Understanding Clinical Mammographic Breast Density Assessment: a Deep Learning Perspective

Mammographic breast density has been established as an independent risk marker for developing breast cancer. Breast density assessment is a routine clinical need in breast cancer screening and current standard is using the Breast Imaging and Reporting Data System (BI-RADS) criteria including four qualitative categories (i.e., fatty, scattered density, heterogeneously dense, or extremely dense). In each mammogram examination, a breast is typically imaged with two different views, i.e., the mediolateral oblique (MLO) view and cranial caudal (CC) view. The BI-RADS-based breast density assessment is a qualitative process made by visual observation of both the MLO and CC views by radiologists, where there is a notable inter- and intra-reader variability. In order to maintain consistency and accuracy in BI-RADS-based breast density assessment, gaining understanding on radiologists’ reading behaviors will be educational. In this study, we proposed to leverage the newly emerged deep learning approach to investigate how the MLO and CC view images of a mammogram examination may have been clinically used by radiologists in coming up with a BI-RADS density category. We implemented a convolutional neural network (CNN)-based deep learning model, aimed at distinguishing the breast density categories using a large (15,415 images) set of real-world clinical mammogram images. Our results showed that the classification of density categories (in terms of area under the receiver operating characteristic curve) using MLO view images is significantly higher than that using the CC view. This indicates that most likely it is the MLO view that the radiologists have predominately used to determine the breast density BI-RADS categories. Our study holds a potential to further interpret radiologists’ reading characteristics, enhance personalized clinical training to radiologists, and ultimately reduce reader variations in breast density assessment.     

An ellipse-fitting based method for efficient registration of breast masses on two mammographic views

When reading mammograms, radiologists routinely search for and compare suspicious breast lesions identified on two corresponding craniocaudal (CC) and mediolateral oblique (MLO) views. Automatically identifying and matching the same true-positive breast lesions depicted on two views is an important step for developing successful multiview based computer-aided detection (CAD) schemes. The authors developed a method to automatically register breast areas and detect matching strips of interest used to identify the matched mass regions depicted on CC and MLO views. The method uses an ellipse based model to fit the breast boundary contour (skin line) and set a local Cartesian coordinate system for each view. One intersection point between the major/minor axis and the fitted ellipse perimeter passed through breast boundary is selected as the origin and the majoraxis and the minoraxis of the ellipse are used as the two axis of the Cartesian coordinate system. When a mass is identified on one view, the scheme computes its position in the local coordinate system. Then, the distance is mapped onto the local coordinate of the other view. At the end of the mapped distance a registered centerline of the matching strip is created. The authors established an image database that includes 200 test examinations each depicting one verified mass visible on the two views. They tested whether the registered centerline identified on another view can be used to locate the matched mass region. The experiments show that the average distance between the mass region centers and the registered centerlines was +/- 8.3 mm and in 91% of testing cases the registered centerline actually passes through the matched mass regions. A matching strip width of 47 mm was required to achieve 100% sensitivity for the test database. The results demonstrate the feasibility of the proposed method to automatically identify masses depicted on CC and MLO views, which may improve future development of multiview based CAD schemes.     

Dosimetric evaluation of the mean glandular dose for mammography in Korean women: a preliminary report

The purpose of this study was to evaluate the thickness of the compressed breast in mediolateral oblique (MLO) and craniocaudal (CC) mammograms, to relate these thickness and breast patterns to mean glandular dose (MGD) in Korean women, and to evaluate the suitability of using the American College of Radiology's Recommendations for Korean women from a quality assurance standpoint. The study population consisted of 92 paired MLO and CC mammograms obtained on one mammographic unit. The digital readouts of compressed breast thickness, applied compression force and tube voltage were recorded. Entrance skin exposure was measured by dosimetry. MGD was calculated by multiplying entrance skin exposure by the exposure-to-absorbed dose conversion factor. The range of breast thickness was 1.3-6.2 cm in CC mammograms with a mean breast thickness of 3.6 cm, and 1.6-6.5 cm in MLO mammograms with a mean breast thickness of 3.9 cm. MGDs in CC and MLO mammograms were 1.77 mSv and 1.88 mSv per view, respectively. Breast composition patterns were divided into 4 groups according to ACR BI-RADS; P1 (n=20), P2 (n=16), P3 (n=48) and P4 (n=8). The MGDs for these groups were: 1.82, 1.84, 1.84, and 1.91 mSv, respectively. When subjects were subdivided by breast thickness into three groups, namely, below 3 cm, 3 cm to 4.2 cm, aaa and above 4.2 cm, the corresponding MGDs were 1.83, 1.86, and 1.91 mSv. According to our initial trial, the mean breast thickness and the MGDs of Korean women are lower than recommended by the American College of Radiology, which are commonly used for quality assurance purposes.     

A breast density index for digital mammograms based on radiologists’ randing

The purpose of this study was to develop and evaluate a computerized method of calculating a breast density index (BDI) from digitized mammograms that was designed specifically to model radiologists’ perception of breast density. A set of 153 pairs of digitized mammograms (cranio-caudal, CC, and mediolateral oblique, MLO, views) were acquired and preprocessed to reduce detector biases. The sets of mammograms were ordered on an ordinal scale (a scale based only on relative rank-ordering) by two radiologists, and a cardinal (an absolute numerical score) BDI value was calculated from the oridinal ranks. The images were also assigned cardinal BDI values by the radiologists in a subsequent session. Six. mathematical features (including fractal dimension and others) were calculated from the digital mammograms, and were used in conjunction with single value decomposition and multiple linear regression to calculate a computerized BDI. The linear correlation coefficient between different ordinal ranking sessions were as follows: intraradiologist intraprojection (CC/CC):r=0.978; intraradiologist interprojection (CC/MLO):r=0.960; and interradiologist intraprojection (CC/CC):r=0.968. A separate breast density index was derived from three separate ordinal rankings by one radiologist (two with CC views, one with the MLO view). The computer derivedBDI had a correlation coefficient (r) of 0.907 with the radiologists’ ordinalBDI. A comparison between radiologists using a cardinal scoring system (which is closest to how radiologists actually evaluate breast density) showedr=0.914. A breast density index calculated by a computer but modeled after radiologist perception of breast density may be valuable in objectively measuring breast density. Such a metric may prove valuable in numerous areas, including breast cancer risk assessment and in evaluating screening techniques specifically designed to improve imaging of the dense breast.     

Combining two mammographic projections in a computer aided mass detection method

A method is presented to improve computer aided detection (CAD) results for masses in mammograms by fusing information obtained from two views of the same breast. It is based on a previously developed approach to link potentially suspicious regions in mediolateral oblique (MLO) and craniocaudal (CC) views. Using correspondence between regions, we extended our CAD scheme by building a cascaded multiple-classifier system, in which the last stage computes suspiciousness of an initially detected region conditional on the existence and similarity of a linked candidate region in the other view. We compared the two-view detection system with the single-view detection method using free-response receiver operating characteristic (FROC) analysis and cross validation. The dataset used in the evaluation consisted of 948 four-view mammograms, including 412 cancer cases with a mass, architectural distortion, or asymmetry. A statistically significant improvement was found in the lesion based detection performance. At a false positive (FP) rate of 0.1 FP/image, the lesion sensitivity improved from 56% to 61%. Case based sensitivity did not improve.     

Computation of the glandular radiation dose in digital tomosynthesis of the breast

Tomosynthesis of the breast is currently a topic of intense interest as a logical next step in the evolution of digital mammography. This study reports on the computation of glandular radiation dose in digital tomosynthesis of the breast. Previously, glandular dose estimations in tomosynthesis have been performed using data from studies of radiation dose in conventional planar mammography. This study evaluates, using Monte Carlo methods, the normalized glandular dose (DgN) to the breast during a tomosynthesis study, and characterizes its dependence on breast size, tissue composition, and x-ray spectrum. The conditions during digital tomosynthesis imaging of the breast were simulated using a computer program based on the Geant4 toolkit. With the use of simulated breasts of varying size, thickness and tissue composition, the DgN to the breast tissue was computed for varying x-ray spectra and tomosynthesis projection angle. Tomosynthesis projections centered about both the cranio-caudal (CC) and medio-lateral oblique (MLO) views were simulated. For each projection angle, the ratio of the glandular dose for that projection to the glandular dose for the zero degree projection was computed. This ratio was denoted the relative glandular dose (RGD) coefficient, and its variation under different imaging parameters was analyzed. Within mammographic energies, the RGD was found to have a weak dependence on glandular fraction and x-ray spectrum for both views. A substantial dependence on breast size and thickness was found for the MLO view, and to a lesser extent for the CC view. Although RGD values deviate substantially from unity as a function of projection angle, the RGD averaged over all projections in a complete tomosynthesis study varies from 0.91 to 1.01. The RGD results were fit to mathematical functions and the resulting equations are provided.     

A new method for quantitative analysis of mammographic density

Women with mammographic percent density >50% have a approximately three-fold increased risk of developing breast cancer, potentially making them screening candidates for breast MRI scanning. The purpose of this work is to introduce a new method to quantify mammographic percent density (MPD), and to compare the results with the current standard of care for breast density assessment. Craniocaudal (CC) and mediolateral oblique (MLO) mammograms for 104 patients were digitized and analyzed using an interactive computer-assisted segmentation routine implemented for two purposes: (1) to segment the breast area from background and radiographic markers, and (2) to segment dense from fatty portions of the breast. Our technique was evaluated by comparing the results to qualitative estimates determined by a certified breast radiologist using the BI-RADS Categorical Assessment (1 (fatty) to 4 (dense) scale). Statistically significant correlations (two-tailed, p < 0.01) were observed between calculated MPD and BI-RADS for both CC (Spearman rho = 0.67) and MLO views (Spearman rho = 0.71). For the CC view, statistically significant differences were revealed between the mean MPD for each BI-RADS category except between fatty (BI-RADS 1) and scattered (BI-RADS 2). Finally, for the MLO views, statistically significant differences in the mean MPD between all BI-RADS categories were observed. Comparing the CC and MLO views revealed a strong positive correlation (Pearson r = 0.8) in calculated MPD. In addition, an evaluation of the reproducibility of our segmentation demonstrated the average standard deviation of MPD for a subsample of eight patients, measured five times, was 1.9% (range: 0.03%-9.9%). Eliminating one misassignment reduced the average standard deviation to 0.75% (range: 0.03%-3.16%). Further analysis of approximately 10% of the patient sample revealed strong agreement (ICC = 0.80-0.85) in the reliability of MPD estimates for both mammographic views. Overall, these results demonstrate the feasibility of utilizing our approach for quantitative breast density segmentation, which may be useful for detecting small changes in MPD introduced through chemoprevention, diet, or other interventions.     

Correlation between mammographic density and volumetric fibroglandular tissue estimated on breast MR images

Previous studies have found that mammographic breast density is highly correlated with breast cancer risk. Therefore, mammographic breast density may be considered as an important risk factor in studies of breast cancer treatments. In this paper, we evaluated the accuracy of using mammograms for estimating breast density by analyzing the correlation between the percent mammographic dense area and the percent glandular tissue volume as estimated from MR images. A dataset of 67 cases having MR images (coronal 3-D SPGR T1-weighted pre-contrast) and corresponding 4-view mammograms was used in this study. Mammographic breast density was estimated by an experienced radiologist and an automated image analysis tool, Mammography Density ESTimator (MDEST) developed previously in our laboratory. For the estimation of the percent volume of fibroglandular tissue in breast MR images, a semiautomatic method was developed to segment the fibroglandular tissue from each slice. The tissue volume was calculated by integration over all slices containing the breast. Interobserver variation was measured for 3 different readers. It was found that the correlation between every two of the three readers for segmentation of MR volumetric fibroglandular tissue was 0.99. The correlations between the percent volumetric fibroglandular tissue on MR images and the percent dense area of the CC and MLO views segmented by an experienced radiologist were both 0.91. The correlation between the percent volumetric fibroglandular tissue on MR images and the percent dense area of the CC and MLO views segmented by MDEST was 0.91 and 0.89, respectively. The root-mean-square (rms) residual ranged from 5.4% to 6.3%. The mean bias ranged from 3% to 6%. The high correlation indicates that changes in mammographic density may be a useful indicator of changes in fibroglandular tissue volume in the breast.     

Correspondence in texture features between two mammographic views

It is well established that radiologists are better able to interpret mammograms when two mammographic views are available. Consequently, two mammographic projections are standard: mediolateral oblique (MLO) and craniocaudal (CC). Computer-aided diagnosis algorithms have been investigated for assisting in the detection and diagnosis of breast lesions in digitized/digital mammograms. A few previous studies suggest that computer-aided systems may also benefit from combining evidence from the two views. Intuitively, we expect that there would only be value in merging data from two views if they provide complementary information. A measure of the similarity of information is the correlation coefficient between corresponding features from the MLO and CC views. The purpose of this study was to investigate the correspondence in Haralick's texture features between the MLO and CC mammographic views of breast lesions. Features were ranked on the basis of correlation values and the two-view correlation of features for subgroups of data including masses versus calcification and benign versus malignant lesions were compared. All experiments were performed on a subset of mammography cases from the Digital Database for Screening Mammography (DDSM). It was observed that the texture features from the MLO and CC views were less strongly correlated for calcification lesions than for mass lesions. Similarly, texture features from the two views were less strongly correlated for benign lesions than for malignant lesions. These differences were statistically significant. The results suggest that the inclusion of texture features from multiple mammographic views in a CADx algorithm may impact the accuracy of diagnosis of calcification lesions and benign lesions.     

Improvement of computerized mass detection on mammograms: fusion of two-view information

Recent clinical studies have proved that computer-aided diagnosis (CAD) systems are helpful for improving lesion detection by radiologists in mammography. However, these systems would be more useful if the false-positive rate is reduced. Current CAD systems generally detect and characterize suspicious abnormal structures in individual mammographic images. Clinical experiences by radiologists indicate that screening with two mammographic views improves the detection accuracy of abnormalities in the breast. It is expected that the fusion of information from different mammographic views will improve the performance of CAD systems. We are developing a two-view matching method that utilizes the geometric locations, and morphological and textural features to correlate objects detected in two different views using a prescreening program. First, a geometrical model is used to predict the search region for an object in a second view from its location in the first view. The distance between the object and the nipple is used to define the search area. After pairing the objects in two views, textural and morphological characteristics of the paired objects are merged and similarity measures are defined. Linear discriminant analysis is then employed to classify each object pair as a true or false mass pair. The resulting object correspondence score is combined with its one-view detection score using a fusion scheme. The fusion information was found to improve the lesion detectability and reduce the number of FPs. In a preliminary study, we used a data set of 169 pairs of cranio-caudal (CC) and mediolateral oblique (MLO) view mammograms. For the detection of malignant masses on current mammograms, the film-based detection sensitivity was found to improve from 62% with a one-view detection scheme to 73% with the new two-view scheme, at a false-positive rate of 1 FP/image. The corresponding cased-based detection sensitivity improved from 77% to 91%.     

Finding corresponding regions of interest in mediolateral oblique and craniocaudal mammographic views

In this paper we present a method to link potentially suspicious mass regions detected by a Computer-Aided Detection (CAD) scheme in mediolateral oblique (MLO) and craniocaudal (CC) mammographic views of the breast. For all possible combinations of mass candidate regions, a number of features are determined. These features include the difference in the radial distance from the candidate regions to the nipple, the gray scale correlation between both regions, and the mass likelihood of the regions determined by the single view CAD scheme. Linear Discriminant Analysis (LDA) is used to discriminate between correct and incorrect links. The method was tested on a set of 412 cancer cases. In each case a malignant mass, architectural distortion, or asymmetry was annotated. In 92% of these cases the candidate mass detections by CAD included the cancer regions in both views. It was found that in 82% of the cases a correct link between the true positive regions in both views could be established by our method. Possible applications of the method may be found in multiple view analysis to improve CAD results, and for the presentation of CAD results to the radiologist on a mammography workstation.     

Computerized image analysis: estimation of breast density on mammograms

An automated image analysis tool is being developed for the estimation of mammographic breast density. This tool may be useful for risk estimation or for monitoring breast density change in prevention or intervention programs. In this preliminary study, a data set of 4-view mammograms from 65 patients was used to evaluate our approach. Breast density analysis was performed on the digitized mammograms in three stages. First, the breast region was segmented from the surrounding background by an automated breast boundary-tracking algorithm. Second, an adaptive dynamic range compression technique was applied to the breast image to reduce the range of the gray level distribution in the low frequency background and to enhance the differences in the characteristic features of the gray level histogram for breasts of different densities. Third, rule-based classification was used to classify the breast images into four classes according to the characteristic features of their gray level histogram. For each image, a gray level threshold was automatically determined to segment the dense tissue from the breast region. The area of segmented dense tissue as a percentage of the breast area was then estimated. To evaluate the performance of the algorithm, the computer segmentation results were compared to manual segmentation with interactive thresholding by five radiologists. A "true" percent dense area for each mammogram was obtained by averaging the manually segmented areas of the radiologists. We found that the histograms of 6% (8 CC and 8 MLO views) of the breast regions were misclassified by the computer, resulting in poor segmentation of the dense region. For the images with correct classification, the correlation between the computer-estimated percent dense area and the "truth" was 0.94 and 0.91, respectively, for CC and MLO views, with a mean bias of less than 2%. The mean biases of the five radiologists' visual estimates for the same images ranged from 0.1% to 11%. The results demonstrate the feasibility of estimating mammographic breast density using computer vision techniques and its potential to improve the accuracy and reproducibility of breast density estimation in comparison with the subjective visual assessment by radiologists.     

Computerized prediction of risk for developing breast cancer based on bilateral mammographic breast tissue asymmetry

This study developed and assessed a computerized scheme to detect breast abnormalities and predict the risk of developing cancer based on bilateral mammographic tissue asymmetry. A digital mammography database of 100 randomly selected negative cases and 100 positive cases for having high-risk of developing breast cancer was established. Each case includes four images of cranio-caudal (CC) and medio-lateral oblique (MLO) views of the left and right breast. To detect bilateral mammographic tissue asymmetry, a pool of 20 computed features was assembled. A genetic algorithm was applied to select optimal features and build an artificial neural network based classifier to predict the likelihood of a test case being positive. The leave-one-case-out validation method was used to evaluate the classifier performance. Several approaches were investigated to improve the classification performance including extracting asymmetrical tissue features from either selected regions of interests or the entire segmented breast area depicted on bilateral images in one view, and the fusion of classification results from two views. The results showed that (1) using the features computed from the entire breast area, the classifier yielded the higher performance than using ROIs, and (2) using a weighted average fusion method, the classifier achieved the highest performance with the area under ROC curve of 0.781 ± 0.023. At 90% specificity, the scheme detected 58.3% of high-risk cases in which cancers developed and verified 6–18 months later. The study demonstrated the feasibility of applying a computerized scheme to detect cases with high risk of developing breast cancer based on computer-detected bilateral mammographic tissue asymmetry.     

Effect of Breast Density on Computer Aided Detection

Purpose: This study was conducted to assess the clinical impact of breast density and density of the lesion’s background on the performance of a computer-aided detection (CAD) system in the detection of breast masses (MA) and microcalcifications (MC). Materials and Methods: A total of 200 screening mammograms interpreted as BI-RADS 1 and suspicious mammograms of 150 patients having a histologically verified malignancy from 1992 to 2000 were selected by using a sampler of tumor cases. Excluding those cases having more than one lesion or a contralateral malignancy attributable to statistical reasons, 127 cases with 127 malignant findings were analyzed with a CAD system (Second Look 5.0, CADx Systems, Inc., Beavercreek, OH). Of the 127 malignant lesions, 56 presented as MC and 101 presented as MA, including 30 cases with both malignant signs. Overall breast density of the mammogram and density of the lesion’s background were determined by two observers in congruence (density a: entirely fatty, density b: scattered fibroglandular tissue, density c: heterogeneously dense, density d: extremely dense). Results: Within the unsuspicious group, 100/200 cases did not have any CAD MA marks and were therefore truly negative (specificity 50%), and 151/200 cases did not have any CAD MC marks (specificity 75.5%). For these 200 cases, the numbers of marks per image were 0.41 and 0.37 (density a), 0.38 and 0.97 (density b), 0.44 and 0.91 (density c), and 0.58 and 0.68 (density d) for MC and MA marks, respectively (Fisher’s t-test: n.s. for MC, p < 0.05 for MA). Malignant lesions were correctly detected in at least one view by the CAD system for 52/56 (92.8%) MC and 91/101 (90.1%) MA. Detection rate versus breast density was: 4/6 (66.7%) and 18/19 (94.7%) (density a), 32/33 (97.0%) and 49/51 (96.1%) (density b), 14/15 (93.3%) and 23/28 (82.1%) (density c), and 2/2 (100%) and 1/3 (33.3%) (density d) for MC and MA, respectively. Detection rate versus the lesion’s background was: 19/21 (90.5%) and 36/38 (94.7%) (density a), 34/36 (94.4%) and 59/62 (95.2%) (density b), 8/9 (88.9%) and 20/24 (83.3%) (density c), and 9/10 (90%) and 4/8 (50%) (density d) for groups 2 and 3, respectively. Detection rates differed significantly for masses in heterogeneously dense and extremely dense tissue (overall or lesion’s background) versus all other densities (Fisher’s t-test: p < 0.05). A significantly lowered FP rate for masses was found on mammograms of entirely fatty tissue. Conclusion: Overall breast density and density at a lesion’s background do not appear to have a significant effect on CAD sensitivity or specificity for MC. CAD sensitivity for MA may be lowered in cases with heterogeneously and extremely dense breasts, and CAD specificity for MA is highest in cases with extremely fatty breasts. The effects of overall breast density and density of a lesion’s background appear to be similar.     

A Heuristic Approach to Automated Nipple Detection in Digital Mammograms

In this paper, a heuristic approach to automated nipple detection in digital mammograms is presented. A multithresholding algorithm is first applied to segment the mammogram and separate the breast region from the background region. Next, the problem is considered separately for craniocaudal (CC) and mediolateral-oblique (MLO) views. In the simplified algorithm, a search is performed on the segmented image along a band around the centroid and in a direction perpendicular to the pectoral muscle edge in the MLO view image. The direction defaults to the horizontal (perpendicular to the thoracic wall) in case of CC view images. The farthest pixel from the base found in this direction can be approximated as the nipple point. Further, an improved version of the simplified algorithm is proposed which can be considered as a subclass of the Branch and Bound algorithms. The mean Euclidean distance between the ground truth and calculated nipple position for 500 mammograms from the Digital Database for Screening Mammography (DDSM) database was found to be 11.03 mm and the average total time taken by the algorithm was 0.79 s. Results of the proposed algorithm demonstrate that even simple heuristics can achieve the desired result in nipple detection thus reducing the time and computational complexity.     

Applicability of ACR breast dosimetry methodology to a digital mammography system

Determination of mean glandular dose (MGD) to breast tissue is an essential aspect of mammography equipment evaluations and exposure controls. The American College of Radiology (ACR) Quality Control Manual outlines the procedure for MGD determination in screen-film mammography based upon conversions of entrance skin exposures (ESEs) measured with an ionization chamber (IC). The development of digital mammography has increased with the demand for improved object resolution and tissue contrast. This change in image receptor from screen-film to a solid-state detector has led to questions about the applicability of the ACR MGD methodology to digital mammography. This research has validated the applicability of the ACR MGD methodology to digital mammography in the GE digital mammography system Senographe 2000D. MGD was determined using light output measurements from thermoluminescent dosimeters (MGDTL), exposure measurements from an IC (MGD(IC)) and conversion factors from the ACR Mammography Quality Control Manual. MGD(TL) and MGD(IC) data indicate that there is a statistically significant difference between the two measurements with the Senographe 2000D. However, the applicability of the ACR's methodology was validated by calculating MGD at various depths in a 50/50 breast phantom. Additionally, the results of backscatter measurements from the image receptors of both mammography modalities indicate there is a difference (all P values < 0.001) in the radiation backscattered from each image receptor.     

Robust Automatic Pectoral Muscle Segmentation from Mammograms Using Texture Gradient and Euclidean Distance Regression

In computer-aided diagnosis (CAD) of mediolateral oblique (MLO) view of mammogram, the accuracy of tissue segmentation highly depends on the exclusion of pectoral muscle. Robust methods for such exclusions are essential as the normal presence of pectoral muscle can bias the decision of CAD. In this paper, a novel texture gradient-based approach for automatic segmentation of pectoral muscle is proposed. The pectoral edge is initially approximated to a straight line by applying Hough transform on Probable Texture Gradient (PTG) map of the mammogram followed by block averaging with the aid of approximated line. Furthermore, a smooth pectoral muscle curve is achieved with proposed Euclidean Distance Regression (EDR) technique and polynomial modeling. The algorithm is robust to texture and overlapping fibro glandular tissues. The method is validated with 340 MLO views from three databases—including 200 randomly selected scanned film images from miniMIAS, 100 computed radiography images and 40 full-field digital mammogram images. Qualitatively, 96.75 % of the pectoral muscles are segmented with an acceptable pectoral score index. The proposed method not only outperforms state-of-the-art approaches but also accurately quantifies the pectoral edge. Thus, its high accuracy and relatively quick processing time clearly justify its suitability for CAD.     

An observer study comparing spot imaging regions selected by radiologists and a computer for an automated stereo spot mammography technique

We are developing an automated stereo spot mammography technique for improved imaging of suspicious dense regions within digital mammograms. The technique entails the acquisition of a full-field digital mammogram, automated detection of a suspicious dense region within that mammogram by a computer aided detection (CAD) program, and acquisition of a stereo pair of images with automated collimation to the suspicious region. The latter stereo spot image is obtained within seconds of the original full-field mammogram, without releasing the compression paddle. The spot image is viewed on a stereo video display. A critical element of this technique is the automated detection of suspicious regions for spot imaging. We performed an observer study to compare the suspicious regions selected by radiologists with those selected by a CAD program developed at the University of Michigan. True regions of interest (TROIs) were separately determined by one of the radiologists who reviewed the original mammograms, biopsy images, and histology results. We compared the radiologist and computer-selected regions of interest (ROIs) to the TROIs. Both the radiologists and the computer were allowed to select up to 3 regions in each of 200 images (mixture of 100 CC and 100 MLO views). We computed overlap indices (the overlap index is defined as the ratio of the area of intersection to the area of interest) to quantify the agreement between the selected regions in each image. The averages of the largest overlap indices per image for the 5 radiologist-to-computer comparisons were directly related to the average number of regions per image traced by the radiologists (about 50% for 1 region/image, 84% for 2 regions/image and 96% for 3 regions/image). The average of the overlap indices with all of the TROIs was 73% for CAD and 76.8% +/- 10.0% for the radiologists. This study indicates that the CAD determined ROIs could potentially be useful for a screening technique that includes stereo spot mammography imaging.     

Patient dose in digital mammography

In the present investigation, we analyze the dose of 5034 patients (20,137 images) who underwent mammographic examinations with a full-field digital mammography system. Also, we evaluate the system calibration by analyzing the exposure factors as a function of breast thickness. The information relevant to this study has been extracted from the image DICOM header and stored in a database during a 3-year period (March 2001-October 2003). Patient data included age, breast thickness, kVp, mAs, target/filter combination, and nominal dose values. Entrance surface air kerma (ESAK) without backscatter was calculated from the tube output as measured for each voltage used under clinical conditions and from the tube loading (mAs) included in the DICOM header. Mean values for the patient age and compressed breast thickness were 56 years (SD: 11) and 52 mm (SD: 13), respectively. The majority of the images was acquired using the STD (for standard) automatic mode (98%). The most frequent target/filter combination automatically selected for breast smaller than 35 mm was Mo/Mo (75%); for intermediate thicknesses between 35 and 65 mm, the combinations were Mo/Rh (54%) and Rh/Rh (38.5%); Rh/Rh was the combination selected for 91% of the cases for breasts thicker than 65 mm. A wide kVp range was observed for each target/filter combination. The most frequent values were 28 kVp for Mo/Mo, 29 kVp for Mo/Rh, and 29 and 30 kV for Rh/Rh. Exposure times ranged from 0.2 to 4.2 s with a mean value of 1.1 s. Average glandular doses (AGD) per exposure were calculated by multiplying the ESAK values by the conversion factors tabulated by Dance for women in the age groups 50 to 64 and 40 to 49. This approach is based on the dependence of breast glandularity on breast thickness and age. The total mean average glandular dose (AGD(T)) was calculated by summing the values associated with the pre-exposure and with the main exposure. Mean AGD(T) per exposure was 1.88 mGy (CI 0.01) and the mean AGD(T) per examination was 3.8 mGy, with 4 images per examination on average. The mean dose for cranio-caudal view (CC) images was 1.8 mGy, which is lower than that for medio-lateral oblique (MLO) view because the thickness for CC images was on average 10% lower than that for MLO images. Mean AGD(T) for the oldest group of women (1.90) was 3% higher than the AGD(T) for the younger group (1.85) due to the larger compressed breast thickness of women in the older group (10% on average). Differences between the corresponding AGD(T) values of each age group were lowest for breast thicknesses in the range 40-60 mm, being slightly higher for the women in the older group.