Segmentation of Breast Microcalcifications: A Multi-Scale Approach

Accurate characterization of microcalcifications (MCs) in 2D full-field digital screening mammography is a necessary step towards reducing diagnostic uncertainty associated with the callback of women with suspicious MCs. Quantitative analysis of MCs has the potential to better identify MCs that have a higher likelihood of corresponding to invasive cancer. However, automated identification and segmentation of MCs remains a challenging task with high false positive rates. We present Hessian Difference of Gaussians Regression (HDoGReg), a two stage multi-scale approach to MC segmentation. Candidate high optical density objects are first delineated using blob detection and Hessian analysis. A regression convolutional network, trained to output a function with higher response near MCs, chooses the objects which constitute actual MCs. The method is trained and validated on 435 mammograms from two separate datasets. HDoGReg achieved a mean intersection over the union of 0.670±0.121 per image, intersection over the union per MC object of 0.607±0.250 and true positive rate of 0.744 at 0.4 false positive detections per cm. The results of HDoGReg perform better when compared to state-of-the-art MC segmentation and detection methods.

[1]  A. Jemal,et al.  Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries , 2018, CA: a cancer journal for clinicians.

[2]  Hans-Peter Kriegel,et al.  OPTICS: ordering points to identify the clustering structure , 1999, SIGMOD '99.

[3]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[4]  Yan Song,et al.  Breast Microcalcification Diagnosis Using Deep Convolutional Neural Network from Digital Mammograms , 2019, Comput. Math. Methods Medicine.

[5]  Ana Maria Mendonça,et al.  A Pixel-Wise Distance Regression Approach for Joint Retinal Optical Disc and Fovea Detection , 2018, MICCAI.

[6]  Reyer Zwiggelaar,et al.  Classification of Microcalcification Clusters in Digital Mammograms Using a Stack Generalization Based Classifier , 2019, J. Imaging.

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

[8]  Yongyi Yang,et al.  A context-sensitive deep learning approach for microcalcification detection in mammograms , 2018, Pattern Recognit..

[9]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[10]  Karla Kerlikowske,et al.  Comparing sensitivity and specificity of screening mammography in the United States and Denmark , 2015, International journal of cancer.

[11]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[12]  Jaime S. Cardoso,et al.  INbreast: toward a full-field digital mammographic database. , 2012, Academic radiology.

[13]  Heinz-Otto Peitgen,et al.  Scale-space signatures for the detection of clustered microcalcifications in digital mammograms , 1999, IEEE Transactions on Medical Imaging.

[14]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[15]  Xavier Lladó,et al.  Automatic microcalcification and cluster detection for digital and digitised mammograms , 2012, Knowl. Based Syst..

[16]  Marcin Ciecholewski,et al.  Microcalcification Segmentation from Mammograms: A Morphological Approach , 2016, Journal of Digital Imaging.

[17]  Vincent Lepetit,et al.  You Should Use Regression to Detect Cells , 2015, MICCAI.

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

[19]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[20]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  L. Wilkinson,et al.  Microcalcification on mammography: approaches to interpretation and biopsy. , 2017, The British journal of radiology.

[22]  Reyer Zwiggelaar,et al.  Modelling mammographic microcalcification clusters using persistent mereotopology , 2014, Pattern Recognit. Lett..

[23]  G. Farshid,et al.  Independent predictors of breast malignancy in screen-detected microcalcifications: biopsy results in 2545 cases , 2011, British Journal of Cancer.

[24]  N Roberts,et al.  Segmentation and numerical analysis of microcalcifications on mammograms using mathematical morphology. , 1997, The British journal of radiology.

[25]  Solveig Hofvind,et al.  Mammographic morphology and distribution of calcifications in ductal carcinoma in situ diagnosed in organized screening , 2011, Acta radiologica.

[26]  D. Altman,et al.  The benefits and harms of breast cancer screening: an independent review , 2012, British Journal of Cancer.

[27]  Joachim Dengler,et al.  Segmentation of microcalcifications in mammograms , 1991, IEEE Trans. Medical Imaging.

[28]  Christopher Joseph Pal,et al.  The Importance of Skip Connections in Biomedical Image Segmentation , 2016, LABELS/DLMIA@MICCAI.

[29]  Ling Guan,et al.  Automatic detection of clustered microcalcifications in digital mammograms based on wavelet features and neural network classification , 1998, Medical Imaging.

[30]  Hong Liu,et al.  Marker-Controlled Watershed for Lesion Segmentation in Mammograms , 2011, Journal of Digital Imaging.

[31]  Mads Nielsen,et al.  Screening mammography: benefit of double reading by breast density , 2018, Breast cancer research and treatment.

[32]  Heng-Da Cheng,et al.  A novel approach to microcalcification detection using fuzzy logic technique , 1998, IEEE Transactions on Medical Imaging.

[33]  Hiroyuki Yoshida,et al.  Automated detection of clustered microcalcifications in digital mammograms using wavelet processing techniques , 1994, Medical Imaging.

[34]  Marleen de Bruijne,et al.  Automated Lesion Detection by Regressing Intensity-Based Distance with a Neural Network , 2019, MICCAI.

[35]  Julia Hirschberg,et al.  V-Measure: A Conditional Entropy-Based External Cluster Evaluation Measure , 2007, EMNLP.

[36]  Tony Lindeberg,et al.  Feature Detection with Automatic Scale Selection , 1998, International Journal of Computer Vision.

[37]  Hai Su,et al.  Efficient and robust cell detection: A structured regression approach , 2018, Medical Image Anal..

[38]  Robin N. Strickland,et al.  Wavelet transforms for detecting microcalcifications in mammograms , 1996, IEEE Trans. Medical Imaging.

[39]  M. Morgan,et al.  Microcalcifications in breast cancer: novel insights into the molecular mechanism and functional consequence of mammary mineralisation , 2012, British Journal of Cancer.

[40]  Lei Zhang,et al.  Microcalcification detection based on wavelet domain hidden markov tree model: study for inclusion to computer aided diagnostic prompting system. , 2007, Medical physics.

[41]  Samuel J. Magny,et al.  Breast Imaging Reporting and Data System , 2020, Definitions.

[42]  Arnau Oliver,et al.  Topological Modeling and Classification of Mammographic Microcalcification Clusters , 2015, IEEE Transactions on Biomedical Engineering.

[43]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.