Application of support vector machines and neural networks in digital mammography: A comparative study

Microcalcification (MC) detection is an important component of breast cancer diagnosis. However, visual analysis of mammograms is a difficult task for radiologists. Computer Aided Diagnosis (CAD) technology helps in identifying lesions and assists the radiologist make his final decision. This work is a part of a CAD project carried out at the Imaging Science Research Division (ISRD), Digital Medical Imaging Program, Moffitt Cancer Research Center, Tampa, FL. A CAD system had been previously developed to perform the following tasks: (a) pre-processing, (b) segmentation and (c) feature extraction of mammogram images. Ten features covering spatial, and morphological domains were extracted from the mammograms and the samples were classified as Microcalcification (MC) or False alarm (False Positive microcalcification/ FP) based on a binary truth file obtained from a radiologist’s initial investigation. The main focus of this work was two-fold: (a) to analyze these features, select the most significant features among them and study their impact on classification accuracy and (b) to implement and compare two machine-learning algorithms, Neural Networks (NNs) and Support Vector Machines (SVMs) and evaluate their performances with these features.

[1]  L. Tabár,et al.  Potential contribution of computer-aided detection to the sensitivity of screening mammography. , 2000, Radiology.

[2]  Raúl Rojas,et al.  The Backpropagation Algorithm , 1996 .

[3]  C J Vyborny,et al.  Can computers help radiologists read mammograms? , 1994, Radiology.

[4]  D R Dance,et al.  The automatic computer detection of subtle calcifications in radiographically dense breasts. , 1992, Physics in medicine and biology.

[5]  Mark J. T. Smith,et al.  A filter bank for the directional decomposition of images: theory and design , 1992, IEEE Trans. Signal Process..

[6]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[7]  G. Moore.  [Breast cancer diagnosis]. , 1988, Ugeskrift for laeger.

[8]  Sung-Jea Ko,et al.  Center weighted median filters and their applications to image enhancement , 1991 .

[9]  Nico Karssemeijer,et al.  A Stochastic Model for Automated Detction of Calculations in Digital Mammograms , 1991, IPMI.

[10]  Ron Kohavi,et al.  Irrelevant Features and the Subset Selection Problem , 1994, ICML.

[11]  Chun-Nan Hsu,et al.  The ANNIGMA-wrapper approach to fast feature selection for neural nets , 2002, IEEE Trans. Syst. Man Cybern. Part B.

[12]  M L Giger,et al.  Computerized detection of clustered microcalcifications: evaluation of performance on mammograms from multiple centers. , 1995, Radiographics : a review publication of the Radiological Society of North America, Inc.

[13]  J. Franklin,et al.  The elements of statistical learning: data mining, inference and prediction , 2005 .

[14]  M. Pamilo,et al.  Double reading of mammography screening films--one radiologist or two? , 1993, Clinical radiology.

[15]  Huan Liu,et al.  Feature Selection for Classification , 1997, Intell. Data Anal..

[16]  Rangaraj M. Rangayyan,et al.  Region-based contrast enhancement of mammograms , 1992, IEEE Trans. Medical Imaging.

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

[18]  Massimiliano Pontil,et al.  Support Vector Machines for 3D Object Recognition , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Chris H. Q. Ding,et al.  Multi-class protein fold recognition using support vector machines and neural networks , 2001, Bioinform..

[20]  Gonzalo R. Arce,et al.  Detail-preserving ranked-order based filters for image processing , 1989, IEEE Trans. Acoust. Speech Signal Process..

[21]  Rajkumar Sv,et al.  Screening mammography in women aged 40-49 years. , 1999 .

[22]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[23]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[24]  Ling Guan,et al.  A CAD System for the Automatic Detection of Clustered Microcalcification in Digitized Mammogram Films , 2000, IEEE Trans. Medical Imaging.

[25]  John C. Platt,et al.  Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[26]  J. M. Pruneda,et al.  Computer-aided mammographic screening for spiculated lesions. , 1994, Radiology.

[27]  Federico Girosi,et al.  Training support vector machines: an application to face detection , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[28]  S. Lai,et al.  On techniques for detecting circumscribed masses in mammograms. , 1989, IEEE transactions on medical imaging.

[29]  Ron Kohavi,et al.  Feature Subset Selection Using the Wrapper Method: Overfitting and Dynamic Search Space Topology , 1995, KDD.

[30]  Mb Popli.  Pictorial essay : Mammographic features of breast cancer , 2001 .

[31]  David R. Cox.  The analysis of binary data , 1970 .

[32]  C. Boggis,et al.  Double reading of mammography screening films--one radiologist or two. , 1994, Clinical radiology.

[33]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[34]  L. Bottou,et al.  COMPARISON OF LEARNING ALGORITHMS FOR , 1995 .

[35]  Harold G. Longbotham,et al.  Application of weighted-majority minimum-range filters in the detection and sizing of tumors in mammograms , 1992, Medical Imaging.

[36]  N Karssemeijer,et al.  Automated detection of breast carcinomas not detected in a screening program. , 1998, Radiology.

[37]  Amara Lynn Graps,et al.  An introduction to wavelets , 1995 .

[38]  D. Hosmer,et al.  Applied Logistic Regression , 1991 .

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

[40]  D. R. Cox,et al.  The analysis of binary data , 1971 .

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

[42]  Bernard F. Buxton,et al.  Drug Design by Machine Learning: Support Vector Machines for Pharmaceutical Data Analysis , 2001, Comput. Chem..

[43]  Wei Qian,et al.  Tree-structured nonlinear filters in digital mammography , 1994, IEEE Trans. Medical Imaging.

[44]  Carey E. Priebe,et al.  COMPARATIVE EVALUATION OF PATTERN RECOGNITION TECHNIQUES FOR DETECTION OF MICROCALCIFICATIONS IN MAMMOGRAPHY , 1993 .

[45]  Albert Macovski,et al.  Lesion contrast enhancement in medical ultrasound imaging , 1997, IEEE Transactions on Medical Imaging.

[46]  R J McKenna,et al.  The abnormal mammogram radiographic findings, diagnostic options, pathology, and stage of cancer diagnosis , 1994, Cancer.

[47]  S. Sathiya Keerthi,et al.  Improvements to Platt's SMO Algorithm for SVM Classifier Design , 2001, Neural Computation.

[48]  Nico Karssemeijer,et al.  Stochastic model for automated detection of calcifications in digital mammograms , 1992, Image Vis. Comput..

[49]  Claudia Wild.  Computer-aided detection (CAD) in mammography. , 2002, TEC bulletin.

[51]  S. Rubin,et al.  Efficacy of screening mammography. A meta-analysis. , 1995, JAMA.

[52]  Stan Matwin,et al.  Machine Learning for the Detection of Oil Spills in Satellite Radar Images , 1998, Machine Learning.

[53]  F. Greene,et al.  Breast cancer statistics: use and misuse. , 1986, International surgery.

[54]  Lucila Ohno-Machado,et al.  Logistic regression and artificial neural network classification models: a methodology review , 2002, J. Biomed. Informatics.

[55]  E. Thurfjell,et al.  Benefit of independent double reading in a population-based mammography screening program. , 1994, Radiology.

[56]  Daphne Koller,et al.  Toward Optimal Feature Selection , 1996, ICML.

[57]  R E Hendrick,et al.  Proposition: All mammograms should be double-read. , 1999, Medical physics.

[58]  Nicolaos B. Karayiannis,et al.  Detection of microcalcifications in digital mammograms using wavelets , 1998, IEEE Transactions on Medical Imaging.

[59]  Recognition of clustered microcalcifications using a random field model , 1993, Electronic Imaging.

[60]  R M Nishikawa,et al.  Image feature analysis and computer-aided diagnosis in mammography: reduction of false-positive clustered microcalcifications using local edge-gradient analysis. , 1995, Medical physics.

[61]  K Doi,et al.  An improved shift-invariant artificial neural network for computerized detection of clustered microcalcifications in digital mammograms. , 1996, Medical physics.

[62]  Hualou Liang,et al.  Detection of delayed gastric emptying from electrogastrograms with support vector machine , 2001, IEEE Transactions on Biomedical Engineering.

[63]  K Doi,et al.  Image feature analysis and computer-aided diagnosis in digital radiography. I. Automated detection of microcalcifications in mammography. , 1987, Medical physics.

[64]  Ron Kohavi,et al.  Wrappers for feature selection , 1997 .

[65]  K Doi,et al.  Analysis of methods for reducing false positives in the automated detection of clustered microcalcifications in mammograms. , 1998, Medical physics.

[66]  Jung-Hsien Chiang,et al.  Neural and Fuzzy Methods in Handwriting Recognition , 1997, Computer.

[67]  Huan Liu,et al.  Feature Selection for High-Dimensional Data: A Fast Correlation-Based Filter Solution , 2003, ICML.

[68]  K. J. Ray Liu,et al.  Fractal modeling and segmentation for the enhancement of microcalcifications in digital mammograms , 1997, IEEE Transactions on Medical Imaging.

[69]  Dong-Chul Park,et al.  Centroid neural network for unsupervised competitive learning , 2000, IEEE Trans. Neural Networks Learn. Syst..

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

[71]  K Doi,et al.  Improvement in radiologists' detection of clustered microcalcifications on mammograms. The potential of computer-aided diagnosis. , 1990, Investigative radiology.

[72]  Nello Cristianini,et al.  An introduction to Support Vector Machines , 2000 .

[73]  Patrick Haffner,et al.  Support vector machines for histogram-based image classification , 1999, IEEE Trans. Neural Networks.

[74]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[75]  N Karssemeijer,et al.  Automated classification of clustered microcalcifications into malignant and benign types. , 2000, Medical physics.

[76]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[77]  Martin T. Hagan,et al.  Neural network design , 1995 .

[78]  Rangaraj M. Rangayyan,et al.  Application of shape analysis to mammographic calcifications , 1994, IEEE Trans. Medical Imaging.