Prescreening entire mammograms for masses with artificial neural networks: preliminary results.

RATIONALE AND OBJECTIVES The authors evaluated the feasibility of combining wavelet transform and artificial neural network (ANN) technologies to prescreen mammograms for masses. METHODS AND MATERIALS Fifty-five mammograms (29 with masses and 26 without) were digitized to 100-mm resolution and processed by using wavelet transformation. These wavelets were subjected to a linear output sequential recursive auto-associative memory ANN and cluster analysis with feature vector formation. These vectors were used in two separate experiments-one with 13 cases and another with seven cases held out in a test set-to train feed-forward ANNs to detect the mammograms with a mass. The experiments were repeated with rerandomization of the data, four and six times, respectively. RESULTS There was a statistically significant correlation (P < .01) between the network's prediction of a mass and the presence of a mass. With majority voting, the feed-forward ANNs detected masses with 79% sensitivity and 50% specificity. CONCLUSION Although preliminary, the combination of wavelet transform and ANN is promising and may provide a viable method to prescreen mammograms for masses with high sensitivity and reasonable specificity.

[1]  R A Gutcheck,et al.  Radiographic information theory and application to mammography. , 1982, Medical physics.

[2]  K Doi,et al.  Comparison of bilateral-subtraction and single-image processing techniques in the computerized detection of mammographic masses. , 1993, Investigative radiology.

[3]  W D Flanders,et al.  The lifetime risk of developing breast cancer. , 1993, Journal of the National Cancer Institute.

[4]  T K Lau,et al.  Automated detection of breast tumors using the asymmetry approach. , 1991, Computers and biomedical research, an international journal.

[5]  K. Doi,et al.  Computer-aided detection of microcalcifications in mammograms. Methodology and preliminary clinical study. , 1988, Investigative radiology.

[6]  Barry L. Kalman,et al.  High performance training of feedforward and simple recurrent networks , 1997, Neurocomputing.

[7]  U Raff,et al.  Lesion detection in radiologic images using an autoassociative paradigm: preliminary results. , 1990, Medical physics.

[8]  W. Reinus,et al.  Diagnosis of Focal Bone Lesions Using Neural Networks , 1994, Investigative radiology.

[9]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[10]  M. Victor Wickerhauser,et al.  Adapted wavelet analysis from theory to software , 1994 .

[11]  Ping Lu,et al.  Computer-aided detection and diagnosis of masses and clustered microcalcifications from digital mammograms , 1993, Electronic Imaging.

[12]  M. J. D. Powell,et al.  Restart procedures for the conjugate gradient method , 1977, Math. Program..

[13]  J M Boone,et al.  Neural networks in radiologic diagnosis. I. Introduction and illustration. , 1990, Investigative radiology.

[14]  Barry L. Kalman,et al.  Tail-recursive Distributed Representations and Simple Recurrent Networks , 1995 .

[15]  J M Boone,et al.  Neural networks in radiology: an introduction and evaluation in a signal detection task. , 1990, Medical physics.

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

[17]  G. Dodd,et al.  American cancer society guidelines from the past to the present , 1993, Cancer.

[18]  Robert F. Sproull,et al.  Principles in interactive computer graphics , 1973 .

[19]  L P Clarke,et al.  Digital mammography: M-channel quadrature mirror filters (QMFs) for microcalcification extraction. , 1994, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[20]  Y.-H. Yu,et al.  Extra output biased learning , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[21]  LiMin Fu,et al.  Neural networks in computer intelligence , 1994 .

[22]  Sholom M. Weiss,et al.  Computer Systems That Learn , 1990 .

[23]  K Doi,et al.  Computerized detection of clustered microcalcifications in digital mammograms: applications of artificial neural networks. , 1992, Medical physics.

[24]  Janice C. Honeyman-Buck,et al.  Hexagonal wavelet processing of digital mammography , 1993 .

[25]  Jian Fan,et al.  Mammographic feature enhancement by multiscale analysis , 1994, IEEE Trans. Medical Imaging.

[26]  K L Lam,et al.  Computer-aided detection of mammographic microcalcifications: pattern recognition with an artificial neural network. , 1995, Medical physics.

[27]  Andrew F. Laine,et al.  Multiscale wavelet representations for mammographic feature analysis , 1992, Optics & Photonics.

[28]  G. W. Gross,et al.  Neural networks in radiologic diagnosis. II. Interpretation of neonatal chest radiographs. , 1990, Investigative radiology.

[29]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[30]  M. Goldberg,et al.  Application of wavelet compression to digitized radiographs. , 1994, AJR. American journal of roentgenology.

[31]  N Volkers.  NCI replaces guidelines with statement of evidence. , 1994, Journal of the National Cancer Institute.

[32]  D R Dance,et al.  Segmentation of mammograms using multiple linked self-organizing neural networks. , 1995, Medical physics.

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

[34]  M L Giger,et al.  Computerized detection of masses in digital mammograms: analysis of bilateral subtraction images. , 1991, Medical physics.

[35]  Andrew F. Laine,et al.  Wavelet processing techniques for digital mammography , 1992, Other Conferences.

[36]  Y. Abu-Mostafa.  Machines that Learn from Hints , 1995 .

[37]  A Manduca,et al.  Improvement in specificity of ultrasonography for diagnosis of breast tumors by means of artificial intelligence. , 1992, Medical physics.

[38]  D. Levine,et al.  Parallel distributed processing and neural networks: origins, methodology and cognitive functions. , 1991, International Journal of Neuroscience.

[39]  L. Clarke,et al.  Tree structured wavelet transform segmentation of microcalcifications in digital mammography. , 1995, Medical physics.

[40]  L P Clarke,et al.  Tree-structured non-linear filter and wavelet transform for microcalcification segmentation in digital mammography. , 1994, Cancer letters.

[41]  N. Petrick,et al.  Classification of mass and normal breast tissue on digital mammograms: multiresolution texture analysis. , 1995, Medical physics.

[42]  C. Smart,et al.  Breast cancer detection guidelines for women aged 40 to 49 years: Rationale for the american cancer society reaffirmation of recommendations , 1994, CA: a cancer journal for clinicians.