Neural vs. statistical classifier in conjunction with genetic algorithm based feature selection

Zhang, Ping; Verma, Brijesh; Kumar, Kuldeep

doi:10.1016/j.patrec.2004.09.053

Cited by 93 publications

(55 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In our previous study [14,15], we also tested various classification techniques including discriminant analysis, logistic regression and neural networks, and compared the different set of features for breast cancer diagnosis in mammography. Our study showed that logistic regression performs very well for breast abnormality classification in mammography, though the theory is not complicated.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Presenting a Simplified Assistant Tool for Breast Cancer Diagnosis in Mammography to Radiologists

Zhang

Doust

Kumar

2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. This paper proposes a method to simplify a computational model from logistic regression for clinical use without computer. The model was built using human interpreted featrues including some BI-RADS standardized features for diagnosing the malignant masses. It was compared with the diagnosis using only assessment categorization from BI-RADS. The research aims at assisting radiologists to diagnose the malignancy of breast cancer in a way without using automated computer aided diagnosis system.

show abstract

Section: Methodsmentioning

confidence: 99%

“…In our previous research, we extracted 25 features including computer extracted features and human interpreted features [14,15]. The human extracted features are the features interpreted from the radiologists including the ones interpreted following the BI-RADS lexicon.…”

Section: Features For Classificationmentioning

confidence: 99%

Presenting a Simplified Assistant Tool for Breast Cancer Diagnosis in Mammography to Radiologists

Zhang

Doust

Kumar

2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…They improved the classification performance from 0.78 to 0.82 with regard to the area under the ROC curve. Jona et al [12] proposed optimization of the feature set using hybrid of Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) which called Genetical Swarm Optimization (GSO) in Digital Mammograms. Their results show that GSO convergence is better than both PSO and GA.…”

Section: Related Workmentioning

confidence: 99%

Automatic Microcalcification Detection Using Wavelet Transform

Abu-Baker¹

2014

IJCTE

View full text Add to dashboard Cite

I. INTRODUCTIONBreast cancer is the most common type of cancer among women [1]. Some important signs of breast cancer that radiologists are seeking to find are microcalcifications (MCs), masses, and structural disorders. MCs are observed in mammograms as white spots varying in size and shape. Mammography as a screening tool is one of the best proven technique for early breast cancer detection. Mammographic image analysis is a complicated and difficult task which requires opinion of highly trained radiologists. Detection of MCs, a possible symptom of breast cancer is a complex task because of the inhomogeneous background and the high noise level in the images due to emulsion artifacts. The MCs has important characteristics in their size, shape/morphology, amount, and distribution. Their sizes vary from 0.1 mm to 1 mm [2]. MC detection is very difficult in mammographies with overlapping breast tissues or high breast tissue density. Moreover, low contrast MCs can be perceived as noise while comparing them with the nonhomogeneous background. MCs are observed in mammograms individually or in clusters. Clustered MCs are more likely to be malignant. A cluster is defined as a group consisting of 3 or more MCs in a 1-cm 2 area. As proposed in this study, many computer-aided detection systems have been developed for MCs.There are problems with the subjective analysis of mammographic images by radiologist. Subjective analysis depends mainly of the experience of the human operator, but Manuscript received February 4, 2014; revised April 16, 2014. Ayman A. AbuBaker is with the Electrical and Computer Engineering Department, Applied Science University, Amman, Jordan (e-mail: a_abubaker@asu.edu.jo).it is also affected by fatigue and other human-related factors. Since, the interpretation is a repetitive task that requires lot of attention to minute details, it requires lot of staff time and effort, which results in increasing diagnosis time. On the other hand, the objective analysis of mammograms, which is carried out by automated systems, provides consistent performance but its accuracy is usually lower. Due to the sensitivity of this problem, I believe that radiologists should be involved and computers should not replace them completely. However, computer systems can help them perform better by enhancing the quality of images, highlighting the suspicious regions and providing better analysis tools.For these reasons, computer-aided diagnoses (CAD) are exciting a great deal of attention from the radiologist community [3], [4]. CAD is defined as a diagnosis made by a physician taking into account the computer output as a second opinion. The goal of applying CAD is to support radiologists' image interpretation and improve the diagnostic accuracy and consistency [4], [5].Many authors have implemented a variety of CAD algorithms to detect the MCs in the mammogram images, with a range of success. This paper presents a new algorithm that can detect the MCs in the mammogram images accurately. This algorithm uses several unique charact...

show abstract

“…30 This method is based on the selection of the individual with the smallest niche count (see definition below) between all the individuals of the tournament group in case (2) and all the nondominated individuals in case (3).…”

Section: The Npga With Random Sampling Tournament Selectionmentioning

confidence: 99%

Application of a niched Pareto genetic algorithm for selecting features for nuclear transients classification

Baraldi

Pedroni

Zio

2009

Int. J. Intell. Syst.

View full text Add to dashboard Cite

Feature selection for transient classification is the problem of choosing among several monitored parameters (i.e., the features) to be used for efficiently recognizing the developing transient patterns. It is a critical issue for the application of "on condition" diagnostic techniques in complex systems, such as the nuclear power plants, where hundreds of parameters are measured. Indeed, irrelevant and noisy features have been shown to unnecessarily increase the complexity of the classification problem and degrade the diagnostic performance. In this paper, the problem of selecting the features to be used for efficient transient classification is tackled by means of multiobjective genetic algorithms. The approach leads to the identification of a family of equivalently optimal subsets of features, in the Pareto sense. However, difficulties in the convergence of the standard Pareto-based multiobjective genetic algorithm search in large feature spaces may arise in terms of representativeness of the identified Pareto front whose elements may turn out to be unevenly distributed in the objective functions space, thus not providing a full picture of the potential Pareto-optimal solutions. To overcome this problem, a niched Pareto genetic algorithm is embraced in this work. The performance of the feature subsets examined during the search is evaluated in terms of two optimization objectives: the classification accuracy of a Fuzzy K-Nearest Neighbors classifier and the number of features in the subsets. During the genetic search, the algorithm applies a controlled "niching pressure" to spread out the population in the search space so that convergence is shared on different niches of the Pareto front, which is thus evenly covered. The method is tested on a diagnostic problem characterized by a very large number of process features available for the classification of simulated transients in the feedwater system of a boiling water reactor. The dynamics of the transient signals is captured by wavelet decomposition, which actually increases the complexity of the search for the optimal feature subsets by triplicating the number of features to be considered. C 2008 Wiley Periodicals, Inc.

show abstract

Neural vs. statistical classifier in conjunction with genetic algorithm based feature selection

Cited by 93 publications

References 10 publications

Presenting a Simplified Assistant Tool for Breast Cancer Diagnosis in Mammography to Radiologists

Presenting a Simplified Assistant Tool for Breast Cancer Diagnosis in Mammography to Radiologists

Automatic Microcalcification Detection Using Wavelet Transform

Application of a niched Pareto genetic algorithm for selecting features for nuclear transients classification

Contact Info

Product

Resources

About