Breast Cancer DiagnosisPresentation OutlineProblem StatementDescription of DataMethods of DiagnosisDiagnosis Through LPFuture PlansBreast Cancer DiagnosisA discussion of methodsMeena VairavanPresentation OutlineProblem StatementDescription of DataMethods of DiagnosisFuture PlansProblem StatementMy goal is to compare two computationalmethods to determine which is a moreeffective means for performing breastcancer diagnosis. The first methoduses linear programming and thesecond method uses neural networks.Both methods analyze data generated by fine needle aspiration tests.Description of DataSource of Data: Wisconsin Diagnosis Breast Cancer Database (WBCD)–Dr. William Wolberg - Department of Surgery–Professor W. Nick Street - Department of Manag. Sciences–Professor O.L. Mangasarian - CS DepartmentEach case is represented by a 30-dim. feature vector computed from a digitized fine needle aspirate of a breast mass.The features describe characteristics of the cell nuclei present in the image. –Radius, texture, smoothness, concavity, and symmetryMethods of DiagnosisMethod 1: Diagnosis through linear programming via generation of a separation plane.Method 2: Diagnosis through the use of a multi-layer perceptron model using back propagation techniques.Diagnosis Through LPA linear function was constructed to generate a separation plane to classify malignant and benign tumors.–f(x) = ’x - –f(x) > 0 for malignant cases–f(x) < 0 for benign cases–minimize misclassified points by choosing and to minimize distance from f(x)Future PlansFind the optimal MLP configuration for this diagnosis.–Plan to modify Professor Hu’s back propagation method for these purposes.Choose appropriate characteristics to compare the LP method and MLP methodProvide an analysis of my
View Full Document