Artificial Neural Networks in Mammography Interpretation and Diagnostic Decision Making

Screening mammography is the most effective means for early detection of breast cancer. Although general rules for discriminating malignant and benign lesions exist, radiologists are unable to perfectly detect and classify all lesions as malignant and benign, for many reasons which include, but are not limited to, overlap of features that distinguish malignancy, difficulty in estimating disease risk, and variability in recommended management. When predictive variables are numerous and interact, ad hoc decision making strategies based on experience and memory may lead to systematic errors and variability in practice. The integration of computer models to help radiologists increase the accuracy of mammography examinations in diagnostic decision making has gained increasing attention in the last two decades. In this study, we provide an overview of one of the most commonly used models, artificial neural networks (ANNs), in mammography interpretation and diagnostic decision making and discuss important features in mammography interpretation. We conclude by discussing several common limitations of existing research on ANN-based detection and diagnostic models and provide possible future research directions.

[1]  K L Lam,et al.  Computerized classification of malignant and benign microcalcifications on mammograms: texture analysis using an artificial neural network. , 1997, Physics in medicine and biology.

[2]  J. Baker,et al.  Breast mass lesions: computer-aided diagnosis models with mammographic and sonographic descriptors. , 2007, Radiology.

[3]  G A Diamond,et al.  What price perfection? Calibration and discrimination of clinical prediction models. , 1992, Journal of clinical epidemiology.

[4]  R. Schmidt,et al.  Comparison of independent double readings and computer-aided diagnosis (CAD) for the diagnosis of breast calcifications. , 2006, Academic radiology.

[5]  J. Shavlik,et al.  Breast cancer risk estimation with artificial neural networks revisited , 2010, Cancer.

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

[7]  C. Floyd,et al.  Effect of patient histoy data on the prediction of breast cancer from mammographic findings with artificial neural networks , 1999 .

[8]  Jacob Beutel,et al.  Application of neural networks to computer-aided pathology detection in mammography , 1993, Medical Imaging.

[9]  M. Kallergi.  Computer-aided diagnosis of mammographic microcalcification clusters. , 2004, Medical physics.

[10]  J. Dayhoff,et al.  Artificial neural networks , 2001, Cancer.

[11]  W. P. Evans,et al.  American Cancer Society Guidelines for Breast Cancer Screening: Update 2003 , 2003, CA: a cancer journal for clinicians.

[12]  N. Cook.  Use and Misuse of the Receiver Operating Characteristic Curve in Risk Prediction , 2007, Circulation.

[13]  Patrick van der Smagt,et al.  Introduction to neural networks , 1995, The Lancet.

[14]  C. Floyd,et al.  A neural network approach to breast cancer diagnosis as a constraint satisfaction problem. , 2001, Medical physics.

[15]  Oguzhan Alagoz,et al.  Informatics in radiology: comparison of logistic regression and artificial neural network models in breast cancer risk estimation. , 2010, Radiographics : a review publication of the Radiological Society of North America, Inc.

[16]  A. Tversky,et al.  Judgment under Uncertainty: Heuristics and Biases , 1974, Science.

[17]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[18]  Emily F Conant,et al.  Association of volume and volume-independent factors with accuracy in screening mammogram interpretation. , 2003, Journal of the National Cancer Institute.

[19]  L. Zhang,et al.  A new false positive reduction method for MCCs detection in digital mammography , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[20]  G. W. Eklund,et al.  Percutaneous large-core breast biopsy: a multi-institutional study. , 1994, Radiology.

[21]  J F Hinkamp.  The role of mammography in the diagnosis of breast cancer: survey in a community hospital. , 1971, American journal of obstetrics and gynecology.

[22]  Chao Qian,et al.  Population , 1940, State Rankings 2020: A Statistical View of America.

[23]  Georgia D. Tourassi,et al.  Impact of missing data in evaluating artificial neural networks trained on complete data , 2006, Comput. Biol. Medicine.

[24]  H. Sittek,et al.  Computer-aided diagnosis in mammography , 1997, Der Radiologe.

[25]  M. Giger,et al.  Breast cancer: effectiveness of computer-aided diagnosis observer study with independent database of mammograms. , 2002, Radiology.

[26]  Alan C. Bovik,et al.  Computer-Aided Detection and Diagnosis in Mammography , 2005 .

[27]  D. Wolverton,et al.  Performance parameters for screening and diagnostic mammography: specialist and general radiologists. , 2002, Radiology.

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

[29]  J. Elmore,et al.  Variability in radiologists' interpretations of mammograms. , 1994, The New England journal of medicine.

[30]  Joseph Y. Lo,et al.  Validation of a constraint satisfaction neural network for breast cancer disgnosis: new results from 1030 cases , 2003, SPIE Medical Imaging.

[31]  C. Floyd,et al.  Effect of patient history data on the prediction of breast cancer from mammographic findings with artificial neural networks. , 1999, Academic radiology.

[32]  W. Vach,et al.  On the misuses of artificial neural networks for prognostic and diagnostic classification in oncology. , 2000, Statistics in medicine.

[33]  B. J. Hillman.  Informed and shared decision making: an alternative to the debate over unproven screening tests. , 2005, Journal of the American College of Radiology : JACR.

[34]  N. Petrick,et al.  Computerized analysis of mammographic microcalcifications in morphological and texture feature spaces. , 1998, Medical physics.

[35]  E A Sickles,et al.  Screening mammography in community practice: positive predictive value of abnormal findings and yield of follow-up diagnostic procedures. , 1995, AJR. American journal of roentgenology.

[36]  M. Giger,et al.  Malignant and benign clustered microcalcifications: automated feature analysis and classification. , 1996, Radiology.

[37]  Mitchell H Gail,et al.  On criteria for evaluating models of absolute risk. , 2005, Biostatistics.

[38]  Gholamali Rezai-Rad,et al.  Detecting microcalcification clusters in digital mammograms using combination of wavelet and neural network , 2005, International Conference on Computer Graphics, Imaging and Visualization (CGIV'05).

[39]  P. Langenberg,et al.  Breast Imaging Reporting and Data System: inter- and intraobserver variability in feature analysis and final assessment. , 2000, AJR. American journal of roentgenology.

[40]  K Doi,et al.  Computerized detection of clustered microcalcifications in digital mammograms using a shift-invariant artificial neural network. , 1994, Medical physics.

[41]  Michele Nappi,et al.  Computer Aided Diagnosis in Radiology , 1995, ICSC.

[42]  M. Giger,et al.  Improving breast cancer diagnosis with computer-aided diagnosis. , 1999, Academic radiology.

[43]  D. Levy,et al.  Prediction of coronary heart disease using risk factor categories. , 1998, Circulation.

[44]  K. Doi,et al.  Potential of computer-aided diagnosis to reduce variability in radiologists' interpretations of mammograms depicting microcalcifications. , 2001, Radiology.

[45]  Jacek M. Zurada,et al.  Impact of Low Class Prevalence on the Performance Evaluation of Neural Network Based Classifiers: Experimental Study in the Context of Computer-Assisted Medical Diagnosis , 2007, 2007 International Joint Conference on Neural Networks.

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

[47]  O. Linton,et al.  American College of Radiology , 2018, Definitions.

[48]  R. Orr,et al.  Use of an artificial neural network to quantitate risk of malignancy for abnormal mammograms. , 2001, Surgery.

[49]  C. Floyd,et al.  Breast cancer: prediction with artificial neural network based on BI-RADS standardized lexicon. , 1995, Radiology.

[50]  E. Feuer,et al.  Estimating Lifetime and Age-Conditional Probabilities of Developing Cancer , 1998, Lifetime data analysis.

[51]  Jacek M. Zurada,et al.  Training neural network classifiers for medical decision making: The effects of imbalanced datasets on classification performance , 2008, Neural Networks.

[52]  N. Cook.  Statistical evaluation of prognostic versus diagnostic models: beyond the ROC curve. , 2008, Clinical chemistry.

[53]  N. Petrick,et al.  Improvement of radiologists' characterization of mammographic masses by using computer-aided diagnosis: an ROC study. , 1999, Radiology.

[54]  K. Kerlikowske,et al.  Performance of Screening Mammography among Women with and without a First-Degree Relative with Breast Cancer , 2000, Annals of Internal Medicine.

[55]  Dimitrios I. Fotiadis,et al.  An automatic microcalcification detection system based on a hybrid neural network classifier , 2002, Artif. Intell. Medicine.

[56]  Karla Kerlikowske,et al.  Comparison of screening mammography in the United States and the United kingdom. , 2003, JAMA.

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

[58]  M. Giger,et al.  Automated computerized classification of malignant and benign masses on digitized mammograms. , 1998, Academic radiology.

[59]  Eugenio Picano,et al.  Informed consent and communication of risk from radiological and nuclear medicine examinations: how to escape from a communication inferno , 2004, BMJ : British Medical Journal.

[60]  E. Chan.  Promoting an ethical approach to unproven screening imaging tests. , 2005, Journal of the American College of Radiology : JACR.

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

[62]  Berkman Sahiner,et al.  Breast masses: computer-aided diagnosis with serial mammograms. , 2006, Radiology.

[63]  Robert M. Pap,et al.  Handbook of neural computing applications , 1990 .

[64]  S. McGuire.  Shields M., Carroll M.D., Ogden C.L. adult obesity prevalence in Canada and the United States. NCHS data brief no. 56, Hyattsville, MD: National Center for Health Statistics, 2011. , 2011, Advances in nutrition.