A Fuzzy Expert System for Cancer Diagnosis

Abstract

In this paper, fuzzy expert systems explained that is capable of mimicking the behavior of a human expert. Fuzzy approach is useful to detect the region of various type of cancer from the original image by performing erosion operation. It is also helpful to determine need for the biopsy and it gives to user a clear idea of spread and severity level of cancer. A fuzzy expert system is design for diagnosing, analyzing and learning purpose of the cancer diseases. For this process suppose for prostate cancer it use prostate specific antigen (PSA), age and prostate volume (PV) as input parameters and prostate cancer risk (PCR) as output. This system allows determining if there is a need for the biopsy and it gives to user a range of the 1risk of the cancer diseases. An automated algorithm approach, based on quantitative measurements, is a valuable tool to a pathologist for verification of colon cancer image abnormalities for effective treatment. The system fuzzifies image feature descriptors and incorporates a clustering paradigm with neural network to classify images. The novelty of the algorithm is that it is independent of the feature extraction procedure adopted and overcomes the sharpness of class characteristics associated with other classifiers. It incorporates feature analysis and differs markedly from other approaches which either ignore them or perform them as separate tasks prior to classification.In this paper, fuzzy expert systems explained that is capable of mimicking the behavior of a human expert. Fuzzy approach is useful to detect the region of various type of cancer from the original image by performing erosion operation. It is also helpful to determine need for the biopsy and it gives to user a clear idea of spread and severity level of cancer. A fuzzy expert system is design for diagnosing, analyzing and learning purpose of the cancer diseases. For this process suppose for prostate cancer it use prostate specific antigen (PSA), age and prostate volume (PV) as input parameters and prostate cancer risk (PCR) as output. This system allows determining if there is a need for the biopsy and it gives to user a range of the 1risk of the cancer diseases. An automated algorithm approach, based on quantitative measurements, is a valuable tool to a pathologist for verification of colon cancer image abnormalities for effective treatment. The system fuzzifies image feature descriptors and incorporates a clustering paradigm with neural network to classify images. The novelty of the algorithm is that it is independent of the feature extraction procedure adopted and overcomes the sharpness of class characteristics associated with other classifiers. It incorporates feature analysis and differs markedly from other approaches which either ignore them or perform them as separate tasks prior to classification.