Search

This study investigates the equivalence or compatibility between U-Net and visual segmentations of fibroglandular tissue regions by mammography experts for calculating the breast density and mean glandular dose (MGD). A total of 703 mediolateral oblique-view mammograms were used for segmentation. Two region types were set as the ground truth (determined visually): (1) one type included only the region where fibroglandular tissue was identifiable (called the ‘dense region’); (2) the other type included the region where the fibroglandular tissue may have existed in the past, provided that apparent adipose-only parts, such as the retromammary space, are excluded (the ‘diffuse region’). U-Net was trained to segment the fibroglandular tissue region with an adaptive moment estimation optimiser, five-fold cross-validated with 400 training and 100 validation mammograms, and tested with 203 mammograms. The breast density and MGD were calculated using the van Engeland and Dance formulas, respectively, and compared between U-Net and the ground truth with the Dice similarity coefficient and Bland–Altman analysis. Dice similarity coefficients between U-Net and the ground truth were 0.895 and 0.939 for the dense and diffuse regions, respectively. In the Bland–Altman analysis, no proportional or fixed errors were discovered in either the dense or diffuse region for breast density, whereas a slight proportional error was discovered in both regions for the MGD (the slopes of the regression lines were −0.0299 and −0.0443 for the dense and diffuse regions, respectively). Consequently, the U-Net and ground truth were deemed equivalent (interchangeable) for breast density and compatible (interchangeable following four simple arithmetic operations) for MGD. U-Net-based segmentation of the fibroglandular tissue region was satisfactory for both regions, providing reliable segmentation for breast density and MGD calculations. U-Net will be useful in developing a reliable individualised screening-mammography programme, instead of relying on the visual judgement of mammography experts.

In individualized screening mammography, a breast density is important to predict potential risks of breast cancer incidence and missing lesions in mammographic diagnosis. Segmentation of the mammary gland region is required when focusing on missing lesions. A deep-learning method was recently developed to segment the mammary gland region. A large amount of ground truth (prepared by mammary experts) is required for highly accurate deep-learning practice; however, this work is time- and labor-intensive. To streamline the ground truth in deep learning, we investigated a difference in acquired mammary gland regions among multiple radiological technologists having various experience and reading levels, who shared the criteria on segmentation. If we can ignore a skill level for image reading, we can increase a number of training images. Three certified radiological technologists segmented the mammary gland region in 195 mammograms. The degree of coincidence among them was assessed with respect to seven factors which indicated the feature of segmented regions including the breast density and mean glandular dose, using Student’s t-test and Bland-Altman analysis. The assessments made by the three radiological technologists were consistent considering all factors, except the mean pixel value. Thus, we concluded that the ground truths prepared by multiple practitioners with different experiences can be accepted for the segmentation of the mammary gland region and they are applicable for training images if they stringently share the criteria on the segmentation.

ObjectiveDespite the high risk of missing lesions in mammography, the missed lesion rate is yet to be clinically established. Further, no breast phantoms with adjustable breast density currently exist. We developed a novel, adjustable-density breast phantom with a composition identical to that of actual breasts, and determined the quantitative relationship between breast density and the missed lesion rate in mammography.MethodsAn original breast phantom consisting of adipose- and fibroglandular-equivalent materials was developed, and a receiver operating characteristic (ROC) study was performed. Breast density, which is the fraction by weight of fibroglandular to total tissue, was adjusted to 25%, 50%, and 75% by arbitrarily mixing the two materials. Microcalcification, mass lesions, and spiculated lesions, each with unique characteristics, were inserted into the phantom. For the above-mentioned fibroglandular densities, 50 positive and 50 negative images for each lesion type were used as case samples for the ROC study. Five certified radiological technologists participated in lesion detection.ResultsThe mass-lesion detection rate, according to the area under the curve, decreased by 18.0% (p= 0.0001, 95% Confidence intervals [CI] = 0.1258 to 0.1822) and 37.8% (p= 0.0003, 95% CI = 0.2453 to 0.4031) for breast densities of 50% and 75%, respectively, compared to that for a 25% breast density. A similar tendency was observed with microcalcification; however, spiculated lesions did not follow this tendency.ConclusionsWe quantified the missed lesion rate in different densities of breast tissue using a novel breast phantom, which is imperative for advancing individualized screening mammography.

This study is aimed to automatically segment mammary gland region into scattered mammary glands and fatty breasts using deep learning method. Total 433 mediolateral oblique-view mammograms of Japanese women were collected and confirmed for scattered mammary glands or fatty breasts; using BI-RADS’s classification. First, manually contoured mammary gland regions were determined for all mammograms as ground truths by three certified radiological technologists. Second, the U-net model was employed to segment the mammary gland region automatically. This model is a type of convolutional neural network (CNN) mainly aimed at medical image segmentation. The segmentation accuracies were assessed based on five criteria, Dice coefficients, breast densities, mean gray values, centroids, and sizes of mammary gland region. The Dice coefficient was 0.915. The mean size of mammary gland regions obtained by the Unet was 8.7% larger than that of the ground truths. The mean centroid coordinates of mammary gland regions by the U-net were shifted 1.6 and 5.4 mm on average in mediolateral and craniocaudal directions, respectively from ground truths. The mean gray value of mammary gland regions obtained by the U-net was only 0.4% higher compared with ground truths. The resultant difference was 0.4% on average in breast densities between ground truths and the segmented mammary gland regions. We found significant similarity in the ground truths and the data generated by deep learning on all the parameters, thereby attesting the efficacy of this method for segmenting the mammary gland regions of not only the dense breasts but also the scattered mammary gland- and fatty- breasts.

Receiver operating characteristic (ROC) examination was performed to investigate the effectiveness of high-luminance monitors in digital X-ray mammography. For this purpose, an original breast phantom consisting of adipose and fibroglandular equivalent tissues with an identical X-ray absorption characteristic over the entire mammographic photon energy range was developed. Furthermore, the phantom’s fibroglandular density and distribution could be changed arbitrarily. Three types of lesions, microcalcification, mass, and spiculated, were inserted into the breast phantom, and the ROC examination was performed by five radiological technologists certified in screening mammography, to obtain the area under the curve. A liquid crystal display (LCD) monitor with 5 megapixels in a 21-inch display size calibrated to a grayscale standard display function curve was used for the observation. The monitor was set to 600, 900, and 1200 cd/m2 in maximum luminance. The experimental details were fibroglandular density of 25%, respective 50 positive and negative images, and free observation time and distance. As a result, the dependence on monitor luminance differed according to the lesion type. The detectability of microcalcification increased with the increase in the luminance of the monitor. Spiculated lesions were similar for all luminance changes. The detectability of mass lesions was significantly higher at 900 cd/m2 than at 600 cd/m2 . There was no significant difference between those at 900 cd/m2 and 1200 cd/m2 . In conclusion, the maximum luminance of the diagnostic LCD monitor for mammography should be at least 900 cd/m2 to guarantee stable detectability.

Glandularity has a marked impact on the incidence of breast cancer and the missed lesion rate of mammography. The aim of this study was to develop a novel model for predicting glandularity and patient radiation dose using physical factors that are easily determined prior to mammography. Data regarding glandularity and mean glandular dose were obtained from 331 mammograms. A stepwise multiple regression analysis model was developed to predict glandularity using age, compressed breast thickness and body mass index (BMI), while a model to predict mean glandular dose was created using quantified glandularity, age, compressed breast thickness, height and body weight. The most significant factor for predicting glandularity was age, the influence of which was 1.8 times that of BMI. The most significant factor for predicting mean glandular dose was compressed breast thickness, the influence of which was 1.4 times that of glandularity, 3.5 times that of age and 6.1 times that of height. Both models were statistically significant (both p 0.0001). Easily determined physical factors were able to explain 42.8% of the total variance in glandularity and 62.4% of the variance in mean glandular dose. Graphical abstract Validation results of the above prediction model made using physical factors in Japanese women. The plotted points of actual vs. prediction glandularity shown in a are distributed in the vicinity of the diagonal line, and the residual plot for predicted glandularity shows an almost random distribution as shown in b. These distributions indicate the appropriateness of the prediction model.

Mammography, the most effective early breast cancer detection technique, is associated with the risk of missed lesions in dense breasts, and excessive X-ray exposure. Accurate estimations of glandularity and radiation dose are important during screening. We propose a novel, inexpensive method for accurate glandularity quantification using pixel values in clinical digital mammograms and X-ray exposure spectra. Glandularities were calculated for 314 mammograms in Japanese women, and the Dance formula c-factor was applied to estimate breast doses. To investigate the relationship between breast thickness and missed lesions, images were classified into four categories based on the rate of missed lesions, and correlated with breast thickness. Glandularity decreased with increasing compressed breast thickness, indicating that commonly used breast doses assumed 50% glandularity significantly overestimate thin breasts and underestimate thick breasts. The missed lesion rate was higher for thinner compressed breast thicknesses. Accurate glandularity estimation could thus promote individualized screening mammography.

Recently, digital mammography with a photon counting silicon detector has been developed. With the aim of reducing the exposure dose, we have proposed a new mammography system that uses a cadmium telluride series photon counting detector. In addition, we also propose to use a high energy X-ray spectrum with a tungsten anode. The purpose of this study was assessed that the effectiveness of the high X-ray energy spectrum in terms of image quality using a Monte Carlo simulation. The proposed photon counting system with the high energy X-ray is compared to a conventional flat panel detector system with a Mo/Rh spectrum. The contrast-to-noise ratio (CNR) is calculated from simulation images with the use of breast phantoms. The breast model phantoms differed by glandularity and thickness, which were determined from Japanese clinical mammograms. We found that the CNR values were higher in the proposed system than in the conventional system. The number of photons incident on the detector was larger in the proposed system, so that the noise values was lower in comparison with the conventional system. Therefore, the high energy spectrum yielded the same CNR as using the conventional spectrum while allowing a considerable dose reduction to the breast.