A machine learning approach on multiscale texture analysis for breast microcalcification diagnosis.

BACKGROUND: Screening programs use mammography as primary diagnostic tool for detecting breast cancer at an early stage. The diagnosis of some lesions, such as microcalcifications, is still difficult today for radiologists. In this paper, we proposed an automatic binary model for discriminating tissue in digital mammograms, as support tool for the radiologists. In particular, we compared the contribution of different methods on the feature selection process in terms of the learning performances and selected features. RESULTS: For each ROI, we extracted textural features on Haar wavelet decompositions and also interest points and corners detected by using Speeded Up Robust Feature (SURF) and Minimum Eigenvalue Algorithm (MinEigenAlg). Then a Random Forest binary classifier is trained on a subset of a sub-set features selected by two different kinds of feature selection techniques, such as filter and embedded methods. We tested the proposed model on 260 ROIs extracted from digital mammograms of the BCDR public database. The best prediction performance for the normal/abnormal and benign/malignant problems reaches a median AUC value of 98.16% and 92.08%, and an accuracy of 97.31% and 88.46%, respectively. The experimental result was comparable with related work performance. CONCLUSIONS: The best performing result obtained with embedded method is more parsimonious than the filter one. The SURF and MinEigen algorithms provide a strong informative content useful for the characterization of microcalcification clusters.

Mammographic characteristics and vacuum-assisted breast biopsy (VABB) of non-palpable breast lesions.

BACKGROUND: The new imaging technology made available today allows for an early detection of small subclinical breast lesions which frequently call for guided presurgical micro-histology. PURPOSE: To evaluate the relationship between vacuum-assisted breast biopsy (VABB) histopathological diagnoses and mammographic findings in non-palpable breast lesions. MATERIAL AND METHODS: The breast lesions of 1393 women who had received consecutive screening mammograms between 2001 and 2007 were assessed by VABB. The mammographic breast lesions, classified according to the Breast Imaging Reporting and Data System (BI-RADS), were subjected to VABB only if rated as highly suspicious (2%), suspicious (64.5%) for malignancy, or probably benign (33.5%). RESULTS: VABB findings included 981 (70.5%) probably benign lesions, 407 (29.2%) suspicious/malignant lesions, and five (0.3%) cases which were considered as inappropriate for diagnostic purposes. At histology, 10.2% of the suspicious/malignant lesions were classified as proliferative lesions, 11.1% as ductal carcinoma in situ (DCIS), and 8% as invasive ductal carcinoma (IDC). The positive predictive value (PPV) of BI-RADS assessment categories 3, 4 and 5 was 4.1%, 25.3% and 75%, respectively. The occurrence of obscured or spiculated masses was found to exhibit the highest PPV for malignancy (12.5% in BI-RADS 3 and 63% in BI-RADS 4), followed by microcalcifications which showed a malignancy rate of 6.4% in BI-RADS 3, and 20% in BI-RADS 4. CONCLUSION: VABB turns out to be effective in the assessment of many malignant and benign preclinical tumour lesions thus allowing for a significant reduction of the number of surgical biopsies.

Elite VABB 13G: A New Ultrasound-Guided Wireless Biopsy System for Breast Lesions. Technical Characteristics and Comparison with Respect to Traditional Core-Biopsy 14-16G Systems.

The typification of breast lumps with fine-needle biopsies is often affected by inconclusive results that extend diagnostic time. Many breast centers have progressively substituted cytology with micro-histology. The aim of this study is to assess the performance of a 13G-needle biopsy using cable-free vacuum-assisted breast biopsy (VABB) technology. Two of our operators carried out 200 micro-histological biopsies using the Elite 13G-needle VABB and 1314 14-16G-needle core biopsies (CBs) on BI-RADS 3, 4, and 5 lesions. Thirty-one of the procedures were repeated following CB, eighteen following cytological biopsy, and three after undergoing both procedures. The VABB Elite procedure showed high diagnostic performance with an accuracy of 94.00%, a sensitivity of 92.30%, and a specificity of 100%, while the diagnostic underestimation was 11.00%, all significantly comparable to of the CB procedure. The VABB Elite 13G system has been shown to be a simple, rapid, reliable, and well-tolerated biopsy procedure, without any significant complications and with a diagnostic performance comparable to traditional CB procedures. The histological class change in an extremely high number of samples would suggest the use of this procedure as a second-line biopsy for suspect cases or those with indeterminate cyto-histological results.

Anaplastic large-cell periprosthetic lymphoma of the breast: could fibrin be an early radiological indicator of the presence of disease?

PURPOSE: The onset characteristics of the anaplastic large cell lymphoma (BI-ALCL) are non-specific and the diagnosis is often difficult and based on clinical suspicion and cytological sampling. The presence of non-pathognomonic radiological signs may delay the diagnosis of BI-ALCL, influencing patient prognosis. This could have an important social impact, considering that the incidence of BI-ALCL correlates with the number of prosthetic implants, which is in constant increase worldwide. The aim of this study was to verify if fibrin can represent a potential early radiological sign of the disease. METHODS: In this study, we present two cases of our series and review the previous studies already described in literature, searching for any early radiological sign of the disease and reporting a diagnostic work-up process for an early diagnosis. RESULTS: Signs clearly recognizable only of magnetic resonance were the following: thickening and hyperemia of the fibrous capsule with seroma and amorphous material (fibrin) present in 8 out of 10 cases (80%) detected on magnetic resonance images (certain or doubtful). CONCLUSION: The presence of fibrin in the periprosthetic effusion, well detectable by magnetic resonance imaging, could represent an early pathognomonic sign of the disease.

Role of the contrast-enhanced spectral mammography for the diagnosis of breast metastases from extramammary neoplasms.

PURPOSE: Extramammary breast tumors are quite unusual but they might represent the first semiotic sign of non negative mammography. Thus, the need for an early and accurate diagnosis is crucial, with the purpose of planning and optimize the therapeuthical strategy and consequently to improve the clinical outcome of patients. METHODS: Due to the intrinsic characteristics of this technique, CESM lends itself as a useful and reliable tool for a complex diagnosis, since it may simultaneously provide both the data of the mammographic semiotic and the dynamic one of an examination with a contrast medium. RESULTS: In this article, the most common radiological signs of this type of lesions are summarized through an analysis of the published literature. The article focuses on the different mammographic semeiotics in primary and secondary malignant lesions in the breast, on the different aspects of metastases deriving from blood and lymphatic spread, as well as on the common analogies between metastatic lesions and fibroadenomas. Moreover, the characteristics of a unique case of breast metastasis from pleural mesothelioma, analyzed by Contrast-Enhanced Spectral Mammography, are described. CONCLUSIONS: On the basis of our experience, CESM could represent an extremely valid method to address a correct diagnosis in complex cases of potentially metastatic lesions.

C-Kit receptor and tryptase expressing mast cells correlate with angiogenesis in breast cancer patients.

C-Kit protein is a transmembrane tyrosine kinase (TK) receptor (c-KitR-TK), which is predominantly expressed on mast cells (MCs) playing a role in tumor angiogenesis. It could be also expressed on epithelial breast cancer cells (EBCCs), but no data have been published regarding the correlation between mast cells positive to c-KitR (MCs-c-KitR), EBCCs positive to c-KitR (EBCCs-c-KitR), BC angiogenesis in terms of microvessel density (MVD) and the main clinic-pathological features. This study aims to evaluate the above parameters and their correlations in a series of selected 121 female early BC patients. It has been found a strong correlation between MVD and MCDPT, and MCs-c-KitR, MVD and MCs density positive to tryptase (MCDPT), and MCs-c-KitR and MCDPT by Pearson correlation. These data suggest an involvement of both MCDPT and MCs-c-KitR in BC tumor angiogenesis. Furthermore, BC tissue expressing c-KitR could be a putative predictive factor to c-KitR-TK inhibitors. In this way, selected patients with higher MCs-c-KitR could be candidate to receive c-KitR-TK inhibitors (e.g. masitinib, sunitinib) or tryptase inhibitors (e.g. nafamostat mesilate, gabexate mesilate).