Assessment Of Microcalcifications Research Articles

Comparison between Visualization of Microcalcifications by Digital Breast Tomosynthesis and Full-Field Digital Mammography

Objective: To date, few studies have compared the diagnostic performance and visibility of microcalcifications obtained using digital breast tomosynthesis (DBT) with those obtained from full-field digital mammography (FFDM). The visualization and characterization of microcalcifications with DBT remain controversial. The purpose of this study was to compare the visibility of microcalcifications and determine whether DBT exhibits a diagnostic advantage for visualizing microcalcifications over FFDM. Methods: We retrospectively reviewed 120 cases including DBT and FFDM imaging (60 histologically verified as breast cancers and 60 as benign microcalcifications or normal). DBT images with a wide scan-angle of 50° and FFDM images were obtained using a flat-panel system (MAMMOMAT Inspiration, Siemens). Images were independently reviewed by four board-certified radiologists and evaluated for the presence of microcalcifications, probability of malignancy (BI-RADS classification), and visibility. Results: In predicting the malignancy of detected microcalcifications, no significant difference was found between readers’ areas under the receiver operating characteristic curve for DBT and FFDM (p = 0.068). The visibility scores of detected microcalcifications were 3.74 ± 1.06 for DBT and 3.46 ± 0.93 for FFDM, respectively. The visibility of microcalcifications when using DBT was found to be significantly superior to that of FFDM (p < 0.05). Conclusion: Our results suggest that the image quality of DBT with a wide scan-angle is comparable or superior to that obtained with FFDM in terms of both visibility and assessment of microcalcifications.

Abstract 2229: Mammography assessment of microcalcifications using a pixel detector system

Abstract Breast cancer is a major public health problem being the most frequently diagnosed malignancy and the second leading cause of dead from cancer among women in the United States. In 2015, there were expected around 231,840 new cases of invasive breast cancer, as well as 60,290 cases of in situ breast cancer, and 40,290 deaths. Worldwide, it represents 23% of the total cases diagnosed of cancer and 14% of the cancer deaths in female. Diagnosing breast cancer before it has the potential to invade surrounding tissue and metastasize can increase the chance of survival, reduce poor prognosis and the need of aggressive treatment. This is one of the main goals of early diagnosis that advocates mammography, the clinical examination and the breast self-examination as screening modalities for breast cancer. Recently, other technologies have been proposed like ultrasound and magnetic resonance imaging (MRI). Although these screening methods have reduced the relative risk of death, they have some limitations in some population groups. The aim of this work is adapting and testing a semiconductor pixel detector, Timepix in a custom-swine breast phantom to evaluate its technical feasibility to introduce this technology in a clinical setting for mammography assessment based on microcalcification detection. Swine model is commonly used in medical research based on anatomical and histopathological characteristics closely resemble those of humans, and this is an advantage over the wax-based phantoms that contains aluminum oxide (Al2O3) specks, nylon fibers and other inclusions to mimic microcalcifications and histopathological structures. The Timepix detector was used together with a Tungsten microfocus X-ray to detect hydroxyapatite crystals mimicking malignant microcalcifications with sizes ranged between 153-827μm, embedded into the swine phantom. To compare the detection performance in the swine phantom, a commercial phantom has been used (Model 015 CIRS Inc., Norfolk, VA, US). Both phantoms were tested on a clinical mammography system (Selenia Dimensions AWS 5000 ET19) and by using the experimental setup with the Timepix. This approach has potential to be used for mammography screening in different population groups based on its performance in microcalcifications detection. The results are highly relevant for further studies of the feasibility of pixel detectors for risk assessment and early diagnosis of breast cancer. Citation Format: Carlos Ávila Bernal, Gerardo Roque, Roberto Rueda, Jorge Racedo. Mammography assessment of microcalcifications using a pixel detector system [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2018; 2018 Apr 14-18; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2018;78(13 Suppl):Abstract nr 2229.

A novel neural-genetic algorithm to find the most significant combination of features in digital mammograms

Digital mammography is one of the most suitable methods for early detection of breast cancer. It uses digital mammograms to find suspicious areas containing benign and malignant microcalcifications. However, it is very difficult to distinguish benign and malignant microcalcifications. This is reflected in the high percentage of unnecessary biopsies that are performed and many deaths caused by late detection or misdiagnosis. A computer based feature selection and classification system can provide a second opinion to the radiologists in assessment of microcalcifications. The research in this paper proposes a neural-genetic algorithm for feature selection to classify microcalcification patterns in digital mammograms. It aims to develop a step-wise algorithm to find the best feature set and a suitable neural architecture for microcalcification classification. The obtained results show that the proposed algorithm is able to find an appropriate feature subset, which also produces a high classification rate.

Neural vs. statistical classifier in conjunction with genetic algorithm based feature selection

Digital mammography is one of the most suitable methods for early detection of breast cancer. It uses digital mammograms to find suspicious areas containing benign and malignant microcalcifications. However, it is very difficult to distinguish benign and malignant microcalcifications. This is reflected in the high percentage of unnecessary biopsies that are performed and many deaths caused by late detection or misdiagnosis. A computer based feature selection and classification system can provide a second opinion to the radiologists in assessment of microcalcifications. The research in this paper proposes and investigates a neural-genetic algorithm for feature selection in conjunction with neural and statistical classifiers to classify microcalcification patterns in digital mammograms. The obtained results show that the proposed approach is able to find an appropriate feature subset and neural classifier achieves better results than two statistical models.

Evaluation of breast microcalcifications according to breast imaging reporting and data system criteria and Le Gal's classification

Introduction/objective: Our aim was to evaluate the positive predictive value (PPV) of the analysis of breast microcalcifications according to Breast Imaging Reporting and Data System (BI-RADS) and Le Gal's classification in identification of malignancy, and to assess the interobserver agreement using these criteria. Methods and material: Eighty-two patients with breast microcalcifications on their screening mammograms underwent surgical excision after a needle localization at our institution between July 1993 and June 2000. The mammograms were examined by two experienced mammographers retrospectively and independently. Each observer noted the morphology, distribution, associated findings, final assessment categories of microcalcifications according to BI-RADS criteria and the morphologic type of microcalcifications according to Le Gal's classification. The PPVs for each radiologist and the interobserver agreement were determined by using these data and histologic findings. Results: Histopathologic results yielded malignancy in 25 (30%) cases. The evaluation of microcalcifications according to BI-RADS criteria revealed PPVs of 17% and 25% for category 4 lesions, and 68% and 44% for categoy 5 lesions. In the assessment of microcalcifications according to Le Gal's classification, the PPV of type 4 lesions was 45% (for both observers), whereas the PPVs of type 5 lesions were 70% and 50%. The interobserver agreement was fair in evaluation of morphology of microcalcifications (κ: 0.31), distribution of microcalcifications (κ: 0.29), final assessment categories (κ: 0.27), and moderate in evaluation of associated findings (κ: 0.48) by using BI-RADS lexicon. It was higher for the assessment of milk of calcium and round microcalcifications than other typically benign microcalcifications, and for fine linear or fine linear branching microcalifications than other probably malignant calcifications. There was a fair interobserver agreement (κ: 0.30) in the description of the morphologic type of microcalcifications according to Le Gal's classification. Discussions and conclusion: In our study, both BI-RADS lexicon and Le Gal's classification did not succeed expectedly in reducing the ambiguity in assessment of breast microcalcifications. Further studies and perhaps development of new methods are required to improve accuracy and standardization in mammographic interpretation.

Low spatial resolution in FFDM is no disadvantage to assessment of microcalcifications

Low spatial resolution in FFDM is no disadvantage to assessment of microcalcifications