Dedicated breast CT: geometric design considerations to maximize posterior breast coverage

To retrospectively compare the sensitivity of a computer-aided detection (CAD) system for depicting breast cancer in three digital mammographic views. This study was conducted with institutional review board approval; informed consent was waived. A commercially available CAD system was applied to the craniocaudal, mediolateral oblique, and mediolateral digital mammographic views of 83 women (mean age, 48 years; range, 30-66 years) with 83 histologically proved breast cancers. Findings were 59 masses and 41 microcalcifications (17 lesions showed both findings; 42 lesions, mass only; and 24 lesions, microcalcification only). The paired t test was used to analyze sensitivity of the CAD system for the detection of cancer in these three mammographic views and in combinations of the views. The sensitivities of the CAD system were 92% (76 of 83) in the craniocaudal view, 83% (69 of 83) in the mediolateral oblique view, and 86% (71 of 83) in the mediolateral view; the differences were not significant (P = .07-.62). Sensitivity increased to 96% (80 of 83) in the craniocaudal plus mediolateral oblique views and to 99% (82 of 83) in the craniocaudal plus mediolateral oblique plus mediolateral views. For masses, the sensitivity of the CAD system was 76% (45 of 59) in the craniocaudal view and 75% (44 of 59) in the mediolateral oblique view and increased to 93% (55 of 59) when mediolateral oblique and craniocaudal views were combined (P < .001). For microcalcifications, sensitivity was 98% (40 of 41) in the craniocaudal view and 95% (39 of 41) in the mediolateral oblique view, and this increased to 100% (41 of 41) when the mediolateral oblique and craniocaudal views were combined (P = .31). The sensitivities of the CAD system were not significantly different among these three digital mammographic views. Sensitivity for depicting masses was significantly increased (P < .001) when the craniocaudal view was added to the mediolateral oblique view.

The purpose of this study was to develop a fully automated algorithm for mammographic breast density estimation using deep learning. Our algorithm used a fully convolutional network, which is a deep learning framework for image segmentation, to segment both the breast and the dense fibroglandular areas on mammographic images. Using the segmented breast and dense areas, our algorithm computed the breast percent density (PD), which is the faction of dense area in a breast. Our dataset included full-field digital screening mammograms of 604 women, which included 1208 mediolateral oblique (MLO) and 1208 craniocaudal (CC) views. We allocated 455, 58, and 91 of 604 women and their exams into training, testing, and validation datasets, respectively. We established ground truth for the breast and the dense fibroglandular areas via manual segmentation and segmentation using a simple thresholding based on BI-RADS density assessments by radiologists, respectively. Using the mammograms and ground truth, we fine-tuned a pretrained deep learning network to train the network to segment both the breast and the fibroglandular areas. Using the validation dataset, we evaluated the performance of the proposed algorithm against radiologists' BI-RADS density assessments. Specifically, we conducted a correlation analysis between a BI-RADS density assessment of a given breast and its corresponding PD estimate by the proposed algorithm. In addition, we evaluated our algorithm in terms of its ability to classify the BI-RADS density using PD estimates, and its ability to provide consistent PD estimates for the left and the right breast and the MLO and CC views of the same women. To show the effectiveness of our algorithm, we compared the performance of our algorithm against a state of the art algorithm, laboratory for individualized breast radiodensity assessment (LIBRA). The PD estimated by our algorithm correlated well with BI-RADS density ratings by radiologists. Pearson's rho values of our algorithm for CC view, MLO view, and CC-MLO-averaged were 0.81, 0.79, and 0.85, respectively, while those of LIBRA were 0.58, 0.71, and 0.69, respectively. For CC view and CC-MLO averaged cases, the difference in rho values between the proposed algorithm and LIBRA showed statistical significance (P<0.006). In addition, our algorithm provided reliable PD estimates for the left and the right breast (Pearson's ρ>0.87) and for the MLO and CC views (Pearson's ρ=0.76). However, LIBRA showed a lower Pearson's rho value (0.66) for both the left and right breasts for the CC view. In addition, our algorithm showed an excellent ability to separate each sub BI-RADS breast density class (statistically significant, p-values = 0.0001 or less); only one comparison pair, density 1 and density 2 in the CC view, was not statistically significant (P=0.54). However, LIBRA failed to separate breasts in density 1 and 2 for both the CC and MLO views (P>0.64). We have developed a new deep learning based algorithm for breast density segmentation and estimation. We showed that the proposed algorithm correlated well with BI-RADS density assessments by radiologists and outperformed an existing state of the art algorithm.

The aim of this study is to investigate any difference in the shape and location of infiltrating lobular carcinoma (ILC) with respect to the parenchymal density between the cranio-caudal (CC) and medio-lateral oblique (MLO) mammographic views. Six film-readers independently re-read 59 ILC mammograms and a matched sample of 59 infiltrating ductal carcinoma (IDC) mammograms from one 3-year screening round to quantify lesion characteristics. There is fair to moderate reader agreement for parenchymal pattern, lesion shape and location (kappa = 0.41-0.60). Both ILC (33/60, 55%) and IDC (22/65, 37%) appear as a spiculate mass more often on the CC view than on the MLO view. 41% (25/60) of the ILC spiculate masses become architectural distortions or asymmetric densities on the MLO view. No more ILC lesions (4/60, 7%) are seen in dense breasts than IDC (5/65, 8%), but ILC is mainly associated with (58/60, 97%), and rarely isolated from (2/60, 3%), the main glandular density. The appearance of ILC is significantly different between the MLO and CC views (paired Wilcoxon test: z = -17.059; significance level <or=0.0005). IDC appearance is not significantly different between these two views (z = -1.244; significance level 0.213). In conclusion, the CC view is optimum for distinctly visualizing ILC as a spiculate mass, as it appears as a more subtle distortion or asymmetry on the MLO view. ILC is not often isolated from the main glandular density and so optimizing visualization of this area of the breast is key to perception.

This study retrospectively analyzed the mean glandular dose (MGD) to 133 breasts from 132 subjects, all women, who participated in a clinical trial evaluating dedicated breast CT in a diagnostic population. The clinical trial was conducted in adherence to a protocol approved by institutional review boards and the study participants provided written informed consent. Individual estimates of MGD to each breast from dedicated breast CT was obtained by combining x-ray beam characteristics with estimates of breast dimensions and fibroglandular fraction from volumetric breast CT images, and using normalized glandular dose coefficients. For each study participant and for the breast corresponding to that imaged with breast CT, an estimate of the MGD from diagnostic mammography (including supplemental views) was obtained from the DICOM image headers for comparison. This estimate uses normalized glandular dose coefficients corresponding to a breast with 50% fibroglandular weight fraction. The median fibroglandular weight fraction for the study cohort determined from volumetric breast CT images was 15%. Hence, the MGD from diagnostic mammography was corrected to be representative of the study cohort. Individualized estimates of MGD from breast CT ranged from 5.7 to 27.8 mGy. Corresponding to the breasts imaged with breast CT, the MGD from diagnostic mammography ranged from 2.6 to 31.6 mGy. The mean (± inter-breast SD) and the median MGD (mGy) from dedicated breast CT exam were 13.9 ± 4.6 and 12.6, respectively. For the corresponding breasts, the mean (± inter-breast SD) and the median MGD (mGy) from diagnostic mammography were 12.4 ± 6.3 and 11.1, respectively. Statistical analysis indicated that at the 0.05 level, the distributions of MGD from dedicated breast CT and diagnostic mammography were significantly different (Wilcoxon signed ranks test, p = 0.007). While the interquartile range and the range (maximum–minimum) of MGD from dedicated breast CT was lower than diagnostic mammography, the median MGD from dedicated breast CT was approximately 13.5% higher than that from diagnostic mammography. The MGD for breast CT is based on a 1.45 mm skin layer and that for diagnostic mammography is based on a 4 mm skin layer; thus, favoring a lower estimate for MGD from diagnostic mammography. The median MGD from dedicated breast CT corresponds to the median MGD from four to five diagnostic mammography views. In comparison, for the same 133 breasts, the mean and the median number of views per breast during diagnostic mammography were 4.53 and 4, respectively. Paired analysis showed that there was approximately equal likelihood of receiving lower MGD from either breast CT or diagnostic mammography. Future work will investigate methods to reduce and optimize radiation dose from dedicated breast CT.

The objective of this study was to investigate the impact of decreasing breast compression during digital mammography and breast tomosynthesis (DBT) on perceived pain and image quality. In this two-part study, two groups of women with prior mammograms were recruited. In part 1, subjects were positioned for craniocaudal (CC) and mediolateral oblique (MLO) views, and four levels of compression force were applied to evaluate changes in breast thickness, perceived pain, and relative tissue coverage. No imaging was performed. In part 2, two MLO DBT images of one breast of each patient were acquired at standard and reduced compression. Blurring artifacts and tissue coverage were judged by three breast imaging radiologists, and compression force, breast thickness, relative tissue coverage, and perceived pain were recorded. Only the first reduction in force was feasible because further reduction resulted in inadequate breast immobilization. Mean force reductions of 48% and 47% for the CC and MLO views, respectively, resulted in a significantly reduced perceived pain level, whereas the thickness of the compressed breast increased by 0.02 cm (CC view) and 0.09 (MLO view, part 1 of the study) and 0.38 cm (MLO view, part 2 of the study), respectively, with no change in tissue coverage or increase in motion blurring. Mammography and DBT acquisitions may be possible using half of the compression force used currently, with a significant and substantial reduction in perceived pain with no clinically significant change in breast thickness and tissue coverage.

Evaluation of average glandular dose and investigation of the relationship with compressed breast thickness in dual energy contrast enhanced digital mammography and digital breast tomosynthesis

Toinvestigate two deep learning-based modeling schemes for predicting short-term risk of developing breast cancer using prior normal screening digital mammograms in a case-control setting. We conducted a retrospective Institutional Review Board-approved study on a case-control cohort of 226 patients (including 113 women diagnosed with breast cancer and 113 controls) who underwent general population breast cancer screening. For each patient, a prior normal (i.e., with negative or benign findings) digital mammogram examination [including mediolateral oblique (MLO) view and craniocaudal (CC) view two images] was collected. Thus, a total of 452 normal images (226 MLO view images and 226 CC view images) of this case-control cohort were analyzed to predict the outcome, i.e., developing breast cancer (cancer cases) or remaining breast cancer-free (controls) within the follow-up period. We implemented an end-to-end deep learning model and a GoogLeNet-LDA model and compared their effects in several experimental settings using two mammographic view images and inputting two different subregions of the images to the models. The proposed models were also compared to logistic regression modeling of mammographic breast density. Area under the receiver operating characteristic curve (AUC) was used as the model performance metric. The highest AUC was 0.73 [95% Confidence Interval (CI): 0.68-0.78; GoogLeNet-LDA model on CC view] when using the whole-breast and was 0.72 (95% CI: 0.67-0.76; GoogLeNet-LDA model on MLO+CC view) when using the dense tissue, respectively, as the model input. The GoogleNet-LDA model significantly (all P<0.05) outperformed the end-to-end GoogLeNet model in all experiments. CC view was consistently more predictive than MLO view in both deep learning models, regardless of the input subregions. Both models exhibited superior performance than the percent breast density (AUC=0.54; 95% CI: 0.49-0.59). The proposed deep learning modeling approach can predict short-term breast cancer risk using normal screening mammogram images. Larger studies are needed to further reveal the promise of deep learning in enhancing imaging-based breast cancer risk assessment.

Multi-view co-occurrence and dual-modality framework for breast cancer classification

To compare the estimate of normalized glandular dose in mammography and breast CT imaging obtained using the actual glandular tissue distribution in the breast to that obtained using the homogeneous tissue mixture approximation. Twenty volumetric images of patient breasts were acquired with a dedicated breast CT prototype system and the voxels in the breast CT images were automatically classified into skin, adipose, and glandular tissue. The breasts in the classified images underwent simulated mechanical compression to mimic the conditions present during mammographic acquisition. The compressed thickness for each breast was set to that achieved during each patient's last screening cranio-caudal (CC) acquisition. The volumetric glandular density of each breast was computed using both the compressed and uncompressed classified images, and additional images were created in which all voxels representing adipose and glandular tissue were replaced by a homogeneous mixture of these two tissues in a proportion corresponding to each breast's volumetric glandular density. All four breast images (compressed and uncompressed; heterogeneous and homogeneous tissue) were input into Monte Carlo simulations to estimate the normalized glandular dose during mammography (compressed breasts) and dedicated breast CT (uncompressed breasts). For the mammography simulations the x-ray spectra used was that used during each patient's last screening CC acquisition. For the breast CT simulations, two x-ray spectra were used, corresponding to the x-ray spectra with the lowest and highest energies currently being used in dedicated breast CT prototype systems under clinical investigation. The resulting normalized glandular dose for the heterogeneous and homogeneous versions of each breast for each modality was compared. For mammography, the normalized glandular dose based on the homogeneous tissue approximation was, on average, 27% higher than that estimated using the true heterogeneous glandular tissue distribution (Wilcoxon Signed Rank Test p = 0.00046). For dedicated breast CT, the overestimation of normalized glandular dose was, on average, 8% (49 kVp spectrum, p = 0.00045) and 4% (80 kVp spectrum, p = 0.000089). Only two cases in mammography and two cases in dedicated breast CT with a tube voltage of 49 kVp resulted in lower dose estimates for the homogeneous tissue approximation compared to the heterogeneous tissue distribution. The normalized glandular dose based on the homogeneous tissue mixture approximation results in a significant overestimation of dose to the imaged breast. This overestimation impacts the use of dose estimates in absolute terms, such as for risk estimates, and may impact some comparative studies, such as when modalities or techniques with different x-ray energies are used. The error introduced by the homogeneous tissue mixture approximation in higher energy x-ray modalities, such as dedicated breast CT, although statistically significant, may not be of clinical concern. Further work is required to better characterize this overestimation and potentially develop new metrics or correction factors to better estimate the true glandular dose to breasts undergoing imaging with ionizing radiation.

BackgroundTo explore the capability and clinical significance of chest thin-section computed tomography (CT) for localization of mammographically detected clustered microcalcifications.MethodsA total of 69 patients with 71 mammographically detected clustered microcalcifications received surgical biopsy under the guidance of mammography (MG), CT was used to localize calcifications combined with MG if calcifications can be seen on CT. Intraoperative mammography of the specimens were performed in all cases for identification of the resected microcalcifications. The clinical, imaging and pathological information of these patients were analyzed.ResultsA total of 42 (59.15%) cases of calcifications were localized by CT + MG, 29 (40.85%) cases were guided only by the mammography. All suspicious calcifications on the mammography were successfully removed. Pathological results showed 42 cases were cancer, 23 cases were benign, and 6 cases were atypical hyperplasia. The mean age in the CT + MG group was older than that of the MG group (54.12 vs. 49.27 years; P = 0.014). The maximum diameter of clusters of microcalcifications on mammography in the CT + MG group was larger than that of the MG group [(cranio-caudal view, 1.52 vs. 0.61 mm, P = 0.000; mediolateral oblique (MLO) view, 1.53 vs. 0.62 mm, P = 0.000)]. The gray value ratio (calcified area / paraglandular; MLO, P = 0.004) and the gray value difference (calcified area - paraglandular; MLO, P = 0.005) in the CT + MG group was higher than that of the MG group. Multivariate analysis showed that the max diameter of clusters of microcalcifications (MLO view) was a significant predictive factor of localization by CT in total patients (P = 0.001).ConclusionsAbout half of the mammographically detected clustered microcalcifications could be localized by thin-section CT. Maximum diameter of clusters of microcalcifications (MLO view) was a predictor of visibility of calcifications by CT. Chest thin-section CT may be useful for localization of calcifications in some patients, especially for calcifications that are only visible in one view on the mammography.

Purpose: To determine whether breast thickness decreases with menopause after the reduction of glandular tissue. We also wanted to know how the decrease in breast thickness affects the compression force and the average glandular dose. Methods: In this project, we collected data regarding the compression force, breast thickness and mean glandular dose of 300 patients who had mammographic imaging in two views: CC (craniocaudal) and MLO (mediolateral oblique) view. The data were divided into three age groups: 100 patients aged 50 to 55, 100 patients aged 60 to 65 and 100 patients aged 70 to 75 years. We used basic statistical tests for measurement purposes, while we used the Shapiro–Wilk test to check normality and the Kruskal–Wallis test to compare the differences. Results and discussion: We presented the results and comparisons in the tables and box plot graphs for CC and MLO views of the left and right breast for compression force, breast thickness and MGD. In the CC view of the both breasts, we found that there were statistically signifi cant differences in thickness between groups 1 and 3, and differences in MGD between groups 1 and 2, and 1 and 3. In the MLO view of both breasts we found that compression force does not increase with the age of patients, which can be attributed to the different size and density of breasts, and different compression force. Higher compression force results in lower MGD and breast thickness. Conclusion: In the CC view of left and right breast, there is no statistically signifi cant differences in compression force, but thickness and MGD changed between some groups. In the MLO view, only MGD changed. For further research, we recommend taking measurements on a larger sample, and concurrently considering and examining other factors that may affect breast thickness, compression force and MGD.

The incidence of breast issues, such as breast cancer, has been increasing in Iraq in recent years. Nonetheless, early detection and screening initiatives utilizing mammography and complementary ultrasoand have substantially lowered mortailty rates from this emerging disease. This study examines the relationship between breast density classification in the right and left breast, average glandular dose (AGD) for cranio-caudal (CC) and medio-lateral oblique (MLO) views, age, body mass index (BMI) across three groups of patients and compresses breast thickness. The study of population comprises of 100 paired MLO and CC mammography obtained on one mammography unit in Alawiya Educational hospital. Twenty one out of 100 females have a lesion (21%) of the total group and seventy nine out 100 females do not have a lesion ,representing 79% of total patients .Mean patient age was 46.8 years and mean body mass index (BMI) was 31.25 .Mean compreessed breast thickness was 50.35 mm for cc and 61.12 mm for MLO. Univariate analysis displayed no association between AGD in CC and MLO views with lesion in breast and BMI of patient ,negative association with age(P&lt;0.05) ,BMI(P=0.694 for CC ,P=0.510 for MLO),lesion (P=0.209 for CC ,P=0.571 for MLO) and the relationships between average glandular dose (of both CC and MLO) and compression breast thickness (of MLO and CC) are not statistically significant (r=0.001, p= 0.996for cc and r=0.079, P=0.267 for MLO).However, there is a statisitically significant moderate positive relationship between the compression breast thickness of MLO and CC (r=-0.001, P=0.985 for cc and r=0.253** ,P=0.0001 for MLO).The AGD and dose in our routine mammography, the equivalent is within recommended limits, and the amount of radiation absorbed by glandular tissue is manageable.of breast. The study suggests a potential trend between both the average glandular dose during mammography, the breast lesions, age of patient ,compressed breast thickness and BMI, there were statistically significant between AGD , compressed breast thickness (CBT) and age . While, there were no significant differences between AGD , BMI of body patient and lesion of breast.

Purpose:Utilization of contrast enhancement in dedicated breast CT (bCT) has been reported to be a reliable metric in determining the conspicuity of malignant breast lesions. In this study, we have designed and developed a framework of image segmentation and registration to align the structure of pre‐ and post‐contrast breast CT image.Methods:An iterative two‐means clustering method was used in image segmentation. The image segmentation algorithm results in segmenting the breast CT image to skin, adipose, fibroglandular and contrast‐enhanced lesions. These results are used in image registration method. A deformable image registration method code‐named Intensity Difference Adaptive Demons (IDAD) was developed based on the Demons image registration. Within the developed framework, the deformation field forces are calculated considering the contrast enhancement levels in the bCT image voxels. The performance of the developed framework was evaluated using mathematical simulations and patient breast CT images.Results:The proposed method outperformed conventional affine and other Demons variations for serial pre‐contrast and post‐contrast breast CT image alignment. In simulation studies, IDAD exhibited 1–11% improvement in Normalized Cross Correlation (NCC) compared to the conventional Demons approach with the improvement increasing with lesion size and contrast enhancement levels. Registration error measured by Target Registration Error (TRE) shows only submillimeter mismatches between the concordant anatomical target points in all patient studies. The implementation of the presented hybridized framework was implemented based on a parallel processing architecture, resulting in rapid execution time for the iterative segmentation and intensity‐adaptive registration techniques.Conclusion:Characterization of contrast‐enhanced lesions is improved using IDAD. Spatial subtraction of the aligned images yields useful diagnostic information with respect to lesion morphology.

AIMS AND OBJECTIVESBreast positioning is the key factor affecting a mammogram. If care is taken during positioning, it maximizes the amount of breast tissue being imaged, eliminates most of the artifacts, and increases sensitivity of the mammogram. This retrospective study was carried out in our department to assess correctness, and also the incorrectness of breast positioning, which need to be avoided to obtain an ideal mammogram.MATERIAL AND METHODSA total of 1369 female patients were included in this study. Mammography was performed on full field detector digital mammography equipment. Craniocaudal (CC) view and mediolateral oblique (MLO) view were carried out for each breast. Four views were done for 1322 patients. The remaining 47 patients had undergone a mastectomy and underwent two views for the other breast. Mistakes in improperly positioned mammogram were assessed with respect to proper visualization of nipple, position of pectoralis major, pectoral–nipple distance (PND), inframammary fold, and adequate coverage of all breast quadrants.RESULTSAs per prescribed guidelines, mistakes in positioning were recognized in 2.879% of total mammograms. Improper positioning of the nipple was the commonest problem, seen in 3.827% of mammograms, CC view. On MLO view, bilaterally, pectoralis shadow was not seen in 0.520% mammograms, its margin was not straight/convex in 0.706%, lower edge of pectoralis was above pectoralis–nipple line in 2.081%, and inframammary fold was not seen in 1.189%. There was inadequate coverage of lower quadrants in 2.787%, and mismatch in PND was seen in 3.864%. In few of the patients, the shortcomings as a result of improper positioning were noted on one view, the rest being normal.CONCLUSIONPositioning is the most important factor affecting the resultant mammography image. During mammography, many cases are improperly positioned and as a result the examination is inconclusive, which reduces the sensitivity of mammography.

To determine the mean and range of volumetric glandular fraction (VGF) of the breast in a diagnostic population using a high-resolution flat-panel cone-beam dedicated breast CT system. This information is important for Monte Carlo-based estimation of normalized glandular dose coefficients and for investigating the dependence of VGF on breast dimensions, race, and pathology. Image data from a clinical trial investigating the role of dedicated breast CT that enrolled 150 women were retrospectively analyzed to determine the VGF. The study was conducted in adherence to a protocol approved by the institutional human subjects review boards and written informed consent was obtained from all study participants. All participants in the study were assigned BI-RADS(®) 4 or 5 as per the American College of Radiology assessment categories after standard diagnostic work-up and underwent dedicated breast CT exam prior to biopsy. A Gaussian-kernel based fuzzy c-means algorithm was used to partition the breast CT images into adipose and fibroglandular tissue after segmenting the skin. Upon determination of the accuracy of the algorithm with a phantom, it was applied to 137 breast CT volumes from 136 women. VGF was determined for each breast and the mean and range were determined. Pathology results with classification as benign, malignant, and hyperplasia were available for 132 women, and were used to investigate if the distributions of VGF varied with pathology. The algorithm was accurate to within ±1.9% in determining the volume of an irregular shaped phantom. The study mean (± inter-breast SD) for the VGF was 0.172 ± 0.142 (range: 0.012-0.719). VGF was found to be negatively correlated with age, breast dimensions (chest-wall to nipple length, pectoralis to nipple length, and effective diameter at chest-wall), and total breast volume, and positively correlated with fibroglandular volume. Based on pathology, pairwise statistical analysis (Mann-Whitney test) indicated that at the 0.05 significance level, there was no significant difference in distributions of VGF without adjustment for age between malignant and nonmalignant breasts (p = 0.41). Pairwise comparisons of the distributions of VGF in increasing order of mammographic breast density indicated all comparisons were statistically significant (p < 0.002). This study used a different clinical prototype breast CT system than that in previous studies to image subjects from a different geographical region, and used a different algorithm for analysis of image data. The mean VGF estimated from this study is within the range reported in previous studies, indicating that the choice of 50% glandular weight fraction to represent an average breast for Monte Carlo-based estimation of normalized glandular dose coefficients in mammography needs revising. In the study, the distributions of VGF did not differ significantly with pathology.