Breast cancer risk prediction using machine learning: a systematic review.

Background: Breast cancer is the leading cause of cancer-related fatalities among women worldwide. Conventional screening and risk prediction models primarily rely on demographic and patient clinical history to devise policies and estimate likelihood. However, recent advancements in artificial intelligence (AI) techniques, particularly deep learning (DL), have shown promise in the development of personalized risk models. These models leverage individual patient information obtained from medical imaging and associated reports. In this systematic review, we thoroughly investigated the existing literature on the application of DL to digital mammography, radiomics, genomics, and clinical information for breast cancer risk assessment. We critically analyzed these studies and discussed their findings, highlighting the promising prospects of DL techniques for breast cancer risk prediction. Additionally, we explored ongoing research initiatives and potential future applications of AI-driven approaches to further improve breast cancer risk prediction, thereby facilitating more effective screening and personalized risk management strategies. Objective and methods: This study presents a comprehensive overview of imaging and non-imaging features used in breast cancer risk prediction using traditional and AI models. The features reviewed in this study included imaging, radiomics, genomics, and clinical features. Furthermore, this survey systematically presented DL methods developed for breast cancer risk prediction, aiming to be useful for both beginners and advanced-level researchers. Results: A total of 600 articles were identified, 20 of which met the set criteria and were selected. Parallel benchmarking of DL models, along with natural language processing (NLP) applied to imaging and non-imaging features, could allow clinicians and researchers to gain greater awareness as they consider the clinical deployment or development of new models. This review provides a comprehensive guide for understanding the current status of breast cancer risk assessment using AI. Conclusion: This study offers investigators a different perspective on the use of AI for breast cancer risk prediction, incorporating numerous imaging and non-imaging features.

Mamografía con contraste: nuestra experiencia / Contrast-enhanced digital mammography: our experience

Resumen La mamografía contrastada (CEDM, contrast-enhanced digital mammography) es una herramienta nueva que ha ido implementándose de forma creciente. Aparece como alternativa a la resonancia magnética (RM), y al igual que esta, tiene como principio el uso de contraste endovenoso para explorar la angiogénesis tumoral. Combina la imagen de mamografía convencional (Mx) con la técnica de sustracción con energía dual poscontraste, lo que resulta en un incremento en la detección de cáncer de mama, en un tiempo corto de estudio y a un bajo costo. Es un método prometedor en casos seleccionados y de fácil lectura, siendo útil principalmente en pacientes con diagnóstico de cáncer de mama para detectar lesiones adicionales y determinar el tamaño tumoral, ayudando en la planificación quirúrgica, así como también en la evaluación de la respuesta a la neoadyuvancia. También en el seguimiento de pacientes operadas, para caracterizar lesiones dudosas en Mx y ecografía, o como alternativa ante contraindicación de la RM. El objetivo de este trabajo es valorar la utilidad de la mamografía contrastada en la práctica diaria y determinar sus principales indicaciones. Repasamos con casos propios las utilidades y características del método.

Abstract Contrast-enhanced digital mammography (CEDM) is an emerging tool that has been increasingly implemented. It appears as an alternative to magnetic resonance imaging (MRI), using intravenous contrast to explore tumor angiogenesis. It combines conventional mammography (Mx) with post-contrast dual energy subtraction technique, resulting in increased detection of breast cancer, in a short study time and at a low cost. It is a promising method in selected cases and easy to read, being useful mainly in patients with breast cancer to detect additional lesions and determine the tumor size, that helps surgical planning, as well as in the evaluation of post-neoadjuvant chemotherapy response in the follow-up of patients treated with surgery, to address inconclusive findings in screening mammogram, or as an alternative when MRI is contraindicated. The purpose of this article is to assess the usefulness of contrasted mammography in daily practice and to determine its main indications. We review with our own cases the applications and characteristics of this method.

Multiscale Monte Carlo simulations for dosimetry in x-ray breast imaging: Part I - Macroscopic scales.

BACKGROUND: X-ray breast imaging modalities are commonly employed for breast cancer detection, from screening programs to diagnosis. Thus, dosimetry studies are important for quality control and risk estimation since ionizing radiation is used. PURPOSE: To perform multiscale dosimetry assessments for different breast imaging modalities and for a variety of breast sizes and compositions. The first part of our study is focused on macroscopic scales (down to millimeters). METHODS: Nine anthropomorphic breast phantoms with a voxel resolution of 0.5 mm were computationally generated using the BreastPhantom software, representing three breast sizes with three distinct values of volume glandular fraction (VGF) for each size. Four breast imaging modalities were studied: digital mammography (DM), contrast-enhanced digital mammography (CEDM), digital breast tomosynthesis (DBT) and dedicated breast computed tomography (BCT). Additionally, the impact of tissue elemental compositions from two databases were compared. Monte Carlo (MC) simulations were performed with the MC-GPU code to obtain the 3D glandular dose distribution (GDD) for each case considered with the mean glandular dose (MGD) fixed at 4 mGy (to facilitate comparisons). RESULTS: The GDD within the breast is more uniform for CEDM and BCT compared to DM and DBT. For large breasts and high VGF, the ratio between the minimum/maximum glandular dose to MGD is 0.12/4.02 for DM and 0.46/1.77 for BCT; the corresponding results for a small breast and low VGF are 0.35/1.98 (DM) and 0.63/1.42 (BCT). The elemental compositions of skin, adipose and glandular tissue have a considerable impact on the MGD, with variations up to 30% compared to the baseline. The inclusion of tissues other than glandular and adipose within the breast has a minor impact on MGD, with differences below 2%. Variations in the final compressed breast thickness alter the shape of the GDD, with a higher compression resulting in a more uniform GDD. CONCLUSIONS: For a constant MGD, the GDD varies with imaging modality and breast compression. Elemental tissue compositions are an important factor for obtaining MGD values, being a source of systematic uncertainties in MC simulations and, consequently, in breast dosimetry.

Artificial Intelligence in Breast Imaging: A Special Focus on Advances in Digital Mammography & Digital Breast Tomosynthesis.

Breast cancer accounts for 30% of female cancers and is the second leading cause of cancerrelated deaths in women. The rate is rising at 0.4% per year. Early detection is crucial to improve treatment efficacy and overall survival of women diagnosed with breast cancer. Digital Mammography and Digital Breast Tomosynthesis have widely demonstrated their role as a screening tool. However, screening mammography is limited by radiologist's experience, unnecessarily high recalls, overdiagnosis, overtreatment and, in the case of Digital Breast Tomosynthesis, long reporting time. This is compounded by an increasing shortage of manpower and resources issue, especially among breast imaging specialists. Recent advances in image analysis with the use of artificial intelligence (AI) in breast imaging have the potential to overcome some of these needs and address the clinical challenges in cancer detection, assessment of treatment response, and monitoring disease progression. This article focuses on the most important clinical implication and future application of AI in the field of digital mammography and digital breast tomosynthesis, providing the readers with a comprehensive overview of AI impact in cancer detection, diagnosis, reduction of workload and breast cancer risk stratification.

Estudios mamográficos en un centro metropolitano de referencia en imágenes mamarias: Chile 2008-2018 ¿Vamos por el camino correcto? / Analysis of mammograms performed in a public imaging center in Santiago, Metropolitan Region Chile 2008-2018

BACKGROUND: Mammograms are one of the most effective preventive means for the early detection of breast cancer. OBJECTIVE: To describe the features of patients and results of mammograms performed at a public breast imaging service of the Santiago Metropolitan Area. MATERIAL AND METHODS: We reviewed the reports of mammograms performed on 174,017 women and 18 men, between 2008 and 2018 in an Imaging Center. The BI-RADS classification was used in the reports. RESULTS: Forty-six percent of mammograms (75,781) were reported as BI-RADS 2. The high proportion of BI-RADS 4 reports (674 reports) was seen in patients aged 40 to 49 years, corresponding to 30% of reports in this age range. Among patients aged 50 to 59 years, there were 779 BI-RADS 4 reports (35%). BI-RADS 5 reports were more common among patients aged 50 to 59 years (50 reports, 30%) and among patients aged 70 years or older (83 reports, 28%). CONCLUSIONS: The presence of a significant number of women between 40 and 49 years of age with a BI-RADS 4 mammography result stands out; being an opportunity to develop new clinical research and public health strategies within the framework of the Universal Health Care policy for breast cancer in Chile.

Comparison of spectra and mean glandular dose (MGD) with tube voltage used in digital mammography for simulated, metrological and clinical cases.

Mammography has a crucial role in breast cancer detection. The National Cancer Institute (INCA) estimates that 29.7% of the cancer cases in Brazil are related specifically to the breast. It is necessary to evaluate the mean glandular dose with a new solid-state detector in a digital radiography system, utilizing PMMA phantoms and spacers for different thicknesses. The Selenia Dimensions (Hologic, Bedford) direct radiography (DR) system can perform full-field digital mammographies through digital detectors. This system uses new technologies, such as the digital breast tomosynthesis system (DBT), and employs a sequence of projections acquired over the breast, resulting in images with low contrast. The estimation of breast dose is an important part of mammographic quality control for x-ray mammography. Nevertheless, there are currently no standard protocols for the dosimetry of breast imaging in 3D. Additionally, a x-ray spectra function is crucial to measure a considerable output in x-ray spectrometry. The purpose of this work was to assess the mean glandular dose (MGD) and the spectra in slabs of polymethyl methacrylate (PMMA) and breast equivalent thickness through digital mammography using four experiments: a Hologic Selenia Dimensions mammograph with a solid-state detector; a spectrometer (only for the spectra, in this case); a clinical COMET x-ray tube with a solid-state detector; and the MCNPX code. References recommend that the real environments that work well with digital mammography are in the following tube voltages: 25 kVp; 26 kVp; 28 kVp; 31 kVp and 33 kVp. Taking into account several thicknesses of PMMA, the results of both the MGD in metrological, clinical and simulated cases were in accordance with the references, from 30 mm of PMMA. All the spectra for all cases have indicated good agreement with the references.

Effect of target/filter combination on the mean glandular dose and contrast-detail threshold: A phantom study.

INTRODUCTION: In mammography it is essential to combine aspects of image quality with compliance with glandular dose levels. The objective of this study was to combine the assessment of the contrast-detail threshold and the mean glandular dose for different target/filter combinations in digital mammography and to indicate the optimal combination through a figure of merit (FOM). METHODS: In a direct digital mammograph, performance and image quality standards were evaluated using a solid-state multidetector capable of measuring various parameters including kerma and standardized phantoms for image quality. After verifying the proper functioning of the mammograph, the contrast-detail detection threshold and the mean glandular dose values for thicknesses ranging from 20 mm to 70 mm in polymethylmethacrylate (PMMA) were evaluated. Combining these values, an FOM was defined to determine the optimal combination. RESULTS: The results indicated that the Mo/Rh and W/Rh combinations present mean glandular doses below the limit for all thicknesses. In contrast, using the Mo/Mo combination, the mean glandular doses were below the limit only up to 45 mm. However, when considering the FOM that combines dosimetric aspects and the contrast-detail threshold, the use of W/Rh is the most optimal option. CONCLUSION: The results obtained in this study demonstrate that the W/Rh combination in direct digital mammography is the option that presents the best trade-off between the mean glandular dose and the contrast-detail detection threshold. IMPLICATIONS FOR PRACTICE: The results demonstrate that the application of the W/Rh combination in direct digital mammography offers an optimized and applicable option, regardless of the thickness of the breast that will be radiographed.

A Novel Fusion-Based Texture Descriptor to Improve the Detection of Architectural Distortion in Digital Mammography.

Architectural distortion (AD) is the earliest sign of breast cancer that can be detected on a mammogram, and it is usually associated with malignant tumors. Breast cancer is one of the major causes of death among women, and the chance of cure can increase significantly when detected early. Computer-aided detection (CAD) systems have been used in clinical practice to assist radiologists with the task of detecting breast lesions. However, due to the complexity and subtlety of AD, its detection is still a challenge, even with the assistance of CAD. Recently, the fusion of descriptors has become a trend for improving the performance of computer vision algorithms. In this work, we evaluated some local texture descriptors and their possible combinations, considering different fusion approaches, for application in CAD systems to improve AD detection. In addition, we present a novel fusion-based texture descriptor, the Completed Mean Local Mapped Pattern (CMLMP), which is based on complementary information between three LMP operators (signal, magnitude and center) and the local differences between pixel values and the mean value of a neighborhood. We compared the performance of the proposed descriptor with two other well-known descriptors: the Completed Local Binary Pattern (CLBP) and the Completed Local Mapped Pattern (CLMP), for the task of detecting AD in 350 digital mammography clinical images. The results showed that the descriptor proposed in this work outperforms the others, for both individual and fused approaches. Moreover, the choice of the fusion operator is crucial because it results in different detection performances.

Characterization of the imaging settings in screening mammography using a tracking and reporting system: A multi-center and multi-vendor analysis.

A tracking and reporting system was developed to monitor radiation dose in X-ray breast imaging. We used our tracking system to characterize and compare the mammographic practices of five breast imaging centers located in the United States and Brazil. Clinical data were acquired using eight mammography systems comprising three modalities: computed radiography (CR), full-field digital mammography (FFDM), and digital breast tomosynthesis (DBT). Our database consists of metadata extracted from 334,234 images. We analyzed distributions and correlations of compressed breast thickness (CBT), compression force, target-filter combinations, X-ray tube voltage, and average glandular dose (AGD). AGD reference curves were calculated based on AGD distributions as a function of CBT. These curves represent an AGD reference for a particular population and system. Differences in AGD and imaging settings were attributed to a combination of factors, such as improvements in technology, imaging protocol, and patient demographics. The tracking system allows the comparison of various imaging settings used in screening mammography, as well as the tracking of patient- and population-specific breast data collected from different populations.

Suspicious amorphous microcalcifications detected on full-field digital mammography: correlation with histopathology.

OBJECTIVE: To evaluate suspicious amorphous calcifications diagnosed on full-field digital mammography (FFDM) and establish correlations with histopathology findings. MATERIALS AND METHODS: This was a retrospective study of 78 suspicious amorphous calcifications (all classified as BI-RADS® 4) detected on FFDM. Vacuum-assisted breast biopsy (VABB) was performed. The histopathological classification of VABB core samples was as follows: pB2 (benign); pB3 (uncertain malignant potential); pB4 (suspicion of malignancy); and pB5 (malignant). Treatment was recommended for pB5 lesions. To rule out malignancy, surgical excision was recommended for pB3 and pB4 lesions. Patients not submitted to surgery were followed for at least 6 months. RESULTS: Among the 78 amorphous calcifications evaluated, the histopathological analysis indicated that 8 (10.3%) were malignant/suspicious (6 classified as pB5 and 2 classified as pB4) and 36 (46.2%) were benign (classified as pB2). The remaining 34 lesions (43.6%) were classified as pB3: 33.3% were precursor lesions (atypical ductal hyperplasia, lobular neoplasia, or flat epithelial atypia) and 10.3% were high-risk lesions. For the pB3 lesions, the underestimation rate was zero. CONCLUSION: The diagnosis of precursor lesions (excluding atypical ductal hyperplasia, which can be pB4 depending on the severity and extent of the lesion) should not necessarily be considered indicative of underestimation of malignancy. Suspicious amorphous calcifications correlated more often with precursor lesions than with malignant lesions, at a ratio of 3:1.

OBJETIVO: Correlacionar o achado mamográfico de calcificações amorfas suspeitas diagnosticadas na mamografia digital com seus diagnósticos anatomopatológicos. MATERIAIS E MÉTODOS: Setenta e oito casos de calcificações amorfas suspeitas (todas classificadas como BI-RADS® 4) detectadas na mamografia digital e submetidas a biópsia percutânea assistida à vácuo foram retrospectivamente avaliados. A classificação anatomopatológica utilizada na biópsia foi: pB2 para lesão benigna, pB3 para lesão com potencial incerto de malignidade, pB4 para lesão suspeita, e pB5 para lesão considerada maligna. O tratamento foi recomendado para as lesões pB5, a exérese cirúrgica foi indicada para lesões pB3 e pB4, para descartar malignidade, e o seguimento evolutivo foi adotado para as demais pacientes. RESULTADOS: A histologia demonstrou 8 (10,3%) casos malignos (6 lesões pB5 e 2 lesões pB4) e 36 (46,2%) casos benignos (pB2). As demais 34 (43,6%) lesões foram classificadas como pB3 (33,3% foram lesões precursoras - hiperplasia ductal atípica, neoplasia lobular ou atipia epitelial plana - e 10,3% foram lesões de alto risco). A taxa de subestimação das lesões pB3 foi zero. CONCLUSÃO: O diagnóstico de lesões precursoras (excluindo hiperplasia ductal atípica, que pode corresponder a lesão pB4 dependendo da severidade e extensão dos achados) na biópsia percutânea assistida à vácuo por calcificações amorfas suspeitas não necessariamente representa lesão subestimada. Calcificações amorfas suspeitas se associaram a lesões precursoras numa proporção de 3:1 em relação às lesões malignas.

Suspicious amorphous microcalcifications detected on full-field digital mammography: correlation with histopathology / Microcalcificações amorfas suspeitas detectadas na mamografia digital: correlação histológica

Abstract Objective: To evaluate suspicious amorphous calcifications diagnosed on full-field digital mammography (FFDM) and establish correlations with histopathology findings. Materials and Methods: This was a retrospective study of 78 suspicious amorphous calcifications (all classified as BI-RADS® 4) detected on FFDM. Vacuum-assisted breast biopsy (VABB) was performed. The histopathological classification of VABB core samples was as follows: pB2 (benign); pB3 (uncertain malignant potential); pB4 (suspicion of malignancy); and pB5 (malignant). Treatment was recommended for pB5 lesions. To rule out malignancy, surgical excision was recommended for pB3 and pB4 lesions. Patients not submitted to surgery were followed for at least 6 months. Results: Among the 78 amorphous calcifications evaluated, the histopathological analysis indicated that 8 (10.3%) were malignant/suspicious (6 classified as pB5 and 2 classified as pB4) and 36 (46.2%) were benign (classified as pB2). The remaining 34 lesions (43.6%) were classified as pB3: 33.3% were precursor lesions (atypical ductal hyperplasia, lobular neoplasia, or flat epithelial atypia) and 10.3% were high-risk lesions. For the pB3 lesions, the underestimation rate was zero. Conclusion: The diagnosis of precursor lesions (excluding atypical ductal hyperplasia, which can be pB4 depending on the severity and extent of the lesion) should not necessarily be considered indicative of underestimation of malignancy. Suspicious amorphous calcifications correlated more often with precursor lesions than with malignant lesions, at a ratio of 3:1.

Resumo Objetivo: Correlacionar o achado mamográfico de calcificações amorfas suspeitas diagnosticadas na mamografia digital com seus diagnósticos anatomopatológicos. Materiais e Métodos: Setenta e oito casos de calcificações amorfas suspeitas (todas classificadas como BI-RADS® 4) detectadas na mamografia digital e submetidas a biópsia percutânea assistida à vácuo foram retrospectivamente avaliados. A classificação anatomopatológica utilizada na biópsia foi: pB2 para lesão benigna, pB3 para lesão com potencial incerto de malignidade, pB4 para lesão suspeita, e pB5 para lesão considerada maligna. O tratamento foi recomendado para as lesões pB5, a exérese cirúrgica foi indicada para lesões pB3 e pB4, para descartar malignidade, e o seguimento evolutivo foi adotado para as demais pacientes. Resultados: A histologia demonstrou 8 (10,3%) casos malignos (6 lesões pB5 e 2 lesões pB4) e 36 (46,2%) casos benignos (pB2). As demais 34 (43,6%) lesões foram classificadas como pB3 (33,3% foram lesões precursoras - hiperplasia ductal atípica, neoplasia lobular ou atipia epitelial plana - e 10,3% foram lesões de alto risco). A taxa de subestimação das lesões pB3 foi zero. Conclusão: O diagnóstico de lesões precursoras (excluindo hiperplasia ductal atípica, que pode corresponder a lesão pB4 dependendo da severidade e extensão dos achados) na biópsia percutânea assistida à vácuo por calcificações amorfas suspeitas não necessariamente representa lesão subestimada. Calcificações amorfas suspeitas se associaram a lesões precursoras numa proporção de 3:1 em relação às lesões malignas.

Optimization of the exposure parameters in digital mammography using contrast-detail metrics.

PURPOSE: Optimization studies in digital mammography aid to assure the image quality and radiological protection of the patient. The aim of this work is to test effectiveness and applicability of a method based on a Figure of Merit (FOM=(IQFinv)2/AGD) to improve all the exposure parameters (Target/Filter combination, kVp and mAs) in order to improve the image acquisition technique that will provide the best compromise between image quality and the average glandular dose (AGD). METHODS: A contrast-detail analysis, employing the test object CDMAM, was carried out for the digital mammography unit manufactured by Lorad Hologic - model Selenia. We simulated two breast thicknesses using phantoms and a Figure of Merit as optimization tool, which includes an indicator of image quality, the IQFinv and the average glandular dose. Images of the ACR and TORMAM phantoms were obtained with both, automatic and optimized exposure parameters. In order to compare the image quality, the SNR (Signal to Noise Ratio) was measured in each image. RESULTS: In the two phantoms, for both 4.5 and 7.5cm thicknesses, the AGDs obtained with the optimized parameters show a reduction. In addition, the images obtained with the optimized exposure parameters, had the same or a better image quality when compared to the images obtained using the automatic mode. CONCLUSIONS: The proposed optimization methodology proved to be an effective tool to improve the digital mammography unit, due to the use of objective metrics for evaluation and validation of the results.

Volumetric Mammogram Assessment: A Helpful Tool in the Treatment of Breast Asymmetries.

The surgical approach to breast asymmetry depends on several factors, including the surgeon's experience, the anatomy of the patient, and several methods that may help to choose a technique and define the size of the implant or the amount of breast tissue to be excised. The aim of this study is to assist in evaluation of breast volumes with the Quantra™ software application, intended for use with Hologic™ digital mammography systems. Twenty-eight women were studied with full-field digital mammography (FFDM) with the Quantra™ software application, for use with Hologic™ digital mammography systems preoperatively. The case diagnoses were as follows: breast hypertrophy, ptosis, hypoplasia, and reconstruction, and the surgeries included breast reduction, mastopexy, mastopexy and breast reduction, mastoplasty and breast augmentation, breast augmentation, and immediate or delayed breast reconstruction. Patients were evaluated from 6 to 18 months after surgery. Volumetric mammogram studies help to decide the amount of tissue to be excised, the size of the implants, and the combination of both. The results of this study were evaluated by surgeons and patients and found to be highly satisfactory. The use of full-field digital mammography with adequate software should be considered as another tool to assist in making decisions regarding the correction of breast asymmetries. Level of Evidence IV This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Breast density pattern characterization by histogram features and texture descriptors

Abstract Introduction Breast cancer is the first leading cause of death for women in Brazil as well as in most countries in the world. Due to the relation between the breast density and the risk of breast cancer, in medical practice, the breast density classification is merely visual and dependent on professional experience, making this task very subjective. The purpose of this paper is to investigate image features based on histograms and Haralick texture descriptors so as to separate mammographic images into categories of breast density using an Artificial Neural Network. Methods We used 307 mammographic images from the INbreast digital database, extracting histogram features and texture descriptors of all mammograms and selecting them with the K-means technique. Then, these groups of selected features were used as inputs of an Artificial Neural Network to classify the images automatically into the four categories reported by radiologists. Results An average accuracy of 92.9% was obtained in a few tests using only some of the Haralick texture descriptors. Also, the accuracy rate increased to 98.95% when texture descriptors were mixed with some features based on a histogram. Conclusion Texture descriptors have proven to be better than gray levels features at differentiating the breast densities in mammographic images. From this paper, it was possible to automate the feature selection and the classification with acceptable error rates since the extraction of the features is suitable to the characteristics of the images involving the problem.

Distorsión de la arquitectura mamaria: la mejor forma de enfrentarla / Distorsion of breast architecture: the best way to confront it

Abstract: Objective. Assess the performance of digital 2D mammography and tomosynthesis in the characterisation of architectural breast distortion (ABD). Material and method. A retrospective study, approved by the Ethics Committee, was conducted on mammographic studies on cases with a diagnosis of ABD selected from August 2015-August 2016. Cases with imaging modalities available on PACS were included: digital mammography (2D), tomosynthesis (TS), ultrasound (US), magnetic resonance (MR), and with biopsy performed at our institution. ABD cases associated with micro-calcifications and post-surgical changes were excluded. Detection rates and imaging characteristics were analysed, as well as the histopathological concordance. Results. A total of 81 cases of ABD without microcalcifications were detected on the mammographs, but only 52 met the inclusion criteria. According to histopathology, 23 (44%) were malignant, 17 (33%) were benign, and 12 (23%) were high-risk lesions. All were detected by TS and US, and classified as suspicious lesions (BI-RADS 4 or 5). In 2D mammography, 24 cases (46%) were not seen and 8 (33%) of these were malignant. Malignant lesions showed dense centres in 87% of cases. The most frequent lesion on ultrasound was a hypoechogenic area (60%) in 86% of lesions with penetrating vessels. A total of 21 MRI were performed, with mass enhancement being identified in all of them. Conclusion. ABD is better displayed in TS than 2D mammography. Despite its characteristics, histological examination is essential (even when a radiolucent centre is observed). Focused US should be the next procedure to follow, since it allows to visualize the lesion to be visualised, and can direct the percutaneous biopsy in most cases.

Resumen: Objetivo. Determinar en qué método de imagen se logra visualizar y caracterizar mejor una distorsión de la arquitectura mamaria (DAM). Material y método. Estudio retrospectivo, aprobado por el Comité de Ética. Se seleccionaron los estudios mamográficos con diagnóstico de DAM en nuestro servicio entre agosto de 2015 y agosto de 2016. Se incluyeron casos estudiados con al menos 3 de las modalidades de imágenes disponibles en PACS: mamografía digital (2D), tomosíntesis (TS), ecografía (US), resonancia (RM) y que fueron biopsiados en nuestra institución. Se excluyeron casos de DAM asociadas con microcalcificaciones y cambios posquirúrgicos. Se evaluaron la tasa de detección, las características imagenológicas y la concordancia histopatológica. Resultados. En 15 meses se detectaron 81 casos de DAM en mamografía; de estos, 52 cumplieron con los criterios de inclusión. Según la histopatología, 23 (44%) resultaron malignas, 17 (33%) benignas y 12 (23%) lesiones de alto riesgo (LAR). Todas fueron detectadas por TS y US, clasificadas como lesiones sospechosas (BI-RADS 4 o 5). En mamografía 2D, 24 casos (46%) quedaron ocultos, y de estos, 8 (33%) resultaron malignos. Las lesiones malignas presentaron centro denso en el 87% de los casos. La lesión más frecuente en ecografía fue el área hipoecogénica (60%), en el 86% de las lesiones con vasos penetrantes. Se contó con 21 RM, identificándose captación tipo masa en las patologías malignas. Conclusión. La DAM es mejor visualizada en TS que en mamografía 2D. Pese a sus características, un estudio histológico es indispensable (incluso al observar un centro radiolúcido). El US dirigido es el paso a seguir, ya que permite visualizar la lesión y dirigir su biopsia percutánea en la mayoría de los casos.

WE-E-217BCD-02: Update on the Upcoming ACR Digital Mammography QC Manual.

PURPOSE: We propose a new metric called Distance Discordance (DD), which is defined as the distance between two anatomic points from two moving images, which are co-located on some reference image, when deformed onto another reference image. METHODS: To demonstrate the concept of DD, we created a reference software phantom which contains two objects. The first object (1) consists of a hollow box with a fixed size core and variable wall thickness. The second object (2) consists of a solid box of fixed size and arbitrary location. 7 different variations of the fixed phantom were created. Each phantom was deformed onto every other phantom using two B-Spline DIR algorithms available in Elastix and Plastimatch. Voxels were sampled from the reference phantom [1], which were also deformed from moving phantoms [2…6], and we find the differences in their corresponding location on phantom [7]. Each voxel results in a distribution of DD values, which we call distance discordance histogram (DDH). We also demonstrate this concept in 8 Head & Neck patients. RESULTS: The two image registration algorithms produced two different DD results for the same phantom image set. The mean values of the DDH were slightly lower for Elastix (0-1.28 cm) as compared to the values produced by Plastimatch (0-1.43 cm). The combined DDH for the H&N patients followed a lognormal distribution with a mean of 0.45 cm and std. deviation of 0.42 cm. CONCLUSIONS: The proposed distance discordance (DD) metric is an easily interpretable, quantitative tool that can be used to evaluate the effect of inter-patient variability on the goodness of the registration in different parts of the patient anatomy. Therefore, it can be utilized to exclude certain images based on their DDH characteristics. In addition, this metric does not rely on 'ground truth' or the presence of contoured structures.

QualIM®: software para treinamento na interpretação de imagens médicas digitais / QualIM®: a software for training in the reading of digital medical images", "_i": "en

OBJETIVO: Foi desenvolvido um software denominado QualIM® - Qualificação de Imagens Médicas para treinamento de profissionais na interpretação de exames digitais de mamografias utilizando ferramentas de manipulação de imagens, em monitores específicos, classificadas em BI-RADS®. MATERIAIS E MÉTODOS: O sistema, desenvolvido em Delphi 7, armazena as respostas da interpretação de imagens mamográficas durante o treinamento e compara aos dados inseridos denominados "padrão-ouro". O sistema contém imagens de computed radiography, direct radiography e digitalizadas. O software converte as imagens do computed radiography e direct radiography para o formato TIFF, mantendo as resoluções espacial e de contraste originais. Profissionais em treinamento manipulam o realce da imagem utilizando ferramentas de software (zoom, inversão, réguas digitais, outras). Dependendo da complexidade, são apresentadas até oito incidências mamográficas, seis imagens de ultra-som e duas de anatomopatológico. RESULTADOS: O treinamento iniciou em 2007 e atualmente faz parte do programa de residência em radiologia. O software compõe o texto, de forma automática, das informações inseridas pelo profissional, baseado nas categorias BI-RADS, e compara com a base de dados. CONCLUSÃO: O software QualIM é uma ferramenta digital de ensino que auxilia profissionais no reconhecimento de padrões visuais de uma imagem mamográfica, bem como na interpretação de exames mamográficos, utilizando a classificação BI-RADS.

OBJECTIVE: A software called QualIM® - Qualificação de Imagens Médicas was developed for training of practitioners in the interpretation of digital mammograms classified according to BI-RADS® categories, utilizing images manipulation tools on state-of-the-art displays. MATERIALS ANDMETHODS: A Delphi 7-based system stores data resulting from mammographic findings interpretation during the training, comparing them with a golden-standard data set. The database includes computed radiography, direct radiography and digitized images. The software converts computed radiography and direct radiography images into TIFF format, preserving their original spatial and contrast resolution. During the training, the images are manipulated with the aid of the software tools (zoom, inversion, digital rulers and others). Depending on the image complexity, up to eight mammographic views, six ultrasonography images and two anatomopathological images can be displayed. RESULTS: The training was initiated in 2007 and is currently included in the radiology residency program. Based on data entered by the practitioner, the software automatically generates a BI-RADS compliant text that is compared with a database. CONCLUSION: The QualIM software is a digital educational tool aimed at assisting practitioners in the recognition of visual patterns on mammographic images as well as in the interpretation of mammograms based on the BI-RADS classification.

Mamografía "full digital" directa o en campo completo: experiencia preliminar / Direct or full-field "full digital" mammography: preliminary experience

Análisis de la introducción de una nueva tecnología en Chile llamada "mamografía full digital o campo completo" para la detección precoz del cáncer de mama no palpable. Esta tecnología se ha desarrollado en Europa, Estados Unidos y en algunos países de Sud América. Se describen las ventajas de la mamografía full digital en la detección de microcalcificaciones comparada con la mamografía convencional. La mamografía digital en campo total permite que se visualice toda la glándula mamaria, desde la piel hasta la pared torácica (1, 2, 3). Entre julio del 2001 y julio del 2002 se estudiaron con mamografía full digital 3.176 pacientes. Se utilizó un mamógrafo digital de campo completo, General Electric Senographe 2000 D. Solo 48 casos disponían de una mamografía convencional reciente. En 10 de las 48 pacientes la mamografía digital detectó microcalcificaciones sospechosas, no visualizadas en mamografía convencional. Estos hallazgos modificaron en algunos casos la conducta de tratamiento en éstas pacientes (3-4).

Introduction of a new technology called "full field digital mammography" (FFDM) for the detection of non palpables breast cancers. The GE Senographe 2000 D is the world`s first all digital mammography system and is installed in Europe, USA and some countries of LatinAmerica. Description of the advantages of full field digital mammography in comparison to conventional Film-Screen Mammography. (FSM) in the study and detection of microcalcifications. Full field digital mammography gives better visibility of the breast, particularly near the skin line , the chest wall and in women with dense breast tissue. Between july 2001 and july 2002, 3.176 patients were studied with full digital mammography with a GE Senographe 2000 D. Only 48 cases had a recently conventional mammography and in 10 of the 48 cases the full digital mammography detected suspicious microcalcifications not seen in conventional mammography. This results changed the patient treatment in some cases.