Improving the Automated Detection of Calcifications Using Adaptive Variance Stabilization

In this paper, we analyze how stabilizing the variance of intensity-dependent quantum noise in digital mammograms can significantly improve the computerized detection of microcalcifications (MCs). These lesions appear on mammograms as tiny deposits of calcium smaller than 20 pixels in diameter. At this scale, high frequency image noise is dominated by quantum noise, which in raw mammograms can be described with a square-root noise model. Under this assumption, we derive an adaptive variance stabilizing transform (VST) that stabilizes the noise to unitary standard deviation in all the images. This is achieved by estimating the noise characteristics from the image at hand. We tested the adaptive VST as a preprocessing stage for four existing computerized MC detection methods on three data sets acquired with mammographic units from different manufacturers. In all the test cases considered, MC detection performance on transformed mammograms was statistically significantly higher than on unprocessed mammograms. Results were also superior in comparison with a “fixed” (nonparametric) VST previously proposed for digital mammograms.

[1]  Nico Karssemeijer,et al.  Automatic Microcalcification Detection in Multi-vendor Mammography Using Convolutional Neural Networks , 2016, Digital Mammography / IWDM.

[2]  Nico Karssemeijer,et al.  Breast cancer screening results 5 years after introduction of digital mammography in a population-based screening program. , 2009, Radiology.

[3]  Arthur Burgess.  On the noise variance of a digital mammography system. , 2004, Medical physics.

[4]  Xinming Liu,et al.  Effects of exposure equalization on image signal-to-noise ratios in digital mammography: a simulation study with an anthropomorphic breast phantom. , 2011, Medical physics.

[5]  Robert M. Nishikawa,et al.  Quantitative study of image features of clustered microcalcifications in for-presentation mammograms , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[6]  Nico Karssemeijer,et al.  Normalization of local contrast in mammograms , 2000, IEEE Transactions on Medical Imaging.

[7]  Alessandro Bria,et al.  An effective learning strategy for cascaded object detection , 2016, Inf. Sci..

[8]  Thierry Blu,et al.  Fast Haar-wavelet denoising of multidimensional fluorescence microscopy data , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[9]  Alessandro Foi,et al.  Optimal Inversion of the Anscombe Transformation in Low-Count Poisson Image Denoising , 2011, IEEE Transactions on Image Processing.

[10]  Nico Karssemeijer,et al.  Deep Cascade Classifiers to Detect Clusters of Microcalcifications , 2016, Digital Mammography / IWDM.

[11]  Thomas W. Parks,et al.  Image denoising using total least squares , 2006, IEEE Transactions on Image Processing.

[12]  Andrew D. A. Maidment,et al.  Digital Mammography , 2019, Advances in Clinical Radiology.

[13]  O. J. Dunn.  Multiple Comparisons among Means , 1961 .

[14]  Nelson D. A. Mascarenhas,et al.  Filtering of Poisson Noise in Digital Mammography Using Local Statistics and Adaptive Wiener Filter , 2012, Digital Mammography / IWDM.

[15]  P. Taylor,et al.  A systematic review of computer-assisted diagnosis in diagnostic cancer imaging. , 2012, European journal of radiology.

[16]  Nico Karssemeijer,et al.  Noise equalization for detection of microcalcification clusters in direct digital mammogram images , 2004, IEEE Transactions on Medical Imaging.

[17]  Heng-Da Cheng,et al.  Computer-aided detection and classification of microcalcifications in mammograms: a survey , 2003, Pattern Recognit..

[18]  Tae-Sun Choi,et al.  Quantum and impulse noise filtering from breast mammogram images , 2012, Comput. Methods Programs Biomed..

[19]  Barbara L. Smith,et al.  A failure analysis of invasive breast cancer: Most deaths from disease occur in women not regularly screened , 2014, Cancer.

[20]  Yumin Liu,et al.  A Shearlet-based algorithm for quantum noise removal in low-dose CT images , 2016, SPIE Medical Imaging.

[21]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[22]  Alessandro Foi,et al.  Optimization of variance-stabilizing transformations , 2010 .

[23]  Joachim Dengler,et al.  Segmentation of Microcalcifications in Mammograms , 1991, DAGM-Symposium.

[24]  Alessandro Foi,et al.  Variance stabilization in Poisson image deblurring , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[25]  Ghazali Bin Sulong,et al.  MRT letter: Quantum noise removal and classification of breast mammogram images , 2012, Microscopy research and technique.

[26]  Ahmet Sertbas,et al.  A Wavelet-Based Mammographic Image Denoising and Enhancement with Homomorphic Filtering , 2009, Journal of Medical Systems.

[27]  D. Kopans,et al.  Reply to A failure analysis of invasive breast cancer: Most deaths from disease occur in women not regularly screened , 2014, Cancer.

[28]  Andrew D. A. Maidment,et al.  Method for Simulating Dose Reduction in Digital Breast Tomosynthesis , 2017, IEEE Transactions on Medical Imaging.

[29]  Nico Karssemeijer,et al.  Learning from unbalanced data: A cascade-based approach for detecting clustered microcalcifications , 2014, Medical Image Anal..

[30]  B. Stewart,et al.  World Cancer Report , 2003 .

[31]  Noriyuki Takahashi,et al.  A Modified Undecimated Discrete Wavelet Transform Based Approach to Mammographic Image Denoising , 2013, Journal of Digital Imaging.

[32]  J. Curtiss.  On Transformations Used in the Analysis of Variance , 1943 .

[33]  Joseph Geradts,et al.  Mammographic predictors of the presence and size of invasive carcinomas associated with malignant microcalcification lesions without a mass. , 2003, AJR. American journal of roentgenology.

[34]  Ulas Bagci,et al.  Denoising PET Images Using Singular Value Thresholding and Stein's Unbiased Risk Estimate , 2013, MICCAI.

[35]  Nico Karssemeijer,et al.  ADAPTIVE NOISE EQUALIZATION AND RECOGNITION OF MICROCALCIFICATION CLUSTERS IN MAMMOGRAMS , 1993 .

[36]  Mohamed-Jalal Fadili,et al.  Wavelets, Ridgelets, and Curvelets for Poisson Noise Removal , 2008, IEEE Transactions on Image Processing.

[37]  Yongyi Yang,et al.  Computer-Aided Detection and Diagnosis of Breast Cancer With Mammography: Recent Advances , 2009, IEEE Transactions on Information Technology in Biomedicine.

[38]  Nico Karssemeijer,et al.  LUT-QNE: Look-Up-Table Quantum Noise Equalization in Digital Mammograms , 2016, Digital Mammography / IWDM.

[39]  Sir Michael Brady,et al.  Quantification and normalization of x-ray mammograms , 2012, Physics in medicine and biology.

[40]  Nelson D. A. Mascarenhas,et al.  Mammographic Image Denoising and Enhancement Using the Anscombe Transformation, Adaptive Wiener Filtering, and the Modulation Transfer Function , 2013, Journal of Digital Imaging.

[41]  F. J. Anscombe,et al.  THE TRANSFORMATION OF POISSON, BINOMIAL AND NEGATIVE-BINOMIAL DATA , 1948 .

[42]  Nikolas P. Galatsanos,et al.  A support vector machine approach for detection of microcalcifications , 2002, IEEE Transactions on Medical Imaging.

[43]  Frank W. Samuelson,et al.  Comparing image detection algorithms using resampling , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

[44]  Alessandro Foi,et al.  Clipped noisy images: Heteroskedastic modeling and practical denoising , 2009, Signal Process..

[45]  J. Tukey,et al.  Transformations Related to the Angular and the Square Root , 1950 .

[46]  M. Bartlett.  The Square Root Transformation in Analysis of Variance , 1936 .

[47]  Mrinal Kanti Naskar,et al.  Poisson Noise Removal from Mammogram Using Poisson Unbiased Risk Estimation Technique , 2015 .

[48]  Mrinal Kanti Naskar,et al.  Mammogram denoising by curvelet transform based on the information of neighbouring coefficients , 2015, Proceedings of the 2015 Third International Conference on Computer, Communication, Control and Information Technology (C3IT).

[49]  Nico Karssemeijer,et al.  Detection of Microcalcifications Using a Nonuniform Noise Model , 2008, Digital Mammography / IWDM.

[50]  Andrew D. A. Maidment,et al.  Pipeline for effective denoising of digital mammography and digital breast tomosynthesis , 2017, Medical Imaging.

[51]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.