination. The therapeutic advantage is limited to patients with highly aggressive tumours.

Purpose:The purpose of this study was to discriminate between benign and malignant breast lesions through several classifiers using, as predictors, radiomic metrics extracted from CEM and DCE-MRI images. In order to optimize the analysis, balancing and feature selection procedures were performed. Methods: Fifty-four patients with 79 histo-pathologically proven breast lesions (48 malignant lesions and 31 benign lesions) underwent both CEM and DCE-MRI. The lesions were retrospectively analyzed with radiomic and artificial intelligence approaches. Forty-eight textural metrics were extracted, and univariate and multivariate analyses were performed: non-parametric statistical test, receiver operating characteristic (ROC) and machine learning classifiers. Results: Considering the single metrics extracted from CEM, the best predictors were KURTOSIS (area under ROC curve (AUC) = 0.71) and SKEWNESS (AUC = 0.71) calculated on late MLO view. Considering the features calculated from DCE-MRI, the best predictors were RANGE (AUC = 0.72), ENERGY (AUC = 0.72), ENTROPY (AUC = 0.70) and GLN (gray-level nonuniformity) of the gray-level run-length matrix (AUC = 0.72). Considering the analysis with classifiers and an unbalanced dataset, no significant results were obtained. After the balancing and feature selection procedures, higher values of accuracy, specificity and AUC were reached. The best performance was obtained considering 18 robust features among all metrics derived from CEM and DCE-MRI, using a linear discriminant analysis (accuracy of 0.84 and AUC = 0.88). Conclusions: Classifiers, adjusted with adaptive synthetic sampling and feature selection, allowed for increased diagnostic performance of CEM and DCE-MRI in the differentiation between benign and malignant lesions.

Purpose. To combine blood oxygenation level dependent magnetic resonance imaging (BOLD-MRI), dynamic contrast enhanced MRI (DCE-MRI), and diffusion weighted MRI (DW-MRI) in differentiation of benign and malignant breast lesions. Methods. Thirty-seven breast lesions (11 benign and 21 malignant lesions) pathologically proven were included in this retrospective preliminary study. Pharmaco-kinetic parameters including K^trans, k^ep, v_e, and v_p were extracted by DCE-MRI; BOLD parameters were estimated by basal signal S0 and the relaxation rate R₂*; and diffusion and perfusion parameters were derived by DW-MRI (pseudo-diffusion coefficient (D_p), perfusion fraction (f_p), and tissue diffusivity (D_t)). The correlation coefficient, Wilcoxon-Mann-Whitney U-test, and receiver operating characteristic (ROC) analysis were calculated and area under the ROC curve (AUC) was obtained. Moreover, pattern recognition approaches (linear discrimination analysis and decision tree) with balancing technique and leave one out cross validation approach were considered. Results. R₂* and D had a significant negative correlation (−0.57). The mean value, standard deviation, Skewness and Kurtosis values of R₂* did not show a statistical significance between benign and malignant lesions (p > 0.05) confirmed by the ‘poor’ diagnostic value of ROC analysis. For DW-MRI derived parameters, the univariate analysis, standard deviation of D, Skewness and Kurtosis values of D* had a significant result to discriminate benign and malignant lesions and the best result at the univariate analysis in the discrimination of benign and malignant lesions was obtained by the Skewness of D* with an AUC of 82.9% (p-value = 0.02). Significant results for the mean value of K^trans, mean value, standard deviation value and Skewness of k_ep, mean value, Skewness and Kurtosis of v_e were obtained and the best AUC among DCE-MRI extracted parameters was reached by the mean value of k_ep and was equal to 80.0%. The best diagnostic performance in the discrimination of benign and malignant lesions was obtained at the multivariate analysis considering the DCE-MRI parameters alone with an AUC = 0.91 when the balancing technique was considered. Conclusions. Our results suggest that the combined use of DCE-MRI, DW-MRI and/or BOLD-MRI does not provide a dramatic improvement compared to the use of DCE-MRI features alone, in the classification of breast lesions. However, an interesting result was the negative correlation between R₂* and D.

Purpose: The aim of the study was to estimate the diagnostic accuracy of textural, morphological and dynamic features, extracted by dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) images, by carrying out univariate and multivariate statistical analyses including artificial intelligence approaches. Methods: In total, 85 patients with known breast lesion were enrolled in this retrospective study according to regulations issued by the local Institutional Review Board. All patients underwent DCE-MRI examination. The reference standard was pathology from a surgical specimen for malignant lesions and pathology from a surgical specimen or fine needle aspiration cytology, core or Tru-Cut needle biopsy for benign lesions. In total, 91 samples of 85 patients were analyzed. Furthermore, 48 textural metrics, 15 morphological and 81 dynamic parameters were extracted by manually segmenting regions of interest. Statistical analyses including univariate and multivariate approaches were performed: non-parametric Wilcoxon–Mann–Whitney test; receiver operating characteristic (ROC), linear classifier (LDA), decision tree (DT), k-nearest neighbors (KNN), and support vector machine (SVM) were utilized. A balancing approach and feature selection methods were used. Results: The univariate analysis showed low accuracy and area under the curve (AUC) for all considered features. Instead, in the multivariate textural analysis, the best performance (accuracy (ACC) = 0.78; AUC = 0.78) was reached with all 48 metrics and an LDA trained with balanced data. The best performance (ACC = 0.75; AUC = 0.80) using morphological features was reached with an SVM trained with 10-fold cross-variation (CV) and balanced data (with adaptive synthetic (ADASYN) function) and a subset of five robust morphological features (circularity, rectangularity, sphericity, gleaning and surface). The best performance (ACC = 0.82; AUC = 0.83) using dynamic features was reached with a trained SVM and balanced data (with ADASYN function). Conclusion: Multivariate analyses using pattern recognition approaches, including all morphological, textural and dynamic features, optimized by adaptive synthetic sampling and feature selection operations obtained the best results and showed the best performance in the discrimination of benign and malignant lesions.