Significance analysis of qualitative mammographic features, using linear classifiers, neural networks and support vector machines.

Advances in modern technologies and computers have enabled digital image processing to become a vital tool in conventional clinical practice, including mammography. However, the core problem of the clinical evaluation of mammographic tumors remains a highly demanding cognitive task. In order for these automated diagnostic systems to perform in levels of sensitivity and specificity similar to that of human experts, it is essential that a robust framework on problem-specific design parameters is formulated. This study is focused on identifying a robust set of clinical features that can be used as the base for designing the input of any computer-aided diagnosis system for automatic mammographic tumor evaluation. A thorough list of clinical features was constructed and the diagnostic value of each feature was verified against current clinical practices by an expert physician. These features were directly or indirectly related to the overall morphological properties of the mammographic tumor or the texture of the fine-scale tissue structures as they appear in the digitized image, while others contained external clinical data of outmost importance, like the patient's age. The entire feature set was used as an annotation list for describing the clinical properties of mammographic tumor cases in a quantitative way, such that subsequent objective analyses were possible. For the purposes of this study, a mammographic image database was created, with complete clinical evaluation descriptions and positive histological verification for each case. All tumors contained in the database were characterized according to the identified clinical features' set and the resulting dataset was used as input for discrimination and diagnostic value analysis for each one of these features. Specifically, several standard methodologies of statistical significance analysis were employed to create feature rankings according to their discriminating power. Moreover, three different classification models, namely linear classifiers, neural networks and support vector machines, were employed to investigate the true efficiency of each one of them, as well as the overall complexity of the diagnostic task of mammographic tumor characterization. Both the statistical and the classification results have proven the explicit correlation of all the selected features with the final diagnosis, qualifying them as an adequate input base for any type of similar automated diagnosis system. The underlying complexity of the diagnostic task has justified the high value of sophisticated pattern recognition architectures.

[1]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[2]  Russell Reed,et al.  Pruning algorithms-a survey , 1993, IEEE Trans. Neural Networks.

[3]  K. J. Ray Liu,et al.  Computerized radiographic mass detection. I. Lesion site selection by morphological enhancement and contextual segmentation , 2001, IEEE Transactions on Medical Imaging.

[4]  E. Gose,et al.  Classification of benign and malignant breast tumors on the basis of 36 radiographic properties , 1973, Cancer.

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

[6]  Dustin Boswell,et al.  Introduction to Support Vector Machines , 2002 .

[7]  Jan de Leeuw,et al.  A Review of Two different Approaches for the Analysis of Growth Data Using Longitudinal Mixed Linear Models: Comparing Hierarchical Linear Regression (ML3), HLM) and Repeated Measures Designs with Structured Covariance Matrices (BMDP5V) , 1996 .

[8]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[9]  L. Bruce,et al.  Classifying mammographic mass shapes using the wavelet transform modulus-maxima method , 1999, IEEE Transactions on Medical Imaging.

[10]  Douglas E. Sanders.  Breast Imaging: Diagnosis and Morphology of Breast Diseases , 1988 .

[11]  Evangelos Dermatas,et al.  Fast detection of masses in computer-aided mammography , 2000, IEEE Signal Process. Mag..

[12]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[13]  Y. Wu,et al.  Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. , 1993, Radiology.

[14]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[15]  M.,et al.  Statistical and Structural Approaches to Texture , 2022 .

[16]  Sergios Theodoridis,et al.  Mammographic mass classification using textural features and descriptive diagnostic data , 2002, 2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628).

[17]  Mary M. Galloway,et al.  Texture analysis using gray level run lengths , 1974 .

[19]  J. Swets,et al.  Reading and decision aids for improved accuracy and standardization of mammographic diagnosis. , 1992, Radiology.

[20]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[21]  Martin D. Fox,et al.  Classifying mammographic lesions using computerized image analysis , 1993, IEEE Trans. Medical Imaging.

[22]  László Györfi,et al.  A Probabilistic Theory of Pattern Recognition , 1996, Stochastic Modelling and Applied Probability.

[23]  Peter C. Cheeseman,et al.  Bayesian Classification (AutoClass): Theory and Results , 1996, Advances in Knowledge Discovery and Data Mining.

[24]  G Coppini,et al.  Tissue characterization from X-ray images. , 1997, Medical engineering & physics.

[25]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[26]  Robert L. Egan,et al.  Breast Imaging: Diagnosis and Morphology of Breast Diseases , 1988 .