Mammogram denoising to improve the calcification detection performance of convolutional nets

Recently, Convolutional Neural Networks (CNNs) have been successfully used to detect microcalcifications in mammograms. An important step in CNN-based detection is image preprocessing that, in raw mammograms, is usually employed to equalize or remove the intensity-dependent quantum noise. In this work, we show how removing the noise can significantly improve the microcalcification detection performance of a CNN. To this end, we describe the quantum noise with a uniform square-root model. Under this assumption, the generalized Anscombe transformation is applied to the raw mammograms by estimating the noise characteristics from the image at hand. In the Anscombe domain, noise is filtered through an adaptive Wiener filter. The denoised images are recovered with an appropriate inverse transformation and are then used to train the CNN-based detector. Experiments were performed on 1,066 mammograms acquired with GE Senographe systems. MC detection performance of a CNN on noise-free mammograms was statistically significantly higher than on unprocessed mammograms. Results were also superior in comparison with a nonparametric noise-equalizing transformation previously proposed for digital mammograms.

[1]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[2]  Raimondo Schettini,et al.  Image Analysis and Processing - ICIAP 2017 , 2017, Lecture Notes in Computer Science.

[3]  Fionn Murtagh,et al.  Image Processing and Data Analysis - The Multiscale Approach , 1998 .

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

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

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

[7]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

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

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

[10]  Nico Karssemeijer,et al.  The Effect of Mammogram Preprocessing on Microcalcification Detection with Convolutional Neural Networks , 2017, 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS).

[11]  Claudio Marrocco,et al.  Detection of Clusters of Microcalcifications in Mammograms: A Multi Classifier Approach , 2008, 2008 21st IEEE International Symposium on Computer-Based Medical Systems.

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

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

[14]  Robert M. Nishikawa,et al.  Relevance vector machine for automatic detection of clustered microcalcifications , 2005, IEEE Transactions on Medical Imaging.

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

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

[17]  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.

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

[19]  Claudio Marrocco,et al.  Automatic segmentation of the pectoral muscle in mediolateral oblique mammograms , 2013, Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems.

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

[21]  Paul W. Fieguth,et al.  Adaptive Wiener filtering of noisy images and image sequences , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[22]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

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

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

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

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

[27]  Ronald M. Summers,et al.  Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique , 2016 .

[28]  J. Hornaday,et al.  Cancer Facts & Figures 2004 , 2004 .

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

[30]  R V Kaczmarek,et al.  Automated Method for Measuring Contrast-to-Noise- Ratio (CNR) and Signal-to-Noise-Ratio (SNR) on a Full Field Digital Mammography System (FFDMS) , 2003 .

[31]  Nico Karssemeijer,et al.  Spatial Enhancement by Dehazing for Detection of Microcalcifications with Convolutional Nets , 2017, ICIAP.

[32]  Majid Rabbani.  Bayesian filtering of Poisson noise using local statistics , 1988, IEEE Trans. Acoust. Speech Signal Process..

[33]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

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