Parallel vessels as a predictor of benignity in solid breast masses.

To evaluate the presence of a parallel artery and vein on color Doppler ultrasound as a predictor of benignity in solid breast masses. This prospective study included all patients with solid breast masses identified by ultrasound at our center from January 2012 through December 2015. All masses were studied with B mode and color Doppler ultrasound. We calculated the sensitivity, specificity, positive predictive value, and negative predictive value, and their respective 95% confidence intervals for the parallel vessel sign against the histologic findings or 2 years' follow-up without changes. A total of 526 solid masses were included in the 3-year period; the parallel vessel sign was observed in 377 (71.6%). We found 74.8% (95% CI: 70.9-78.7) sensitivity, 65% (95% CI: 50.2-79.7) specificity, 96.2% (95% CI: 94.3-98.1) positive predictive value, and 17.5% (95% CI: 11.4-23.6) negative predictive value. Of the 379 masses classified as breast imaging reporting and data system (BI-RADS) 3, the parallel vessel sign was observed in 275 (72.5%); all of these were definitively benign. Of the 109 masses classified as BI-RADS 4, the parallel vessel sign was observed in 89 (80.7%); 88 (98.8%) of these were definitively benign. Of the 38 masses classified as BI-RADS 5, the parallel vessel sign was observed in 13 (34.2%); all of these were definitively malignant. The parallel artery and vein sign is a good predictor of benignity, although it must be analyzed together with other morphologic descriptors.

The impact of preoperative axillary ultrasonography in T1 breast tumours.

OBJECTIVES: To (a) determine the diagnostic validity of axillary ultrasound (AUS) in pT1 tumours and whether fine-needle aspiration (FNA) improves its diagnostic performance, and (b) determine the negative predictive value (NPV) of AUS in a simulation environment (cutoff: two lymph nodes with macrometastases) in patients fulfilling American College of Surgeons Oncology Group (ACOSOG) Z0011 criteria. MATERIALS AND METHODS: This retrospective multicentre cross-sectional study analysed diagnostic accuracy in 355 pT1 breast cancers. All patients underwent AUS; visible nodes underwent FNA regardless of their AUS appearance. Sentinel node biopsy and axillary lymph node dissection (ALND) were gold standards. Data were analysed considering micrometastases 'positive' and considering micrometastases 'N negative'. The simulation environment included all patients fulfilling ACOSOG Z0011 criteria. RESULTS: Axillary involvement: 22.8 %; AUS sensitivity: 46.9 % (Nmic positive)/66.7 % (Nmic negative); AUS+FNA sensitivity: 52.6 % (pNmic positive)/72.0 % (pNmic negative). In the simulation environment, AUS had 75.0 % sensitivity, 88.9 % specificity and 99.2 % NPV. CONCLUSION: AUS has moderate sensitivity in T1 tumours. As ALND is unnecessary in micrometastases, considering micrometastases 'N negative' increases the practical impact of AUS. In patients fulfilling ACOSOG Z0011 criteria, AUS alone can predict cases unlikely to benefit from ALND. KEY POINTS: • AUS+FNA can predict axillary involvement, thus avoiding SNB. • Not all patients with axillary involvement need ALND. • Axillary tumour load determines axillary management. • AUS could classify patients according to axillary load.

Breast Density Analysis Using an Automatic Density Segmentation Algorithm.

Breast density is a strong risk factor for breast cancer. In this paper, we present an automated approach for breast density segmentation in mammographic images based on a supervised pixel-based classification and using textural and morphological features. The objective of the paper is not only to show the feasibility of an automatic algorithm for breast density segmentation but also to prove its potential application to the study of breast density evolution in longitudinal studies. The database used here contains three complete screening examinations, acquired 2 years apart, of 130 different patients. The approach was validated by comparing manual expert annotations with automatically obtained estimations. Transversal analysis of the breast density analysis of craniocaudal (CC) and mediolateral oblique (MLO) views of both breasts acquired in the same study showed a correlation coefficient of ρ = 0.96 between the mammographic density percentage for left and right breasts, whereas a comparison of both mammographic views showed a correlation of ρ = 0.95. A longitudinal study of breast density confirmed the trend that dense tissue percentage decreases over time, although we noticed that the decrease in the ratio depends on the initial amount of breast density.

The impact of axillary ultrasound with biopsy in overtreatment of early breast cancer.

PURPOSE: (a) To compare the axillary tumor burden detected by fine-needle aspiration cytology (FNAC) versus sentinel lymph node biopsy (SLNB). (b) To evaluate the relationship between axillary tumor burden and the number of suspicious lymph nodes detected by axillary ultrasonography (US). (c) To calculate the false-positive and false-negative rates for FNAC in patients fulfilling ACOSOG Z0011 criteria. METHODS: Retrospective multicenter cross-sectional study of 355 pT1 breast cancers. SLNB and axillary lymph node dissection (ALND) were gold standards. Low axillary burden (≤2 positive lymph nodes); high burden (>2 positive lymph nodes). Patients ACOSOG Z0011: false-positive (positive FNAC+low burden), false-negative (negative FNAC+high burden). RESULTS: High axillary burden: in entire series 38.5% FNAC+ vs. 5.7% SLNB+ (p<0.0001). In subgroup fulfilling ACOSOG Z0011 criteria: 45.5% vs 6.7%, respectively (p<0.001). 61 positive axillary US. With 1 suspicious node on axillary US: 95.6% had ≤2 involved nodes (including pN0); with 2 suspicious nodes: 60% had >2 involved nodes. In ACOSOG Z0011 patients, with 1 suspicious node, 93.7% had ≤2 involved nodes. Of the 37 FNAC in ACOSOG Z0011patients: 54.5% false-positives for high burden; 3.8% false-negatives. CONCLUSIONS: FNAC-positive tumors have greater axillary burden, even in patients fulfilling ACOSOG Z0011 criteria. Using axillary US/FNAC to triage patients meeting Z0011 criteria may result in axillary overtreatment. The number of suspicious nodes seen in axillary US is related with the final axillary burden and should be taken into account when deciding to do FNAC in patients fulfilling ACOSOG Z0011 criteria.

Automated Breast Ultrasound Lesions Detection Using Convolutional Neural Networks.

Breast lesion detection using ultrasound imaging is considered an important step of computer-aided diagnosis systems. Over the past decade, researchers have demonstrated the possibilities to automate the initial lesion detection. However, the lack of a common dataset impedes research when comparing the performance of such algorithms. This paper proposes the use of deep learning approaches for breast ultrasound lesion detection and investigates three different methods: a Patch-based LeNet, a U-Net, and a transfer learning approach with a pretrained FCN-AlexNet. Their performance is compared against four state-of-the-art lesion detection algorithms (i.e., Radial Gradient Index, Multifractal Filtering, Rule-based Region Ranking, and Deformable Part Models). In addition, this paper compares and contrasts two conventional ultrasound image datasets acquired from two different ultrasound systems. Dataset A comprises 306 (60 malignant and 246 benign) images and Dataset B comprises 163 (53 malignant and 110 benign) images. To overcome the lack of public datasets in this domain, Dataset B will be made available for research purposes. The results demonstrate an overall improvement by the deep learning approaches when assessed on both datasets in terms of True Positive Fraction, False Positives per image, and F-measure.

Breast core biopsy reporting categories--An internal validation in a series of 3054 consecutive lesions.

We reviewed 3226 consecutive core biopsies (CBs) of 3054 mammographically detected breast lesions performed at our Centre from November 1993 to June 2003. CB diagnoses, classified according to the Non-operative Diagnosis Subgroup of the British National Health Service Breast Cancer Screening Programme (NHSBSP), were B5 (37.1%), B4 (0.5%), B3 (7.6%), B2 (50.9%) and B1 (3.9%). It was necessary to repeat the procedure in 172 cases (5.3%). The values for absolute sensitivity and specificity are 90.8% and 83.8%, respectively. The positive predictive value for categories B4 and B5 is 100%, with no false-positives. The positive predictive value for category B3 is 16.3%. The negative predictive value for B2 category is 97.2%, with a false-negative rate of 3.5%. In conclusion, this system of analysis has enabled us to confirm that our CB results surpass the minimum recommended standards proposed by the NHSBSP.

Local breast density assessment using reacquired mammographic images.

PURPOSE: The aim of this paper is to evaluate the spatial glandular volumetric tissue distribution as well as the density measures provided by Volpara™ using a dataset composed of repeated pairs of mammograms, where each pair was acquired in a short time frame and in a slightly changed position of the breast. MATERIALS AND METHODS: We conducted a retrospective analysis of 99 pairs of repeatedly acquired full-field digital mammograms from 99 different patients. The commercial software Volpara™ Density Maps (Volpara Solutions, Wellington, New Zealand) is used to estimate both the global and the local glandular tissue distribution in each image. The global measures provided by Volpara™, such as breast volume, volume of glandular tissue, and volumetric breast density are compared between the two acquisitions. The evaluation of the local glandular information is performed using histogram similarity metrics, such as intersection and correlation, and local measures, such as statistics from the difference image and local gradient correlation measures. RESULTS: Global measures showed a high correlation (breast volume R=0.99, volume of glandular tissue R=0.94, and volumetric breast density R=0.96) regardless the anode/filter material. Similarly, histogram intersection and correlation metric showed that, for each pair, the images share a high degree of information. Regarding the local distribution of glandular tissue, small changes in the angle of view do not yield significant differences in the glandular pattern, whilst changes in the breast thickness between both acquisition affect the spatial parenchymal distribution. CONCLUSIONS: This study indicates that Volpara™ Density Maps is reliable in estimating the local glandular tissue distribution and can be used for its assessment and follow-up. Volpara™ Density Maps is robust to small variations of the acquisition angle and to the beam energy, although divergences arise due to different breast compression conditions.

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.

Computerized detection of breast lesions using deformable part models in ultrasound images.

Ultrasound imaging is considered an important complementary technique for the screening of dense breasts. Detection of lesions at an early stage is a key step in which computerized lesion detection systems could play an important role in the analysis of US images. In this article, we propose adaptation of a generic object detection technique, deformable part models, to detect lesions in breast US images. The data set used in this study included 326 images, all from different patients (54 malignant lesions, 109 benign lesions and 163 healthy breasts). In terms of lesion detection, our proposal outperformed some of the most relevant approaches described in the literature; we obtained a sensitivity of 86% with 0.28 false-positive detection per image and an Az value of 0.975. In the detection of malignant lesions, our proposed approached had an Az value of 0.93 and a sensitivity of 78% at a 1.15 false-positive detections per image.

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.

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.