Search

The screening of individuals at high risk of breast cancer has become an important issue in recent years. Since this population consists mostly of young women with dense breasts, new modalities such as magnetic resonance imaging (MRI) and ultrasonography (US) have been evaluated, and MRI screening has been implemented in some countries, because of its higher sensitivity and specificity than those of conventional mammography in the sceening of dense breasts. MRI is the most sensitive method for the detection of invasive breast cancers, and provides the best assessment of the extent of the disease, multifocality, bilaterality, an extensive intraductal component (especially ductal carcinoma in situ without microcalcifications), and the involvement of skin, the pectoral muscle or the chest wall. After the diagnosis of breast cancer, MRI is able to detect additional foci in the same or in the contralateral breast in up to 24% of the cases, which frequently results in changes in the therapy plan. MRI is also a successful imaging method for the detection of residual and recurrent disease. [ABSTRACT FROM AUTHOR]

In the randomized controlled trials carried out in the late 1970s and the 1980s, mammographic screening was demonstrated to have an impact in decreasing mortality from breast cancer. The evaluation of mammographic service screening programmes implemented in several Western European countries in the late 1980s and the 1990s demonstrated that these programmes may have an even higher effect on breast cancer mortality than indicated in the randomized controlled trials. Breast cancer is in most cases a progressive disease, and early detection may arrest its progression. Consequently, earlier detection of breast cancers in their preclinical stage can be expected to lower the breast cancer mortality rate. To achieve this goal, high-quality organized mammographic screening is essential. The prerequisites for high-quality screening mammography are dedicated screening units, a multidisciplinary approach, including the team work of radiologists, pathologists, surgeons and oncologists, and ongoing quality assurance of the performance indicators of the screening program. The detection of early breast cancers, i.e. non-palpable ductal carcinoma in situ and invasive cancers measuring less than 15 mm, is a great challenge for the radiologist, as illustrated by the major problems of interobserver variability and discordant interpretations in organized screening programmes with double reading. Since the effect of screening on the breast cancer mortality rate can be demonstrated only after some years, the ongoing evaluation of performance indicators according to the European Guidelines is of utmost importance. [ABSTRACT FROM AUTHOR]

In this paper, we propose a method to identify abnormal growth of cells in breast tissue and suggest further pathological test, if necessary. We compare normal breast tissue with malignant invasive breast tissue by a series of image processing steps. Normal ductal epithelial cells and ductal / lobular invasive carcinogenic cells also consider for comparison here in this paper. In fact, features of cancerous breast tissue (invasive) are extracted and analyses with normal breast tissue. We also suggest the breast cancer recognition technique through image processing and prevention by controlling p53 gene mutation to some greater extent. [ABSTRACT FROM AUTHOR]

This paper proposes a method to simplify a computational model from logistic regression for clinical use without computer. The model was built using human interpreted featrues including some BI-RADS standardized features for diagnosing the malignant masses. It was compared with the diagnosis using only assessment categorization from BI-RADS. The research aims at assisting radiologists to diagnose the malignancy of breast cancer in a way without using automated computer aided diagnosis system. [ABSTRACT FROM AUTHOR]

This paper presents a computer-aided approach to enhancing suspicious lesions in digital mammograms. The developed algorithm improves on a well-known preprocessor filter named contrast-limited adaptive histogram equalization (CLAHE) to remove noise and intensity inhomogeneities. The proposed preprocessing filter, called fuzzy contrast-limited adaptive histogram equalization (FCLAHE), performs non-linear enhancement. The filter eliminates noise and intensity inhomogeneities in the background while retaining the natural gray level variations of mammographic images within suspicious lesions. We applied Catarious segmentation method (CSM) to compare the segmentation accuracy in two scenarios: when there is no preprocessing filter, and when the proposed preprocessing filter is applied to the original image. The proposed filter has been evaluated on 50 real mammographic images and the experimental results show an average increase of segmentation accuracy by 14.16% when the new filter is applied. [ABSTRACT FROM AUTHOR]

The purpose of this study is to evaluate the potential of computer-aided diagnosis (CADx) methods utilizing three breast imaging modalities: full-field digital mammography (FFDM), sonography, and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for breast lesion classification. Three separate databases for each modality were retrospectively organized: FFDM (255 malignant lesions, 177 benign lesions), ultrasound (968 malignant lesions, 158 benign lesions), and DCE-MRI (347 malignant lesions, 129 benign lesions). From these single-modality databases, three dual-modality databases were constructed as well as a triple-modality database (31 malignant lesions, 17 benign lesions). Our computerized analysis methods consisted of several steps: (1) automatic lesion segmentation; (2) automatic feature extraction; (3) automatic feature selection; (4) merging of selected features into a probability of malignancy. Stepwise linear discriminant analysis using a Wilks lambda cost function in a leave-one-lesion-out method was used for feature selection. The selected features were merged using a Bayesian artificial neural network (BANN) with a leave-one-lesion-out method. The classification performance was assessed using receiver-operating characteristics (ROC) analysis. Results showed that the computerized analysis of breast lesions using image information from all three modalities yielded an AUC of 0.95±0.03. The observed trend of increasing performance as information from more modalities is included in the classifier indicates that the use of all three modalities can potentially improve the diagnostic classification of CADx. [ABSTRACT FROM AUTHOR]

Classification of linear structures, such as blood vessels, milk ducts, spiculations and fibrous tissue can be used to aid the automated detection and diagnosis of mammographic abnormalities. We use a combination of dual-tree complex wavelet coefficients and random forest classification to detect and classify different types of linear structure. Encouraging results are presented for synthetic linear structures added to real mammographic backgrounds, and spicules in real mammograms. For spicule/non-spicule classification in real mammograms we report an area Az = 0.764 under the receiver operating characteristic. [ABSTRACT FROM AUTHOR]

The appearance of breast tissue in mammograms is altered by the presence of a malignant mass. Existing synthesis methods have not addressed this structural deformation. We aim to use a set of mass background images that display altered breast tissue to simulate such deformations in regions of digital mammograms previously showing no signs of disease. Regions are decomposed using the dual-tree complex wavelet transform (DT-CWT) to obtain a richer representation of local structure than provided by image grey-levels alone. Synthesis is achieved by modifying the high-frequency DT-CWT coefficients of normal regions to match those in mass backgrounds. Three methods for completing this task are described. The results, advantages and current limitations of the methods are discussed. [ABSTRACT FROM AUTHOR]

Comparing the clinical performance of digital mammography technologies is challenging. The aim of this work is to develop and test a methodology for adjusting mammographic images taken on a given imaging system to simulate their appearance as if taken on a different system. Such methodology would be very useful for a wide range of system performance and design studies using both phantom and clinical images. The process involves changing the image blurring in accordance with the measured modulation transfer functions and adding noise (electronic, quantum and structure). The method has been tested by adapting flat field images acquired using an amorphous selenium detector and a computed radiography (CR) detector to different dose levels and comparing the resultant simulated NPSs with directly measured NPSs. For the detectors used in this work the NPSs at different dose levels are well predicted. This could be a powerful tool for studies of clinical image quality. [ABSTRACT FROM AUTHOR]

We investigated the link between the results from daily quality control (QC) data, on the one hand, and from successive half-yearly medical physics QC visits on the other hand. To do so, criteria defining `unchanged results΄ were set for both the daily QC data and the half-yearly QC results. Out of the results of 181 QC visits and daily QC at the time of the QC visit, we found that systems that showed little or no deviation in daily constancy performance were likely to show basically unchanged results in the half-yearly medical physics test. The specificity of the daily QC data for a change in results at QC visits was 93% for the dose and SDNR test and 88% for a change in contrast threshold values. Daily QC data could be used to prioritize the work load of the medical physicist. [ABSTRACT FROM AUTHOR]

Using mammograms in which signs of breast cancer have been synthesised overcomes the problem of obtaining a sufficiently large volume of real data with known ground truth for training and test purposes. This paper describes a fully automated method for generating synthetic spiculated masses. Statistical methods are used to model the appearance and location of a training set of real masses and their effect on surrounding breast tissue. The models are then used to synthesise the appearance of a malignant mass in an otherwise normal mammogram. By virtue of using generative statistical models, the synthesis process can be fully automated. In an observer study in which 10 expert mammogram readers attempted to distinguish between synthetic masses generated by the method and real masses, we report an area Az = 0.70±0.09 under the receiver operating characteristic. [ABSTRACT FROM AUTHOR]

As the number of installed digital breast tomosynthesis (DBT) systems increases, the need for quality control routines rises. Current work reports on our initial experience with a newly developed method for the analysis of DBT acquisitions of a homogenous phantom. Both the uniformity of the projection as of the reconstruction data is analyzed, together with the in-plane and inter-plane noise variations. The approach was tested in 2 different ways: on DBT projection and reconstructed data of different vendors and via simulations of potential detector artifacts known from 2D mammography into the projection images of the DBT (and followed by reconstruction of the hybrid data). The following potentially disturbing artifacts were observed: localized detector artifacts, modification of reconstruction software settings and synchronization issues. Our results indicate that the proposed method could be an easy and reliable way of performing constancy checking of DBT systems. [ABSTRACT FROM AUTHOR]

Clinical research has shown that breast cancer risk is strongly related to characteristic mixture of breast tissues as seen on mammographic images. We present an automatic mammographic image segmentation approach, which uses a novel texture signature based methodology, the resultant segmentation can be found useful as a means of aiding radiologists΄ estimation in mammographic risk assessment. The developed approach consists of four distinct steps: 1) feature extraction use a stack of small detail annotated mammographic patches, 2) Tabár mammographic building blocks are modelled as texture signatures, 3) model selection and reduction is used to remove noise and possible outliers, and 4) mammographic image segmentation. Visual assessment indicates good and consistent segmentation results. The MIAS database was used in a quantitative and qualitative evaluation with respect to mammographic risk assessment based on both Tabár and Birads risk categories. We found substantial agreement (Κ= 0.7 and 0.75 based on Tabár and Birads risk categories, respectively) between classification results and ground truth data. Classification accuracy were 78% and 75% in Tabár and Birads categories, respectively; 86% and 87% in the corresponding low and high categories for Tabár and Birads, respectively. [ABSTRACT FROM AUTHOR]

Ideally, the outcome of any CAD performance assessment should predict how well the system would work if used clinically. In principle, if the selection process draws cases that are ˵representative″ of the general patient population, the study design will be unbiased. In this study we explored the effect of stratified sampling on stand-alone and radiologists΄ performance using data from an observer study. Although our database was relatively small, 50 cancer cases, no meaningful difference in performance was measured among different stratified sampling schemes or against the whole dataset nor was there any difference in the variance in the measured performance metrics. These results cast doubts on the usefulness of requiring stratified sampling, whose added cost does not seem to be justifiable without empirical evidence. We believe that it is more important to specify how cases should be collected than try to define the range and frequency of the characteristics of patients and cancers to be included the dataset, which we suspect to be prone to actually produce unrealistic samples. [ABSTRACT FROM AUTHOR]

Digital breast tomosynthesis (DBT) is an emerging technique that allows for slices parallel with the detector to be constructed through the breast, as opposed to two dimensional mammography. Present phantoms for use on mammography systems are two dimensional in nature and focus mainly on differences in contrast. Since tomosynthesis is a three-dimensional-technique, a suitable phantom for use on a DBT-system should contain different overlying structures, as is the case within a real breast. We present a method to construct such a three dimensional phantom from a liquid polyurethane-basis that contains overlapping masses, microcalcifications and a representative anatomical background. This way a representative quantitative phantom could be constructed for image quality control on a DBT-system. [ABSTRACT FROM AUTHOR]

In 2006 the fourth edition of the European Guidelines for Breast Cancer Screening and Diagnosis was published by the European Commission. Due to the fast developments in the field of digital mammography and the experience with digital mammography systems over the past years a supplement to the technical quality control procedures proved necessary. This paper describes important changes compared to the Guidelines and their rationale. Testing methods which are new or have changed include: the size of the standard region of interest (ROI), the thickness compensation measurement, noise evaluation, threshold contrast visibility, an AEC measurement which simulates local dense area. A paragraph on evaluation of image processing has been added. With these changes European quality control procedures are again up-to-date with current knowledge. [ABSTRACT FROM AUTHOR]

Lesion detectability in contrast-enhanced digital mammography (CEDM) was studied using a model observer for task-based system evaluation. Digital mammography (DM) and CEDM images were simulated to include a realistic mammographic appearance and contrast enhancement based on simple physiological assumptions of iodinated contrast agent uptake. A Laguerre-Gauss Channelized Hotelling observer (LG-CHO) was implemented to compute the lesion detectability, d', according to the signal-to-noise ratio of the CHO test statistic. Iodine concentrations from 0.3 to 3 mg/ml in simulated lesions resulted in greater d' for log-subtracted CEDM images (acquisition technique of Jong et al. Radiology 2003) compared to full dose DM (standard screening DM acquisition technique). Doubling mean glandular radiation dose yielded only minimal relative gains in d' for all but the lowest lesion contrast agent uptake levels considered, suggesting that quantum noise was not the limiting factor for lesion detectability. [ABSTRACT FROM AUTHOR]

This paper presents a novel representation of Cartesian genetic programming (CGP) in which multiple networks are used in the classification of high resolution X-rays of the breast, known as mammograms. CGP networks are used in a number of different recombination strategies and results are presented for mammograms taken from the Lawrence Livermore National Laboratory database. [ABSTRACT FROM AUTHOR]

Absorbed dose in breast cannot be measured directly in mammography equipments. Therefore, methods based on Compton spectrometry are alternatives to evaluate dose distributions in a simulator of human breast material. In this work, a CdTe detector was used for the Compton spectrometry measurements of radiation scattered at approximately 90° by a PMMA cylinder. To reach the objective, the necessary reconstruction of primary spectra (in units of photon fluence) has been made using Klein-Nishina and Compton theories, followed by a determination of air kerma and, finally, of absorbed dose values in the breast phantom. Incident X-ray spectra and depth-dose distributions in a BR-12 phantom were determined. Results presented here were obtained for mammography range (28 to 35 kV) and show good agreement with literature data. [ABSTRACT FROM AUTHOR]

Patient doses in mammography screening examinations in Lithuania have been investigated within a period between 2003 and 2009. In vivo dose measurements were performed using thermoluminescence dosimetry (TLD) technique. Interactive database MAMOLIT was created, which allowed calculating of patient΄s doses, documenting of measured and calculated doses and other parameters of the mammography screening examination, following up of the frequency of patient related X-ray examinations, and analysing of the collected data from different points of view. Reference level of 2.4 mGy of the average glandular dose was set for mammography screening in Lithuania on the base of the obtained results. Present paper summarises gathered experience and outlines some problems which may occur when performing dose measurements during mammography screening examinations of patients. [ABSTRACT FROM AUTHOR]

How safe is the patient in developing countries and making patient safer has been the objective of the International Action Plan on Radiological Protection of Patients launched by the IAEA in 2002. This requires assessment and comparison of radiation doses to the patients undergoing diagnostic radiological examinations with reference levels without compromising on quality, finding how many patients are getting peak skin dose exceeding the threshold for erythema in interventional procedures (IP) and through this process creating awareness on radiation protection. A number of tools have been used namely; training courses, providing free training material developed in cooperation with international organizations and professional bodies, establishing a new website on radiation protection of patients (http://rpop.iaea.org), guidance documents, establishing networks and launching projects in over 80 countries. It is becoming clear that the patient doses (ESAK) in radiography examinations in many developing countries are generally within established diagnostic reference levels (DRL) but poor image quality is the root cause of higher patient doses, the situation with regard to computed tomography (CT) is different as many patients are receiving higher doses (DLP) than DRLs, in the case of interventional procedures like PTCA, many patients receive higher dose (KAP) than the currently known DRL and in mammography also there is need to achieve better optimization. There have been a number of success stories of optimization demonstrating reduction in patient doses in developing countries without compromising on image quality. With increased usage of high dose procedures in developing countries such as CT & IP and with fast changing technology that poses great challenge in implementing patient dose management, there is a greater need today to focus on patient protection. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the major causes of death among women all over the world. Presently, mammographic analysis is the most used method for early detection of abnormalities. This paper presents a computational methodology to help the specialist with this task. In the first step, the K-Means clustering algorithm and the Template Matching technique are used to detect suspicious regions. Next, the texture of each region is described using the Simpson΄s Diversity Index, which is used in Ecology to measure the biodiversity of an ecosystem. Finally, the information of texture is used by SVM to classify the suspicious regions into two classes: masses and non-masses. The tests demonstrate that the methodology has 79.12% of accuracy, 77.27% of sensitivity, and 79.66% of specificity. [ABSTRACT FROM AUTHOR]

Mammography is considered the most effective method for early detection of the breast cancer. However, it is difficult for radiologists to detect microcalcification (MC) clusters and camouflages masses. The mammograms (MG) images were decomposed into several subimages using Wavelet transform (WT) based on classical and novel class Wavelets using atomic function for reducing the volume of data in the classification stage. Various regions of interest (ROIs) in the MG images were selected where input data for multilayer artificial neural network (ANN) type classifier are formed applying the WT. We used different patterns to classify the normal, MC, spiculated and circumscribed masses ROIs. The detection performance has been evaluated on MG images from the Mammographic Image Analysis Society (MIAS) database. The proposed classification scheme was shown good performance in detecting the MC clusters and masses with acceptable classification. [ABSTRACT FROM AUTHOR]

The use of X-ray image receptors that produce a digital image is becoming increasingly important. Possible benefits include improved dynamic range and detective quantum efficiency, improved detectability for objects of low intrinsic contrast, and reduced radiation dose. The image can be available quickly. The display is separated from the image capture so that processing and contrast adjustment are possible before the image is viewed. The availability of a digital image means ready input into PACS and opens up the possibility of computer-aided detection and classification of abnormality. Possible drawbacks of digital systems include high cost, limited high contrast resolution and the fact that their clinical value is sometimes not proven in comparison with conventional, analogue techniques. The high contrast resolution attainable with such systems is discussed and the problem of sampling limitations and aliasing considered. The properties and limitations of digital systems using computed radiography, caesium iodide plus CCDs and active matrix arrays with either caesium iodide or selenium detectors are demonstrated. Examples are given of digital systems for mammography and general radiography and their performance is demonstrated in terms of clinical assessment and measurements of the modulation transfer function and detective quantum efficiency. [ABSTRACT FROM AUTHOR]

In reading mammograms, radiologists judge for the presence of a lesion by comparing at least two breast projections (views) as a lesion is to be observed in both of them. Most computer-aided detection (CAD) systems, on the other hand, treat single views independently and thus they fail to account for the interaction between the breast views. Following the radiologist΄s practice, in this paper, we develop a Bayesian network framework for automatic multi-view mammographic analysis based on causal independence models and the regions detected as suspicious by a single-view CAD system. We have implemented two versions of the framework based on different definitions of multi-view correspondences. The proposed approach is evaluated and compared against the single-view CAD system in an experimental study with real-life data. The results show that using expert knowledge helps to increase the cancer detection rate at a patient level. [ABSTRACT FROM AUTHOR]

We propose an approach for analyzing tree-like structures in biomedical images. Our analysis is based on Vector Quantization (VQ), an image compression technique. Here, we approach VQ from a different perspective: we use the histogram of the codeword usage as a feature vector representing the initial image. As ductal tree topology has predictive value for a variety of diseases, such as papilloma, ductal ectasia, and ductal carcinoma, we chose to apply this technique to compare texture of the breast ductal tree in x-ray galactograms against the same tissue in corresponding unenhanced mammograms, which do not visualize the ductal tree. We also investigate the relationship between texture and the underlying ductal branching topology using descriptors adapted from the data mining literature. We believe that our method has the potential to assist the interpretation of clinical images and deepen our understanding of relationships among structure, texture, function, and pathology. [ABSTRACT FROM AUTHOR]

In this paper, we present a method for microcalcification detection on filtered back-projection reconstructed slices of breasts acquired on a Digital Breast Tomosynthesis system. Performance of the algorithm has been evaluated on a ground-truth database composed of 50 cases (13 lesions, 37 normals). Since the method is derived from an algorithm developed to detect microcalcifications on 2D digital mammograms, a comparison in terms of performances is provided leading to a discussion for future improvements. [ABSTRACT FROM AUTHOR]

The appearance of tissue in mammograms is altered by the presence of a mass. Existing mass synthesis methods have not addressed this structural deformation. We present a method for modifying the fine-scale detail in regions of digital mammograms. Regions are decomposed into sub-bands localised in scale and orientation using a wavelet-like decomposition. New structures are synthesised in the high frequency components of the decomposition, leaving coarse levels of the pyramid unchanged. In contrast to existing methods of synthesising mammographic texture, this ensures the global appearance of the region is maintained. Early results in the form of synthesised regions show the promise of this approach. [ABSTRACT FROM AUTHOR]

Computer-aided detection (CAD) systems are improving their performance both in terms of sensitivity and specificity, but false prompts remain an area of interest because of their potential to distract from prompts marking real abnormalities and to reduce the importance attached to any given prompt by a film reader. Many false prompts are very near to the threshold for prompting: in this study we investigate reproducibility of prompting by a commercial CAD system. [ABSTRACT FROM AUTHOR]

Under typical dark conditions found in mammography reading rooms, a reader΄s pupils will contract and dilate as the visual focus moves between the high luminance display and the darker background wall, potentially resulting in visual fatigue and degraded diagnostic performance. A controlled increase of ambient lighting can, however, minimize this luminance discrepancy, potentially reducing pupillary action while improving reader comfort and detection ability. A psychophysical study was conducted to determine the effect of a controlled ambient lighting increase on observer detection of subtle masses within mammograms viewed on a DICOM-calibrated medical-grade LCD. Four mammographers read 86 mammograms (43 normal and 43 with cancerous masses) under a dark room condition (1 lux) and an elevated room illuminance level (50 lux). Results show generally constant or decreased average selection times and decreased average observer performance under elevated illuminance. Differences, however, were not statistically significant, and of the same magnitude as interobserver variability. [ABSTRACT FROM AUTHOR]

Tomosynthesis as a technique is being developed and studied with the goal of overcoming mammography΄s limitations due to overlying tissue. Various algorithms exist for tomosynthesis datasets including a novel Computer Aided Detection (CADe) algorithm using a featureless False Positive (FP) reduction stage. The goal of this project is to study the previously unexplored effects of variation of Region of Interest (ROI) sizes as well as the crucial similarity metrics for such a CADe algorithm΄s performance. Four datasets consisting of 1479 tomosynthesis ROIs were generated by a CADe algorithm from reconstructed volumes of one hundred subjects consisting of 4 different sizes – 128 x 128, 256 x 256, 512 x 512, and 1024 x 1024 pixels. Five different similarity metrics – (1) mutual information, (2) average conditional entropy, (3) joint entropy, (3) Jensen divergence and (4) average Kullback-Leibler divergence were used for the task of FP reduction using a leave-one-case-out sampling scheme. Mutual information and average conditional entropy were the best performing metrics with an Area Under Curve (AUC) of 0.88. Cross-bin measures performed consistently higher than those that rely on only marginal distributions. Also, for all metrics, the datatset consisting of 256 x 256 pixel ROIs gave the best performance. In conclusion, for the tomosynthesis dataset, cross-bin measures such as MI and average conditional entropy should be used over other metrics using a ROI size of 256 x 256 pixels. [ABSTRACT FROM AUTHOR]

Temporal comparison is indispensable for mammography reading. In this paper, we propose a new method to perform temporal comparison of digital mammograms using persistence of vision and propose a dense-tissue-preserving registration method for the temporal alignment. In this method, we use non-rigid registration to deform a prior mammogram to align with its corresponding current mammogram. We apply a dense-tissue-preserving constraint to the registration to preserve the shape and size of the dense tissue areas. Once aligned, we toggle the display back and forth between the current mammogram and its corresponding registered prior mammogram. The proposed method was applied to 11 temporal mammogram cases and evaluated by two experienced radiologists. [ABSTRACT FROM AUTHOR]

In the UK, a large-scale collaborative research project (GIMI: Generic Infrastructures for Medical Informatics) is underway which is concerned with the development of a secure IT infrastructure to support very widespread medical research across the country. One aspect of this project is to develop a training tool for potential use by mammographers in the UK Breast Screening Programme. A working prototype system has been developed which is currently being tested by clinical colleagues so as to enable it to be further developed prior to any wider deployment. This is currently based on knowing an individual΄s strengths and weaknesses in mammographic interpretation. The background to the project is given and then the ongoing research is detailed together with future plans for the proposed system. [ABSTRACT FROM AUTHOR]

Chapter 11 of the book "Journey Across the Life Span" is presented. It describes the physiological changes that occur during early adulthood. It discusses the psychosocial task for the early adulthood period as identified by psychologist Erik Erikson. It identifies the Papanicolaou test and mammography as two health screening tests important for women in early adulthood.

Mammography is a vital screening test for breast cancer because early diagnosis is the most effective means of decreasing the death rate from this disease. However, interpreting the mammographic images and rendering the correct diagnosis is challenging. The diagnostic accuracy of mammography varies with the expertise of the radiologist interpreting the images, resulting in significant variability in screening performance. Radiologists interpreting mammograms must manage uncertainties arising from a multitude of findings. We believe that much of the variability in mammography diagnostic performance arises from heuristic errors that radiologists make in managing these uncertainties. We developed a Bayesian network that models the probabilistic relationships between breast diseases, mammographic findings and patient risk factors. We have performed some preliminary evaluations in test cases from a mammography atlas and in a prospective series of patients who had biopsy confirmation of the diagnosis. The model appears useful for clarifying the decision about whether to biopsy abnormalities seen on mammography, and also can help the radiologist correlate histopathologic findings with the mammographic abnormalities observed. Our preliminary experience suggests that this model may help reduce variability and improve overall interpretive performance in mammography. [ABSTRACT FROM AUTHOR]

In the scope of the RAPSODI EU research project, a prototype detector for in-vivo dose measurements in Mammography was developed. We present and discuss first results on the system qualification, in particular on the linear dynamic range, the energy response and the radiological as well as optical transparency of the detector. [ABSTRACT FROM AUTHOR]

Mammography is an effective and widely used method for breast diagnostics and early detection of breast cancer (screening). In order to obtain high quality mammograms at an acceptable breast dose, it is essential to use the correct equipment and perform regular quality control tests on mammography equipment. The aim of this work was to optimize radiation protection of patient and improve quality of mammography examinations by evaluating clinical image quality and measuring the entrance surface air-kerma for standard 4.5 cm breast thickness and the optical density of films herewith identifying problems and taking correction actions for optimization. The evaluation of mammography images of more than 180 patients was done according to selected image quality criteria and overall image quality assessment on a 5 point scale. The evaluation was performed in two hospitals. The results showed that up to 48% of cranio-caudal and 26% of medio-lateral oblique mammograms didn΄t fulfill all quality criteria, but only about 4% of images were unacceptable or of suboptimal quality. The repeated (after corrective actions) image quality evaluation revealed the improvement of image quality up to 30%. The entrance surface airkerma values were in range of 3.1-11.6 mGy and optical densities of films were in range of 1.11-1.86. The survey exhibited the potentiality to optimize radiation protection during mammography procedures by performing periodical image quality assessments and monitoring of doses. [ABSTRACT FROM AUTHOR]