Detection of masses in digital breast tomosynthesis using complementary information of simulated projection.

PURPOSE The purpose of this study is to develop a computer-aided detection system that combines the detection results in 3D digital breast tomosynthesis (DBT) volume and 2D simulated projection (synthesized image which is not provided by the vendor but generated from DBT volume in this study) to improve the accuracy of mass detection in DBT. METHODS The 3D DBT volume has a problem of blurring in the out-of-focus plane because it is reconstructed from a limited number of projection view images acquired over a limited angular range. To solve the problem, the simulated projection is generated by measuring the blurriness of voxels in the DBT volume and adopting conspicuity voxels. A contour-based detection algorithm is applied to detecting masses in the simulated projection. The DBT volume is analyzed by using an unsupervised mass detection algorithm, which results in mass candidates in the DBT volume. The mass likelihood scores estimated for mass candidates on the DBT volume and the simulated projection are merged in a probabilistic manner through a Bayesian network model to differentiate masses and false positives (FPs). Experiments were conducted on a clinical data set of 320 DBT volumes. In 90 volumes, at least one biopsy-proven malignant mass was presented. The longest diameter of masses ranged from 7.0 to 56.4 mm (mean = 25.4 mm). The sizes of masses in the data set were relatively large compared to the sizes of the masses reported in other detection studies. Three image quality measurements (overall sharpness, sharpness of mass boundary, and contrast) were used to evaluate the image quality of the simulated projection compared to the DBT central slice where the mass was most conspicuous and other projection methods (maximum intensity projection and average projection). A free-response receiver operating characteristic (FROC) analysis was adopted for evaluating the accuracy of mass detection in the DBT volume, the simulated projection, and the combined approach. A jackknife FROC analysis (JAFROC) was used to estimate the statistical significance of the difference between two FROC curves. RESULTS The overall sharpness and the sharpness of mass boundary in the simulated projection are higher than those in the DBT central slice and other projection methods. The contrast of the simulated projection is lower than the DBT central slice. The mass detection in the DBT volume achieved region-based sensitivities of 80% and 85% with 1.75 and 2.11 FPs per DBT volume. The proposed combined mass detection approach achieved same sensitivities with reduced FPs of 1.33 and 1.93 per DBT volume. The difference of the FROC curves between the combined approach and the mass detection in the DBT volume was statistically significant (p < 0.01) by JAFROC analysis. CONCLUSIONS This study indicates that the combined approach that merges the detection results in the DBT volume and the simulated projection is a promising approach to improve the accuracy of mass detection in DBT.

[1]  Nico Karssemeijer,et al.  Mass detection in reconstructed digital breast tomosynthesis volumes with a computer-aided detection system trained on 2D mammograms. , 2013, Medical physics.

[2]  Erik Fredenberg,et al.  A photon-counting detector for dual-energy breast tomosynthesis , 2009, Medical Imaging.

[3]  Andriy I Bandos,et al.  Comparison of two-dimensional synthesized mammograms versus original digital mammograms alone and in combination with tomosynthesis images. , 2014, Radiology.

[4]  David Gur,et al.  Digital breast tomosynthesis: observer performance study. , 2009, AJR. American journal of roentgenology.

[5]  Andriy I. Bandos,et al.  Comparison of digital mammography alone and digital mammography plus tomosynthesis in a population-based screening program. , 2013, Radiology.

[6]  David Gur,et al.  Fusion of digital breast tomosynthesis images via wavelet synthesis for improved lesion conspicuity , 2014, Medical Imaging.

[7]  Woo Kyung Moon,et al.  Characteristics of breast cancers detected by ultrasound screening in women with negative mammograms , 2011, Cancer science.

[8]  Nico Karssemeijer,et al.  Improved mammographic CAD performance using multi-view information: a Bayesian network framework , 2009, Physics in medicine and biology.

[9]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[10]  Andriy I Bandos,et al.  Two-view digital breast tomosynthesis screening with synthetically reconstructed projection images: comparison with digital breast tomosynthesis with full-field digital mammographic images. , 2014, Radiology.

[11]  Arun Ross,et al.  Score normalization in multimodal biometric systems , 2005, Pattern Recognit..

[12]  Erik Fredenberg,et al.  Contrast-enhanced spectral mammography with a photon-counting detector. , 2010, Medical physics.

[13]  David Gur,et al.  Digital breast tomosynthesis versus supplemental diagnostic mammographic views for evaluation of noncalcified breast lesions. , 2013, Radiology.

[14]  Rodney X. Sturdivant,et al.  Applied Logistic Regression: Hosmer/Applied Logistic Regression , 2005 .

[15]  Yong Man Ro,et al.  Generation of conspicuity-improved synthetic image from digital breast tomosynthesis , 2014, 2014 19th International Conference on Digital Signal Processing.

[16]  Tao Wu,et al.  A comparison of reconstruction algorithms for breast tomosynthesis. , 2004, Medical physics.

[17]  Rangaraj M. Rangayyan,et al.  Detection of breast masses in mammograms by density slicing and texture flow-field analysis , 2001, IEEE Transactions on Medical Imaging.

[18]  Gisella Gennaro,et al.  Digital breast tomosynthesis versus digital mammography: a clinical performance study , 2010, European Radiology.

[19]  J. Cha,et al.  Assessment of extent of breast cancer: comparison between digital breast tomosynthesis and full-field digital mammography. , 2013, Clinical radiology.

[20]  Nico Karssemeijer,et al.  Generating Synthetic Mammograms From Reconstructed Tomosynthesis Volumes , 2013, IEEE Transactions on Medical Imaging.

[21]  Unni Haakenaasen,et al.  Digital breast tomosynthesis (DBT): initial experience in a clinical setting , 2012, Acta radiologica.

[22]  Yong Man Ro,et al.  Improving positive predictive value in computer-aided diagnosis using mammographic mass and microcalcification confidence score fusion based on co-location information , 2013, Medical Imaging.

[23]  S. Rose,et al.  Implementation of breast tomosynthesis in a routine screening practice: an observational study. , 2013, AJR. American journal of roentgenology.

[24]  Mark A Helvie,et al.  Digital mammography imaging: breast tomosynthesis and advanced applications. , 2010, Radiologic clinics of North America.

[25]  Lubomir M. Hadjiiski,et al.  A comparative study of limited-angle cone-beam reconstruction methods for breast tomosynthesis. , 2006, Medical physics.

[26]  Ehsan Samei,et al.  Automated breast mass detection in 3D reconstructed tomosynthesis volumes: a featureless approach. , 2008, Medical physics.

[27]  Byung-Woo Hong,et al.  Segmentation of Regions of Interest in Mammograms in a Topographic Approach , 2010, IEEE Transactions on Information Technology in Biomedicine.

[28]  Yong Man Ro,et al.  Computer-aided detection (CAD) of breast masses in mammography: combined detection and ensemble classification , 2014, Physics in medicine and biology.

[29]  Dev P Chakraborty,et al.  Observer studies involving detection and localization: modeling, analysis, and validation. , 2004, Medical physics.

[30]  Thomas Mertelmeier,et al.  Optimizing filtered backprojection reconstruction for a breast tomosynthesis prototype device , 2006, SPIE Medical Imaging.

[31]  Berkman Sahiner,et al.  Computer-aided detection of masses in digital tomosynthesis mammography: comparison of three approaches. , 2008, Medical physics.

[32]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[33]  Alan C. Bovik,et al.  Computer-Aided Detection and Diagnosis in Mammography , 2005 .

[34]  M. Giger,et al.  Computerized mass detection for digital breast tomosynthesis directly from the projection images. , 2006, Medical physics.

[35]  J. Baker,et al.  Breast tomosynthesis: state-of-the-art and review of the literature. , 2011, Academic radiology.

[36]  Yong Man Ro,et al.  Multiresolution local binary pattern texture analysis combined with variable selection for application to false-positive reduction in computer-aided detection of breast masses on mammograms , 2012, Physics in medicine and biology.

[37]  David Gur,et al.  Time to diagnosis and performance levels during repeat interpretations of digital breast tomosynthesis: preliminary observations. , 2010, Academic radiology.

[38]  Isabelle Bloch,et al.  Detection of masses and architectural distortions in digital breast tomosynthesis images using fuzzy and a contrario approaches , 2014, Pattern Recognit..

[39]  Yong Man Ro,et al.  Mammographic enhancement with combining local statistical measures and sliding band filter for improved mass segmentation in mammograms , 2012, Medical Imaging.

[40]  Serge Muller,et al.  Thick Slices from Tomosynthesis Data Sets: Phantom Study for the Evaluation of Different Algorithms , 2009, Journal of Digital Imaging.

[41]  Berkman Sahiner,et al.  Dual system approach to computer-aided detection of breast masses on mammograms. , 2006, Medical physics.

[42]  Asoke K. Nandi,et al.  Detection of masses in mammograms via statistically based enhancement, multilevel-thresholding segmentation, and region selection , 2008, Comput. Medical Imaging Graph..

[43]  Carlos S. Pereira,et al.  Detection of Lung Nodule Candidates in Chest Radiographs , 2007, IbPRIA.

[44]  Yong Man Ro,et al.  Breast mass detection using slice conspicuity in 3D reconstructed digital breast volumes , 2014, Physics in medicine and biology.