Competitive/collaborative neural computing system for medical diagnosis in pancreatic cancer detection

Gorunescu, Florin; Gorunescu, Marina; Săftoiu, Adrian; Vilmann, Peter; Belciug, Smaranda

doi:10.1111/j.1468-0394.2010.00540.x

Cited by 28 publications

(11 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this respect, from the recent literature, we mention only two references. Thus, Lisboa and Taktak (2006) offers an extended and systematic report regarding the recent use of NNs in the decision support in cancer, focused on the prostate cancer, cervical cancer, bladder cancer, leukaemia, breast cancer, pancreatic cancer Gorunescu et al (2011) etc., and using multi-layer perceptron (MLP), Kohonen self-organizing map (SOM) with MLP combined in a hybrid system, GAs, SVMs, as decisionsupport tools. Next, Taktak and Fisher (2007) reviews recent advances related to the management of cancer, including the use of NNs for diagnosis and estimation of prognosis in cancer patients.…”

Section: Introductionmentioning

confidence: 99%

A hybrid neural network/genetic algorithm applied to breast cancer detection and recurrence

Belciug

Gorunescu

2012

Expert Systems

Self Cite

View full text Add to dashboard Cite

Genetic algorithms (GAs) and neural networks (NNs) are both inspired by computation in biological systems and many attempts have been made to combine the two methodologies to boost the NNs performance. This paper deals with the evolutionary training of a feedforward NN for both breast cancer detection and recurrence. A multi‐layer perceptron (MLP) has been designed for this purpose, using a GA routine to set weights, and a Java implementation of this hybrid model has been made. Four databases concerning cancer detection and recurrence have been used, two databases containing numerical attributes only, one database containing ordinal (categorical) attributes solely and one database with mixed attributes. In comparison to some standard NNs, the performance of this approach using the same databases is shown to be superior. Moreover, this hybrid MLP/GA model is very flexible in terms of providing accurate classification, even with different types of attributes, which is usually found in medical studies.

show abstract

Section: Introductionmentioning

confidence: 99%

A hybrid neural network/genetic algorithm applied to breast cancer detection and recurrence

Belciug

Gorunescu

2012

Expert Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…Many data mining techniques namely ANN, SVM, Gassian Mixture Model (GMM), Decision Tree, Fuzzy classifiers, etc., have been used for the automated diagnosis of the cancer (Delen, 2009;Übeyli, 2009, 2010Gorunescu et al, 2011). A description of the radon transform and the HOS features extracted from the transformed data are given in this section.…”

Section: Methodsmentioning

confidence: 99%

Higher order spectra analysis of breast thermograms for the automated identification of breast cancer

Acharya

Sree

et al. 2012

Expert Systems

View full text Add to dashboard Cite

Breast cancer is a leading cancer affecting women worldwide. Mammography is a scanning procedure involvingX‐rays of the breast. It causes discomfort and may cause high incidence of false negatives. Breast thermography is a new screening method of breast that helps in the early detection of cancer. It is a non‐invasive imaging procedure that captures the infrared heat radiating off from the breast surface using an infrared camera. The main objective of this work is to evaluate the use of higher order spectral features extracted from thermograms in classifying normal and abnormal thermograms. For this purpose, we extracted five higher order spectral features and used them in a feed‐forward artificial neural network (ANN) classifier and a support vector machine (SVM). Fifty thermograms (25 each of normal and abnormal) were used for analysis.SVM presented a good sensitivity of 76% and specificity of 84%, and theANN classifier demonstrated higher values of sensitivity (92%) and specificity (88%). The proposed system, therefore, shows great promise in automatic classification of normal and abnormal breast thermograms without the need for subjective interpretation.

show abstract

“…Furthermore, automatic decision systems consisting of forward/backward stepwise models easily can be designed based on machine learning algorithms and used to determine the focal pancreatic diagnostic classes, based on as little as possible information. 56 Integration with EUS. Digital image analysis was used to some extent for the analysis of gray-scale images in EUS, mostly for the differential diagnosis of focal pancreatic masses.…”

Section: Software-assisted Image Analysismentioning

confidence: 99%

Techniques of image enhancement in EUS (with videos)

Fusaroli

Săftoiu

Mancino

et al. 2011

Gastrointestinal Endoscopy

Self Cite

View full text Add to dashboard Cite

Competitive/collaborative neural computing system for medical diagnosis in pancreatic cancer detection

Cited by 28 publications

References 39 publications

A hybrid neural network/genetic algorithm applied to breast cancer detection and recurrence

A hybrid neural network/genetic algorithm applied to breast cancer detection and recurrence

Higher order spectra analysis of breast thermograms for the automated identification of breast cancer

Techniques of image enhancement in EUS (with videos)

Contact Info

Product

Resources

About