Lidia Tortajada

Automatic microcalcification and cluster detection for digital and digitised mammograms

In this paper we present a knowledge-based approach for the automatic detection of microcalcifications and clusters in mammographic images. Our proposal is based on using local features extracted from a bank of filters to obtain a local description of the microcalcifications morphology. The developed approach performs an initial training step in order to automatically learn and select the most salient features, which are subsequently used in a boosted classifier to perform the detection of individual microcalcifications. Subsequently, the microcalcification detection method is extended in order to detect clusters. The validity of our approach is extensively demonstrated using two digitised databases and one full-field digital database. The experimental evaluation is performed in terms of ROC analysis for the microcalcification detection and FROC analysis for the cluster detection, resulting in better than 80% sensitivity at 1 false positive cluster per image.

The Great Mimicker: Fat Necrosis of the Breast—Magnetic Resonance Mammography Approach

Fat necrosis of the breast is a common benign inflammatory process resulting from injury to breast fat. The pathogenesis of fat necrosis helps to explain its imaging features, which range from benign to malignant-appearing findings. This article reviews the role of magnetic resonance mammography and other conventional imaging techniques in the differential diagnosis of fat necrosis.

Interval breast cancers in a community screening programme: frequency, radiological classification and prognostic factors.

The frequency of interval cancers (IC) can be an indicator inversely related to the quality of a breast screening programme. The objectives were to estimate the frequency of IC, to classify IC by posterior radiological review, and to describe the prognostic factors of these IC. The setting was the Sabadell-Cerdanyola Breast Cancer Screening Programme, in Northeast Spain. We developed a population-based study of the IC occurring in the first three rounds (1995–2001). The indicators used were the incidence rate of invasive IC per 10 000 women screened and the proportional incidence, stratified by age group, type of screening and the round, and the time elapsed since the last screening mammogram. A radiological informed consensus review was used to classify the IC. No specific pattern of incidence rates was evident with respect to age, type of screening, or round, although screening was generally more sensitive in women aged 60–69 years. The proportional incidence for the period 0–11 months was always under 30%. Twenty-one percent of 38 IC evaluated (95% CI: 8.0–34.0) were attributed to errors in the screening process (false negatives). No major differences in the prognostic factors of the 57 IC were identified on examining the radiological type or the time since the last screening mammogram. We observed a high frequency of IC from 12 months after screening. It is necessary to reach a consensus regarding the definition and the analysis of IC and to establish mechanisms that would allow all the malignant tumours diagnosed in the target population to be identified.

Adapting breast density classification from digitized to full-field digital mammograms

Mammographic density is strongly associated with breast cancer, being considered one of the most important risk indicators for the development of this type of disease. Likewise, the sensitivity of automatic breast lesion detection systems is significantly dependent on breast tissue characteristics. Therefore, the measurement of density is definitely useful for detecting breast cancer. The aim of this work is to adapt our previously developed automatic breast tissue density classification methodology for digitized mammograms to full-field digital mammograms (FFDM), as well as to evaluate the possible improvements and the classification results. After breast area extraction and peripheral enhancement, the method segments the breast area into fatty and dense tissue, then morphological and texture features from each class are extracted and finally FFDM are classified according to a standard qualitative criteria. Results show a strong correlation (κ=0.88) between automatic and expert assessments and a better classification correction percentage (CCP = 92%) compared to our earlier work.

Shear-wave elastography and immunohistochemical profiles in invasive breast cancer: Evaluation of maximum and mean elasticity values

PURPOSE To evaluate the correlations of maximum stiffness (Emax) and mean stiffness (Emean) of invasive carcinomas on shear-wave elastography (SWE) with St. Gallen consensus tumor phenotypes. METHODS We used an ultrasound system with SWE capabilities to prospectively study 190 women with 216 histologically confirmed invasive breast cancers. We obtained one elastogram for each lesion. We correlated Emax and Emean with tumor size, histologic type and grade, estrogen and progesterone receptors, HER2 expression, the Ki67 proliferation index, and the five St. Gallen molecular subtypes: luminal A, luminal B without HER2 overexpression (luminal B HER2-), luminal B with HER2 overexpression (luminal B HER2+), HER2, and triple negative. RESULTS Lesions larger than 20 mm had significantly higher Emax (148.04 kPa) and Emean (118.32 kPa) (P=0.005) than smaller lesions. We found no statistically significant correlations between elasticity parameters and histologic type and grade or molecular subtypes, although tumors with HER2 overexpression regardless whether they expressed hormone receptors (luminal B HER2+ and HER2 phenotypes) and triple-negative tumors had lower Emax and Emean than the others. We assessed the B-mode ultrasound findings of the lesions with some of the Emax or Emean values less than or equal to 80 kPa; only four of these had ultrasound findings suggestive of a benign lesion (two with luminal A phenotype and two with HER2 phenotype). CONCLUSIONS We were unable to demonstrate statistically significant differences among the subtypes of invasive tumors, although there appears to be a trend toward lower Emax and Emean in the aggressive phenotypes.

Silicone lymphadenopathy: an unusual cause of internal mammary lymph node enlargement.

A61-year-old woman was treated for a ductal invasive carcinoma in the right breast (mastectomy, axillary dissection and chemotherapy in 1990, and breast reconstruction with submuscular Becker silicone outside ⁄ saline inside double lumen prosthesis in 1994). In 2002, she presented with a progressive shrinkage of the right breast volume since 2000, after a traffic accident. A rupture of the implant was suggested. For this reason, a magnetic resonance imaging examination with specific prosthesis sequences and contrast-enhanced dynamic study was performed, showing both intracapsular rupture (linguini sign) and silicone bleeds outside the implant capsule (Fig. 1a,b). Although contrast-enhanced magnetic resonance study showed no appreciable enhancement, there was an evidence of a right internal mammary node measuring 1 cm (Fig. 1c). The significance of the node was uncertain, but on clinical considerations (possible regional spread of breast cancer), this lymph node was excised at the same time as the breast implant removal. Pathologic examination identified an histiocytic infiltrate with multinucleated giant cells, vacuoles, and refractive material consistent with silicone lymphadenopathy (Fig. 2). Magnetic resonance imaging was repeated 12 months after the initial study and showed no implant complications (a single lumen entirely gelfilled prosthesis reimplantation) or contrast enhancement. However, a new right internal mammary node measuring 0.8 cm was demonstrated (Fig. 3). Because of the similarity of its appearance to that seen before, the node was not removed. On follow-up 12 months

Breast peripheral area correction in digital mammograms

Digital mammograms may present an overexposed area in the peripheral part of the breast, which is visually shown as a darker area with lower contrast. This has a direct impact on image quality and affects image visualisation and assessment. This paper presents an automatic method to enhance the overexposed peripheral breast area providing a more homogeneous and improved view of the whole mammogram. The method automatically restores the overexposed area by equalising the image using information from the intensity of non-overexposed neighbour pixels. The correction is based on a multiplicative model and on the computation of the distance map from the breast boundary. A total of 334 digital mammograms were used for evaluation. Mammograms before and after enhancement were evaluated by an expert using visual comparison. In 90.42% of the cases, the enhancement obtained improved visualisation compared to the original image in terms of contrast and detail. Moreover, results show that lesions found in the peripheral area after enhancement presented a more homogeneous intensity distribution. Hence, peripheral enhancement is shown to improve visualisation and will play a role in further development of CAD systems in mammography.

A boosting based approach for automatic micro-calcification detection

In this paper we present a boosting based approach for automatic detection of micro-calcifications in mammographic images Our proposal is based on using local features extracted from a bank of filters for obtaining a description of the different micro-calcifications morphology The approach performs an initial training step in order to automatically learn and select the most salient features, which are subsequently used in a boosting classifier to perform the detection The validity of our method is demonstrated using 112 mammograms of the well-known digitised MIAS database and 280 mammograms of a full-field digital database The experimental evaluation is performed in terms of ROC analysis, obtaining Az=0.88 and Az=0.90 respectively, and FROC analysis The obtained results show the feasibility of our approach for detecting micro-calcifications in both digitised and digital technologies.

Carcinoma metaplásico de mama: resonancia magnética y correlación radiopatológica

Objetivos Revisar nuestra experiencia en los hallazgos de imagen del carcinoma metaplasico, su presentacion clinica y los hallazgos histopatologicos. Material y metodos Revision retrospectiva de ocho casos de carcinoma metaplasico de mama confirmados histopatologicamente. Se analizan los hallazgos ecograficos, mamograficos y por resonancia magnetica, asi como los estudios inmunohistoquimicos de la biopsia prequirurgica. Se determinan factores pronosticos convencionales, marcadores de diferenciacion condral, marcadores de musculo liso y esqueletico, marcadores neurales, citoqueratina, vimentina y filamentos intermedios. Resultados Ocho pacientes con edades entre 41-72 anos. En cinco casos el carcinoma metaplasico se presenta como un nodulo palpable, en uno como retraccion del pezon y dos casos fueron hallazgos incidentals en mamografia de control. Mamograficamente, en siete casos aparece un nodulo redondo, hiperdenso, de 10-50 mm, de margenes variables, en un caso distorsion de la arquitectura, en tres casos calcificaciones. Solo dos pacientes tienen retraccion de piel y de pezon. Ecograficamente se manifestaron como nodulos mal delimitados, hipoecogenicos y heterogeneos. En la resonancia magnetica se muestran como masas relativamente bien definidas, hiperintensas en T2 y con curvas intensidad de senaltiempo similares a las del carcinoma infiltrante de mama. Histopatologicamente hay diferentes variantes de carcinoma metaplasico: un carcinoma metaplasico escamoide, un sarcoide, tres condroides, un fusocelular, una variante de celulas gigantes y un acantolitico, todos con un alto grado histologico. Conclusiones El carcinoma metaplasico debe incluirse en el diagnostico diferencial de un nodulo mamograficamente hiperdenso y de margenes variables, ecograficamente hipoecogenico y mal delimitado, hiperintenso en T2 y con captacion en el rango de malignidad en RM T2. Para el diagnostico final son necesarios los estudios inmunohistoquimicos. Las pruebas de imagen pueden sugerir este subtipo particular.

Use of serum progesterone concentration for timing breast MRI examinations and avoiding false-negative findings.

AJR 2010; 195:W85 0361–803X/10/1951–W85