07-05-2011, 02:39 PM
[attachment=13426]
ABSTRACT:
In this paper expert system is designed using rule-based reasoning to evaluate the probability of cancer .This is developed for mammographic findings to provide support for the clinical decision to perform biopsy of the breast. The system was evaluated using a WBCD dataset and performed with an area under the receiver operating characteristic curve of 0.83, comparable with the performance of a neural network model. If only the cases returning a malignancy fraction of greater than a threshold of 0.10 are sent to biopsy, no malignancies would be missed, and the number of benign biopsies would be decreased by 25%. At a threshold of 0.21, 98%, of the malignancies would be biopsied, and the number of benign biopsies would be decreased by 41%.
1.INTRODUCTION
The most appropriate treatment of breast cancer patients depends crucially on an accurate and detailed prognosis. Prognostic factors. such as estrogen and rogesterone visualized in biopsy slides, are an important part of the prognostic process,Therefore, standardized and comparable assessment schemes for medical experts and computer aided-systems are desirable. Interobserver and intraobserver variation errors limit the accuracy of manual biopsy Manual assessment schemes are commonly based on counting and classification of individual nuclei according to intensity of stain. The number of scales used for classifying individual nuclei and the computation of the final diagnostic index (H-Score) for the biopsies can vary from three to six depending on the scheme used.
Computer-aided systems may introduce variation errors due to their sensitivity to the manual choice of hardware and software parameters.Commercial computer-aided systems, measure nuclear area in a biopsy and the corresponding intensity of stain. Nuclear area is obtained by a global thresholding algorithm.
ARCHITECTURES DESIGNED
Arch 1esign architecture
Arch 2 : functional view of Arch 1
2.SUBJECTS AND METHODS.
The rule-based reasoning system is designed to support the decision to perform biopsy in those patients who have suspicious findings on diagnostic mammography. Currently, between 66% and 90% of biopsies are performed on benign lesions. Current Algorithm is designed to help decrease the number of benign biopsies without missing malignancies. Clinicians interpret the mammograms using a standard reporting lexicon. The rule-based reasoning system compares these findings with a database of cases with known outcomes (from biopsy) and returns the fraction of similar cases that were malignant. This malignancy fraction is an intuitive response that the clinician can then consider when making the decision regarding biopsy.
BELLOW ARE THE FEATURES EVALUATED USING EXPERT SYSTEM
The Quest For Information Gathering Of Facts Figures And Building The Decision Table: Facts and information had to be gathered in order to facilitate enough knowledge to be incorporated in the expert system. Based upon the various premises listed previously, work then began in developing the framework of the expert system