Mammographic image analysis

Staying abreast of imaging - Current status of breast cancer detection in high density breast

OBJECTIVES

The aim of this paper is to illustrate the current status of imaging in high breast density as we enter a new decade of advancing medicine and technology to diagnose breast lesions.

KEY FINDINGS

Early detection of breast cancer has become the chief focus of research from governments to individuals. However, with varying breast densities across the globe, the explosion of breast density information related to imaging, phenotypes, diet, computer aided diagnosis and artificial intelligence has witnessed a dramatic shift in new screening recommendations in mammography, physical examination, screening younger women and women with comorbid conditions, screening women at high risk, and new screening technologies. Breast density is well known to be a risk factor in patients with suspected/known breast neoplasia. Extensive research in the field of qualitative and quantitative analysis on different tissue characteristics of the breast has rapidly become the chief focus of breast imaging. A summary of the available guidelines and modalities of breast imaging, as well as new emerging techniques under study that can potentially provide an augmentation or even a replacement of those currently available.

CONCLUSION

Despite all the advances in technology and all the research directed towards breast cancer, detection of breast cancer in dense breasts remains a dilemma.

IMPLICATIONS FOR PRACTICE

It is of utmost importance to develop highly sensitive screening modalities for early detection of breast cancer.

Breast Density Estimation with Fully Automated Volumetric Method: Comparison to Radiologists' Assessment by BI-RADS Categories

RATIONALE AND OBJECTIVES

The objective of our study was to calculate mammographic breast density with a fully automated volumetric breast density measurement method and to compare it to breast imaging reporting and data system (BI-RADS) breast density categories assigned by two radiologists.

MATERIALS AND METHODS

A total of 476 full-field digital mammography examinations with standard mediolateral oblique and craniocaudal views were evaluated by two blinded radiologists and BI-RADS density categories were assigned. Using a fully automated software, mean fibroglandular tissue volume, mean breast volume, and mean volumetric breast density were calculated. Based on percentage volumetric breast density, a volumetric density grade was assigned from 1 to 4.

RESULTS

The weighted overall kappa was 0.895 (almost perfect agreement) for the two radiologists' BI-RADS density estimates. A statistically significant difference was seen in mean volumetric breast density among the BI-RADS density categories. With increased BI-RADS density category, increase in mean volumetric breast density was also seen (P < 0.001). A significant positive correlation was found between BI-RADS categories and volumetric density grading by fully automated software (ρ = 0.728, P < 0.001 for first radiologist and ρ = 0.725, P < 0.001 for second radiologist). Pairwise estimates of the weighted kappa between Volpara density grade and BI-RADS density category by two observers showed fair agreement (κ = 0.398 and 0.388, respectively).

CONCLUSIONS

In our study, a good correlation was seen between density grading using fully automated volumetric method and density grading using BI-RADS density categories assigned by the two radiologists. Thus, the fully automated volumetric method may be used to quantify breast density on routine mammography.

Radiologist assessment of breast density by BI-RADS categories versus fully automated volumetric assessment

OBJECTIVE

The objective of our study was to estimate mammographic breast density using a fully automated volumetric breast density measurement method in comparison with BI-RADS breast density categories determined by radiologists.

MATERIALS AND METHODS

A total of 791 full-field digital mammography examinations with standard views were evaluated by three blinded radiologists as BI-RADS density categories 1-4. For fully automated volumetric analysis, volumetric breast density was calculated with fully automated software. The volume of fibroglandular tissue, the volume of the breast, and the volumetric percentage density were provided.

RESULTS

The weighted overall kappa was 0.48 (moderate agreement) for the three radiologists' estimates of BI-RADS density. Pairwise comparisons of the radiologists' measurements of BI-RADS density revealed moderate to substantial agreement, with kappa values ranging from 0.51 to 0.64. There was a significant difference in mean volumetric breast density among the BI-RADS density categories, and the mean volumetric breast density increased as the BI-RADS density category increased (p<0.001). A significant positive correlation was found between BI-RADS categories and fully automated volumetric breast density (ρ=0.765, p<0.001).

CONCLUSION

Our study showed good correlation of the fully automated volumetric method with radiologist-assigned BI-RADS density categories. Mammographic density assessment with the fully automated volumetric method may be used to assign BI-RADS density categories.

[Computerized estimation of a percent glandular tissue composition in computed radiography mammography]

Measurement of a percent glandular tissue composition (%GTC) is important in terms of the estimation of individual patient exposure dose and the prediction of malignancy, and thus a number of reports for estimating %GTC by use of a mammogram have been published. In this study, we propose a method for estimating individual %GTC by use of computed radiography (CR) mammograms. By employing breast-equivalent phantoms that are able to create breast phantom images with various combinations of fat and glandular tissue, as well as the thickness of whole breast, we determined a reference table for converting an each pixel value on CR mammography to the glandular tissue ratio. Therefore, the %GTC for individual breast was estimated by averaging glandular tissue ratio for a whole region. The clinical image data set that consisted of 49 CR mammograms were used for estimating %GTC. A paired comparison method for determining subjective ranking of the degree of breast density was employed in order to demonstrate the validity of our method. The results indicate that the average estimated %GTC was 35.0% (ranged from 12.0% to 67.0%) and they had a increased correlation with the ranking of those obtained by observer test. Therefore, it was suggested that our proposed method would be utilized for estimating the %GTC in objective manner.

Computerized Evaluation of Mammographic Lesions:What Diagnostic Role Does the Shape of the Individual Microcalcifications Play Compared with the Geometry of the Cluster?

OBJECTIVE

The objective of this study was to compare the diagnostic role of features reflecting the geometry of clusters with features reflecting the shape of the individual microcalcification in a mammographic computer-aided diagnosis system.

MATERIALS AND METHODS

Three hundred twenty-four cases of clustered microcalcifications with biopsy-proven results were digitized at 42-microm resolution and analyzed on a computerized system. The shape factor and number of neighbors were computed for each microcalcification, and the eccentricity of the cluster was computed as well. The shape factor is related to the individual microcalcification; the average number of neighbors and the cluster eccentricity reflect the cluster geometry. Stepwise discriminant analysis was used to evaluate the contribution of the extracted features in predicting malignancy. The performance of a classifier based on the features selected by stepwise discriminant analysis was evaluated by receiver operating characteristic (ROC) analysis.

RESULTS

To obtain the best discrimination model, we used stepwise discriminant analysis to select the average number of neighbors and the shape of the individual microcalcification, but excluded cluster eccentricity. A classification scheme assigned the average number of neighbors a weighting factor, which was 1.49 times greater than that assigned to the shape factor of the individual microcalcification. A scheme based only on these two features yielded an ROC curve with an area under the curve (A(z)) of 0.87, indicating a positive predictive value of 61% for 98% sensitivity.

CONCLUSION

Computerized analysis permitted calculations reflecting the shape of individual microcalcification and the geometry of clusters of microcalcifications. For the computerized classification scheme studied, the cluster geometry was more effective in differentiating benign from malignant clusters than was the shape of individual microcalcification.

A digital equalisation technique improving visualisation of dense mammary gland and breast periphery in mammography

INTRODUCTION

In mammographic imaging, use of high contrast screen-film combinations results in under-exposed and over-exposed film areas corresponding to dense mammary gland and breast periphery (BP), respectively, characterised by degraded image contrast. A digital equalisation technique was designed and developed in order to deal with the problem of poor visualisation of these regions.

METHODS AND MATERIAL

The technique is based on the film-digitiser characteristic curve and a layer model of the breast region, as depicted on a mammogram. It remaps each layer grey level (GL) values by a correction factor that accounts for thickness variation in BP and the presence of dense fibroglandular tissues at the mammary gland. The major steps of the technique are segmentation, to isolate the breast region from mammogram background, and adaptive layer GL remapping.

RESULTS

The performance of the technique was initially evaluated on a sample of 60 mammograms. Comparative evaluation between the initial and processed images was performed on the basis of nine anatomical features situated at dense mammary gland and BP. The mammographic images resulting from application of the proposed technique are GL equalised and the visualisation improvement of all anatomical features was found to be statistically significant (P<0.05) or highly significant (P<0.0001). The proposed technique was also compared with contrast-limited adaptive histogram equalisation (CLAHE) and found to be more effective in the visualisation of all anatomical features examined, for both dense breast (DB) and BP.

DISCUSSION AND CONCLUSION

Application of the proposed technique results in improved visualisation of both dense mammary gland and BP regions. The proposed technique is independent of breast size, breast symmetry and mammographic view. The technique contributes to breast dose minimisation by eliminating the need for a second acquisition.

Model-based technique for the measurement of skin thickness in mammography

A model-based method is proposed for the measurement of breast skin thickness from digitised mammograms that takes into account both the geometric and radiographic properties of the skin region. The method initially identifies a salient feature that discriminates the skin from the other anatomical structures of the breast. Its identification is based on a multi-scale grey-level gradient estimation, using a wavelet decomposition of the image. The spatial distribution of this feature is organised as a graph, with each of its nodes associated with a binary set of interpretation labels. A Markov random field is defined on the set of labels, and the best graph labelling is finally determined with a maximum a posteriori (MAP) probability criterion. The method was applied on 11 mammograms with improved contrast characteristics at the breast periphery, obtained by an exposure equalisation technique during image acquisition. The validation of the approach was performed by calculating the root mean square (RMS) error between the detected skin thickness and manual measurements performed on each of the films. The resulting error values ranged from 0.1 mm to 0.2 mm for normal cases and reached a maximum of 0.5mm in pathological cases with advanced skin thickening.

A digital density equalization technique to improve visualization of breast periphery in mammography

In mammographic imaging, the film area corresponding to the breast periphery is overexposed, resulting in high optical density and degraded contrast in this region. A digital, model-driven density equalization technique was designed and developed to overcome this overexposure problem, taking into account the non-linear characteristic curve of the film-digitizer system. The method is based on several image processing and analysis techniques, such as thresholding, which is used to segment the pixels of the mammogram belonging to the breast region from the background, and wavelet-based fusion, which is used to equalize the pixels of breast periphery selectively while leaving the remaining breast region unaffected. Initial application of the method resulted in density-equalized mammographic images, characterized by improved contrast at the breast periphery.

Detecting film-screen artifacts in mammography using a model-based approach

Microcalcifications can be one of the earliest signs of breast cancer. Unfortunately, their appearance in mammograms can be mimicked by dust and dirt entering the imaging process and this has been shown previously to lead to false positives. We use a model of the imaging process and, in particular, the blurring functions inherent within it to detect the film-screen artifacts caused by dust and dirt and, thus, reduce false-positives. A crucial facet of the work is the choice of the correct image representation upon which to perform the image processing. After extensive testing, our algorithm has identified no microcalcifications as being artifacts and has an artifact detection rate of approaching 96%.