Multiattribute Decision-Making: Use of Three Scoring Methods to Compare the Performance of Imaging Techniques for Breast Cancer Detection

Multiple Attribute Decision Making (MADM) involves "making preference decisions (such as evaluation, prioritization, selection) over the available alternatives that are characterized by multiple, usually conflicting, attributes". The problems of MADM are diverse, and can be found in virtually any topic. In this paper, we use three different scoring methods for evaluating the performance of different imaging techniques used to detect cancers in the female breast. The need for such a decision support system arises from the fact that each of the several techniques which helps diagnose breast cancer today, has its own specific characteristics, advantages and drawbacks. These characteristics or attributes are generally conflicting. The goal is to detect as many malignant lesions in the breast as is possible, while identifying the maximum number of benign lesions. The four imaging techniques that are compared here are Magnetic Resonance Imaging (MRI), Mammography, Ultrasonography, and Nuclear Medicine. The three different multiattribute scoring methods are the Simple Additive Weighting method (SAW), the Weighted Product Method (WPM), and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). The three methods are described in detail, and then used to rank the four imaging techniques. The results are analyzed and the validity and robustness of the methods are tested using post-evaluation analysis. Disciplines Oncology Comments University of Pennsylvania Department of Computer and Information Science Technical Report No. MSCIS-00-10. This technical report is available at ScholarlyCommons: http://repository.upenn.edu/cis_reports/119

[1]  S. Heywang,et al.  MR imaging of the breast with Gd-DTPA: use and limitations. , 1989, Radiology.

[2]  D. Kopans The positive predictive value of mammography. , 1992, AJR. American journal of roentgenology.

[3]  Paul E. Spector Summated rating scale construction , 1991 .

[4]  G De Vincentis,et al.  A three center study on the diagnostic accuracy of 99mTc-MIBI scintimammography. , 1997, Anticancer research.

[5]  M D Schnall,et al.  Future directions in imaging of breast diseases. , 1998, Radiology.

[6]  J A Swets,et al.  Enhancing and Evaluating Diagnostic Accuracy , 1991, Medical decision making : an international journal of the Society for Medical Decision Making.

[7]  A. Giuliano,et al.  The prevalence of carcinoma in palpable vs impalpable, mammographically detected lesions. , 1991, AJR. American journal of roentgenology.

[8]  Ching-Lai Hwang,et al.  Fuzzy Multiple Attribute Decision Making - Methods and Applications , 1992, Lecture Notes in Economics and Mathematical Systems.

[9]  I. Khalkhali,et al.  Radionuclide-guided stereotactic prebiopsy localization of nonpalpable breast lesions with normal mammograms. , 1997, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[10]  M D Schnall,et al.  Breast MR imaging: interpretation model. , 1997, Radiology.

[11]  S. Feig,et al.  Clinically occult breast lesions: localization and significance. , 1987, Radiology.

[12]  A. Stavros,et al.  Solid breast nodules: use of sonography to distinguish between benign and malignant lesions. , 1995, Radiology.

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

[14]  J. K. Martin,et al.  Prebiopsy localization of nonpalpable breast lesions. , 1984, AJR. American journal of roentgenology.

[15]  W. Edwards How to Use Multi-Attribute Utility Measurement for Social Decision Making , 1976 .

[16]  Ching-Lai Hwang,et al.  Multiple attribute decision making : an introduction , 1995 .