A Fuzzy-ACO Method for Detect Breast Cancer

Artificial Intelligence in Medicine, 1999

The automatic diagnosis of breast cancer is an important, real-world medical problem. In this paper we focus on the Wisconsin breast cancer diagnosis (WBCD) problem, combining two methodologies-fuzzy systems and evolutionary algorithms -so as to automatically produce diagnostic systems. We find that our fuzzy-genetic approach produces systems exhibiting two prime characteristics: first, they attain high classification performance (the best shown to date), with the possibility of attributing a confidence measure to the output diagnosis; second, the resulting systems involve a few simple rules, and are therefore (human-) interpretable. (C.A. Peñ a-Reyes), moshe.sipper@di.epfl.ch (M. Sipper) 0933-3657/99/$ -see front matter © 1999 Elsevier Science B.V. All rights reserved. PII: S 0 9 3 3 -3 6 5 7 ( 9 9 ) 0 0 0 1 9 -6 C.A. Peña-Reyes, M. Sipper / Artificial Intelligence in Medicine 17 (1999) 131-155 132

Res. Comput. Sci., 2020

Breast cancer is a disease that affects a large part of world society. It is the most diagnosed cancer in women and its prevention although it is not impossible, it seems really difficult since its cause is unknown, so early detection is based on the patient's forecast. The most common form for detection is selfexploration, however this is only detected in more advanced stages. That is why during the article some data mining techniques are presented along with three artificial intelligence algorithms, using data obtained from the University Medical Center, Institute of Oncology, Ljubljana, Yugoslavia and using the algorithms it is possible to identify patients likely to suffer from this disease.

There are huge numbers of patient's data that exist in the databases of some laboratories all over the world today, but clinical diagnosis is still being handled by manual computation. This paper presents a system that diagnoses breast tumors and categorizes them as either cancerous or not, using a hybrid data mining algorithm proposed in the paper. The system " learns " by clustering known patient data sets to find underlying classification patterns. The data set used in this work is obtained from the University of California Irvine (UCI) repository. Our design was built using the Object Oriented Analysis and Design methodology (OOADM) and implemented with Java programming language and MySQL as the database admin back end. The results obtained show that the system could assist clinicians diagnose easily by identifying tumors that are cancerous or non-cancerous, thereby suggesting early treatment for patients with breast cancer diseases.

2012

Background: Breast cancer is one of the most prevalent cancers among women today. The importance of breast cancer screening, its role in the timely identification of patients, and the reduction in treatment expenses are considered to be among the highest sanitary priorities of a modern country. Thermal imaging clearly possesses a special role in this stage due to rapid diagnosis and use of harmless rays.

Breast cancer is one of the major causes of death in women when compared to all other cancers. This cancer has become the most hazardous types of cancer among women in the world. Early detection of breast cancer is essential in reducing life losses. In this paper some metaheuristic optimization algorithms was used to find the parameters of the Fuzzy-ART. Fuzzy-ART is not so strong to deal with above data. However, its performance is significantly improved by using evolutionary optimization methods. These hybrid classification techniques were tested on a training data set provided by the Wisconsin dataset for breast cancer. Results showed that the proposed harmony search (HS) algorithm provides better result with less time and less number of steps than genetic algorithm (GA) and particle swarm optimization (PSO) in the same conditions. As seen in this research, evolutionary HS algorithm had a higher convergence ability to obtain optimal solution too. The best performance obtained from this algorithm is 97.80% for accuracy and 98.92% for specificity.

The breast tumor is the primary driver of female casualty everywhere throughout the world and the real area of study from a long time but with slighter development than anticipated. Numerous establishments and associations are working in this field to prompt to a conceivable arrangement of the issue or to prompt to additionally comprehension of the issue. Numerous past inquiries about the said were contemplated for improved comprehension of the issue and the research performed previously was to reduce dimensionality and to contribute to the betterment in the field of cancer, Wisconsin-Madison Diagnostic Breast cancer (WDBC) dataset was taken from learning repository of UCI database with 569 distinct instances for training by choosing finest features out of 32 different attributes. Different feature selection algorithms were used with data mining algorithms for better classification. Numerous enhancements in classification accuracy of WDBC were discovered by utilizing distinctive methodologies than the prior reviews directed in a similar field. The Logistic Regression, Linear Regression, and SVM algorithms showed better classification accuracy i.e. 98.24 %, 98.24 % and 98.07 % than the previous outcome results known for the said classification algorithms. The results were generated using 10 fold cross validation, by using different classification algorithms with feature selection and generation algorithms.

Filomat, 2016

Breast Cancer (BC) is considered as the most implacable malignancy and the leading cause of mortality among women in general and in Saudi Arabia specially. Most of the previous work in Saudi Arabia on this subject was on epidemiology, knowledge of (BC) and practice of breast self-examination (BSE), etiological factors, metastases and rate of survival. Early detection and diagnosis of Breast Cancer (BC) is an important, real-world medical problem. In this paper, we propose a soft computing methodology to build a Breast Cancer (BC) diagnosis system with high capabilities as described by Andres et al. [4] but on the Saudi Arabian breast cancer dataset and using a simplified fitness function. We focus on combining fuzzy concepts and genetic algorithms so as to automatically produce diagnostic systems to support and assist the expert to understand and evaluate its results with high classification performance.

Classification systems have been widely utilized in medical domain to explore patient's data and extract a predictive model. This model helps physicians to improve the irprognos is diagnosis or treatment planning procedures. Data mining can be done by using different functionalities. Classification is one of them. Classification is a data mining technique that assigns objects to a predefined classes or labels. The aim of classification is to classify the objects into target class. On the other hand biology inspired algorithms such as Genetic Algorithms (GA) and Swarm based approaches like Particle Swarm Optimization (PSO) and Ant Colonies Optimization (ACO) were used in solving many data mining problems. In this project, binary classification is considered as an area of problem. The main aim of this project is to discover the classification rule on biological dataset using ant miner by calculating accuracy function depends upon pheromone update levels. Ant miner uses rule induction algorithm that occupies collective intelligence to construct classification rules.

Expert Systems with Applications, 2011

Recent advances in the field of artificial intelligence have led to the emergence of expert systems for medical applications. Moreover, in the last few decades computational tools have been designed to improve the experiences and abilities of physicians for making decisions about their patients. Breast cancer is the commonest cancer in women and is the second leading cause of cancer death . Although it is curable when detected early, about one third of women with breast cancer die of the disease . In this study, we have developed an expert system that we called as an Ex-DBC (Expert system for Diagnosis of Breast Cancer), because differentiating between benign and malignant mammographic findings, however, is quite difficult. Only 15-30% of biopsies performed on nonpalpable but mammographically suspicious lesions prove malignant . The golden standard for diagnosis of breast cancer is biopsy. But, biopsy can be a source of patient discomfort, bleeding and infection, and can burden the health care system with extra costs. Thus, to reduce unnecessary biopsy rate have acquired big importance. The fuzzy rules which will be use in inference engine of Ex-DBC system were found by using neurofuzzy method. Ex-DBC can be used as a strong diagnostic tool with 97% specificity, 76% sensitivity, 96% positive and 81% negative predictive values for diagnosing of breast cancer. That the developed system's positive predictive is high is very important. By means of this system can be prevented unnecessary biopsy. Beside it can be benefited from this system for training of students in medicine.

1999

The automatic diagnosis of breast cancer is an important, real-world medical problem. In the paper we focus on the Wisconsin breast cancer diagnosis (WBCD) problem, combining two methodologies-fuzzy systems and evolutionary algorithms-so as to automatically produce diagnostic systems. We find that our fuzzy-genetic approach produces systems exhibiting the highest classification performance shown to date, and which are also (human-)interpretable.