Characterizing mammographic images by using generic texture features

Häberle, Lothar; Wagner, Florian; Fasching, Peter A.; Jud, Sebastian M.; Heusinger, Katharina; Loehberg, Christian R.; Hein, Alexander; Bayer, Christian; Hack, Carolin C.; Lux, Michael P.; Binder, Katja; Elter, Matthias; Münzenmayer, Christian; Schulz‐Wendtland, Rüdiger; Meier-Meitinger, M.; Adamietz, Boris; Uder, Michael; Beckmann, Matthias W.; Wittenberg, Thomas

doi:10.1186/bcr3163

Cited by 70 publications

(63 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) in either the retroareolar area, 25 the central breast area, 11,23 the largest rectangular box inscribed within the breast, 27 or as a single feature from the entire segmented breast. 28 However, such approaches may be limited, as they cannot fully capture the granularity and heterogeneity of the parenchymal texture. Following the original definition of image texture, [29][30][31][32] mammographic texture should be described as repeated local primitives (i.e., structure elements) estimated over the entire breast.…”

Section: Introductionmentioning

confidence: 99%

Parenchymal texture analysis in digital mammography: A fully automated pipeline for breast cancer risk assessment

et al. 2015

View full text Add to dashboard Cite

Purpose: Mammographic percent density (PD%) is known to be a strong risk factor for breast cancer. Recent studies also suggest that parenchymal texture features, which are more granular descriptors of the parenchymal pattern, can provide additional information about breast cancer risk. To date, most studies have measured mammographic texture within selected regions of interest (ROIs) in the breast, which cannot adequately capture the complexity of the parenchymal pattern throughout the whole breast. To better characterize patterns of the parenchymal tissue, the authors have developed a fully automated software pipeline based on a novel lattice-based strategy to extract a range of parenchymal texture features from the entire breast region. Methods: Digital mammograms from 106 cases with 318 age-matched controls were retrospectively analyzed. The lattice-based approach is based on a regular grid virtually overlaid on each mammographic image. Texture features are computed from the intersection (i.e., lattice) points of the grid lines within the breast, using a local window centered at each lattice point. Using this strategy, a range of statistical (gray-level histogram, co-occurrence, and run-length) and structural (edge-enhancing, local binary pattern, and fractal dimension) features are extracted. To cover the entire breast, the size of the local window for feature extraction is set equal to the lattice grid spacing and optimized experimentally by evaluating different windows sizes. The association between their lattice-based texture features and breast cancer was evaluated using logistic regression with leave-one-out cross validation and further compared to that of breast PD% and commonly used single-ROI texture features extracted from the retroareolar or the central breast region. Classification performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC). DeLong's test was used to compare the different ROCs in terms of AUC performance. Results: The average univariate performance of the lattice-based features is higher when extracted from smaller than larger window sizes. While not every individual texture feature is superior to breast PD% (AUC: 0.59, STD: 0.03), their combination in multivariate analysis has significantly better performance (AUC: 0.85, STD: 0.02, p < 0.001). The lattice-based texture features also outperform the single-ROI texture features when extracted from the retroareolar or the central breast region (AUC: 0.60-0.74, STD: 0.03). Adding breast PD% does not make a significant performance improvement to the lattice-based texture features or the single-ROI features (p > 0.05). Conclusions: The proposed lattice-based strategy for mammographic texture analysis enables to characterize the parenchymal pattern over the entire breast. As such, these features provide richer information compared to currently used descriptors and may ultimately improve breast cancer risk assessment. Larger studies are warranted to validate these findings and also compare...

show abstract

Section: Introductionmentioning

confidence: 99%

Parenchymal texture analysis in digital mammography: A fully automated pipeline for breast cancer risk assessment

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Percentage mammographic density (PD) is an established independent risk factor for breast cancer, and research has also provided evidence that mammographic image texture may contribute differently from PD to breast cancer prediction [2,3,4]. Image-based methods related to breast cancer prediction analyze mammograms of controls and cancer-cases prior to diagnosis, and attempt to predict future incidents of cancer.…”

Section: Introductionmentioning

confidence: 98%

Texture-Based Breast Cancer Prediction in Full-Field Digital Mammograms Using the Dual-Tree Complex Wavelet Transform and Random Forest Classification

et al. 2014

View full text Add to dashboard Cite

Abstract. In this paper we describe a novel methodology for texture-based breast cancer prediction in full-field digital mammograms. Our method employs the Dual-Tree Complex Wavelet Transform for texture-based image analysis and representation, and Random Forest classification for discriminative learning and breast cancer prediction. We assess the ability of our method to identify women with breast cancer using raw images, processed images and Volpara™ density maps of two case-control datasets. We also investigate whether different regions of the breast exhibit different predictive power with respect to breast cancer. The best results are obtained using the processed images of a casecontrol dataset consisting of 100 cancers and 300 controls, where we achieve an area under the ROC curve of 0.74 for a texture model based on the whole breast and an equal area under the ROC curve when the most predictive regional model is used.

show abstract

“…To overcome these limitations, recent studies have indicated texture features extracted from mammograms can help improve the prediction accuracy, even when breast density is considered. [27][28][29] Furthermore, we noticed that in most reported studies, computerized features were measured and extracted from the single region of each mammogram, usually the whole breast area, but only a few considered the internal tissue/structural information. 30 The purpose of this study is to develop a new framework for near-term breast cancer risk analysis for multiscale texture measurements on mammograms as well as more accurate and sensitive measurements of breast density.…”

Section: Introductionmentioning

confidence: 99%

Using multiscale texture and density features for near-term breast cancer risk analysis

et al. 2015

View full text Add to dashboard Cite

Purpose: To help improve efficacy of screening mammography by eventually establishing a new optimal personalized screening paradigm, the authors investigated the potential of using the quantitative multiscale texture and density feature analysis of digital mammograms to predict near-term breast cancer risk. Methods: The authors' dataset includes digital mammograms acquired from 340 women. Among them, 141 were positive and 199 were negative/benign cases. The negative digital mammograms acquired from the "prior" screening examinations were used in the study. Based on the intensity value distributions, five subregions at different scales were extracted from each mammogram. Five groups of features, including density and texture features, were developed and calculated on every one of the subregions. Sequential forward floating selection was used to search for the effective combinations. Using the selected features, a support vector machine (SVM) was optimized using a tenfold validation method to predict the risk of each woman having image-detectable cancer in the next sequential mammography screening. The area under the receiver operating characteristic curve (AUC) was used as the performance assessment index. Results: From a total number of 765 features computed from multiscale subregions, an optimal feature set of 12 features was selected. Applying this feature set, a SVM classifier yielded performance of AUC = 0.729 ± 0.021. The positive predictive value was 0.657 (92 of 140) and the negative predictive value was 0.755 (151 of 200). Conclusions:The study results demonstrated a moderately high positive association between risk prediction scores generated by the quantitative multiscale mammographic image feature analysis and the actual risk of a woman having an image-detectable breast cancer in the next subsequent examinations. C 2015 American Association of Physicists in Medicine. [http://dx

show abstract

Characterizing mammographic images by using generic texture features

Cited by 70 publications

References 45 publications

Parenchymal texture analysis in digital mammography: A fully automated pipeline for breast cancer risk assessment

Parenchymal texture analysis in digital mammography: A fully automated pipeline for breast cancer risk assessment

Texture-Based Breast Cancer Prediction in Full-Field Digital Mammograms Using the Dual-Tree Complex Wavelet Transform and Random Forest Classification

Using multiscale texture and density features for near-term breast cancer risk analysis

Contact Info

Product

Resources

About