Spatial Enhancement by Dehazing for Detection of Microcalcifications with Convolutional Nets

Microcalcifications are early indicators of breast cancer that appear on mammograms as small bright regions within the breast tissue. To assist screening radiologists in reading mammograms, supervised learning techniques have been found successful to detect microcalcifications automatically. Among them, Convolutional Neural Networks (CNNs) can automatically learn and extract low-level features that capture contrast and spatial information, and use these features to build robust classifiers. Therefore, spatial enhancement that enhances local contrast based on spatial context is expected to positively influence the learning task of the CNN and, as a result, its classification performance. In this work, we propose a novel spatial enhancement technique for microcalcifications based on the removal of haze, an apparently unrelated phenomenon that causes image degradation due to atmospheric absorption and scattering. We tested the influence of dehazing of digital mammograms on the microcalcification detection performance of two CNNs inspired by the popular AlexNet and VGGnet. Experiments were performed on 1, 066 mammograms acquired with GE Senographe systems. Statistically significantly better microcalcification detection performance was obtained when dehazing was used as preprocessing. Results of dehazing were superior also to those obtained with Contrast Limited Adaptive Histogram Equalization (CLAHE).

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

[2]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[3]  Jean-Philippe Tarel,et al.  Fast visibility restoration from a single color or gray level image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[4]  John D. Austin,et al.  Adaptive histogram equalization and its variations , 1987 .

[5]  Jian Sun,et al.  Single image haze removal using dark channel prior , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  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.

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

[8]  Karel J. Zuiderveld,et al.  Contrast Limited Adaptive Histogram Equalization , 1994, Graphics Gems.

[9]  Nima Tajbakhsh,et al.  Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? , 2016, IEEE Transactions on Medical Imaging.

[10]  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.

[11]  Yongyi Yang,et al.  Detection of clustered microcalcifications using spatial point process modeling , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[12]  Matthew B. Blaschko,et al.  Convolutional neural network transfer for automated glaucoma identification , 2017, Symposium on Medical Information Processing and Analysis.

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

[14]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

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

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

[17]  Jian Sun,et al.  Guided Image Filtering , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Alessandro Bria,et al.  A ranking-based cascade approach for unbalanced data , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

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

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

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

[22]  Hongmin Cai,et al.  Discrimination of Breast Cancer with Microcalcifications on Mammography by Deep Learning , 2016, Scientific Reports.

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

[24]  Rob Fergus,et al.  Stochastic Pooling for Regularization of Deep Convolutional Neural Networks , 2013, ICLR.

[25]  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).

[26]  Krzysztof Krawiec,et al.  Segmenting Retinal Blood Vessels With Deep Neural Networks , 2016, IEEE Transactions on Medical Imaging.

[27]  Yann LeCun,et al.  What is the best multi-stage architecture for object recognition? , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[28]  Luca Maria Gambardella,et al.  Flexible, High Performance Convolutional Neural Networks for Image Classification , 2011, IJCAI.

[29]  Claudio Marrocco,et al.  Detection of cluster of microcalcifications based on watershed segmentation algorithm , 2012, 2012 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS).

[30]  Samir Kumar Bandyopadhyay,et al.  Technique for preprocessing of digital mammogram , 2012, Comput. Methods Programs Biomed..