MRI feature extraction using genetic algorithms

Velthuizen, R.P.; Hall, Larry; Clarke, Laurence P.

doi:10.1109/iembs.1996.652744

Cited by 9 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the results presented here cannot be used for feature selection directly, it can be a useful reference in feature ranking. We will explore the use of genetic algorithms for feature selection 29 and the use of neural networks with more efficient training by Kalman filtering 30 for improved feature classification. And by optimization of specifically all CAD modules, it is anticipated that a more realistic perfor-mance can be achieved and a CAD method that may be potentially generalized for applications to different sensors as required for clinical trials for CAD.…”

Section: Discussionmentioning

confidence: 99%

Image feature extraction for mass detection in digital mammography: Influence of wavelet analysis

Qian

Clarke

1999

Medical Physics

View full text Add to dashboard Cite

Rationale and objectives. The objective of this work is to evaluate the importance of image preprocessing, using multiresolution and multiorientation wavelet transforms (WTs), on the performance of a previously reported computer assisted diagnostic (CAD) method for breast cancer screening, using digital mammography. Method: An analysis of the influence of WTs on image feature extraction for mass detection is achieved by comparing the discriminant ability of features extracted with and without the wavelet‐based image preprocessing using computed ROC. Three indexes are proposed to assess the segmentation of the mass area with comparison to the ground truth. Data was analyzed on the region‐of‐interest (ROI) database that included mass and normal regions from digitized mammograms with the ground truth. Results: The metrics for the measurement of segmentation of the mass clearly demonstrated the importance of image preprocessing methods. Similarly, the relative improvement in performance was observed in feature extraction based on the evaluation of the ROC curves, where the Az values are increased, for example, from 0.71 to 0.75 for a pixel intensity feature and from 0.72 to 0.85 for a morphological feature of the Normalized Deviation of Radial Length. The improvement, therefore, depends on the feature characteristics, being large for boundary‐related features while small for intensity‐related features. Conclusion: The use of image preprocessing modules using wavelet transforms results in a significant improvement in feature extraction for the previously proposed CAD detection method. We are therefore exploring additional improvement in wavelet‐based image preprocessing methods, including adaptive methods, to achieve a further improvement in performance and an evaluation on larger image databases.

show abstract

Section: Discussionmentioning

confidence: 99%

Image feature extraction for mass detection in digital mammography: Influence of wavelet analysis

Qian

Clarke

1999

Medical Physics

View full text Add to dashboard Cite

show abstract

“…For the classification of brain tumors in [3], the author proposed the use of a genetic algorithm for feature extraction, which used fuzzy c-means for segmentation purposes. Intensity-based shape features were identified using Fourier [4] analysis for classification of the breast tumors.…”

Section: Related Workmentioning

confidence: 99%

Machine Learning Assisted Methodology for Multiclass Classification of Malignant Brain Tumors

Vidyarthi

Agarwal²,

Gupta

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Analysis of malignant and non-malignant brain tumors is done using a computer-aided diagnosis system by practitioners worldwide. Radiologists refer computer-assisted techniques to draw conclusions using image modalities and inferences. Pedagogically, various machine learning approaches have been used, which usually focus on the classification of imaging modality into two categories, either normal and abnormal images or differentiating between benign and malignant tumors. Still, the work requirement is to classify these multi-class malignant tumors into their specific class with better precision. The proposed work focuses on distinguishing between the types of high-grade malignant brain tumors. This study is performed on real-life malignant brain tumor datasets having five classes. The proposed methodology uses the vast feature set from six domains to capture most of the hidden information in the extracted region of interest. Later, relevant features are extracted from the feature set pool using a new proposed feature selection algorithm named the Cumulative Variance method (CVM). Next, the selected features are used for model training and testing using K-Nearest Neighbour (KNN), multi-class Support Vector Machine (mSVM), and Neural Network (NN) for predicting multi-class classification accuracy. The experiments are performed using the proposed feature selection algorithm with three classifiers. The mean average classification accuracy achieved by using the proposed approach is88.43% (KNN), 92.5% (mSVM), and 95.86% (NN), respectively. The comparative analysis of the proposed approach with other existing algorithms like ICA, and GA suggest that the proposed approach gains an increase of accuracy around 2% (KNN), 3% (SVM), and 4% (NN).The experimentation results concluded that the proposed approach is found better with NN classifier with an accuracy of 95.86% using diversified features.

show abstract

“…For the classification of brain tumors in [3] author uses genetic algorithm for feature extraction which was used by fuzzy cmeans for segmentation purpose. While intensity based shape features was identified using Fourier [4] analysis for classification of the breast tumors.…”

Section: Related Workmentioning

confidence: 99%

Performance analysis of Gabor-Wavelet based features in classification of high grade malignant brain tumors

Vidyarthi

Mittal

2015

2015 39th National Systems Conference (NSC)

View full text Add to dashboard Cite

Incorporating machine learning based concepts and knowledge in medical science domain elaborates the interdisciplinary research areas. Using such the identification of the disease is accomplished at initial state of its generation with better accuracy as compared to naked eye. In past, lot of feature extraction approaches were proposed to extract the features in spectral domain. Among all approaches, two major approaches was Gabor filter based feature extraction and Wavelet based feature extraction mechanism. But it leads to the kiosk that which feature extraction mechanism is better for classification perspective. This paper focuses on machine learning based approach for performance analysis for the grade of malignant tumor types using a diverse feature set based on Gabor and Wavelet transformation. Further, various feature selection (FS) algorithms are taken into consideration for selection of the best feature set among the feature vector. For experimental purpose, several state-of-art classifiers are used for analysis of the performance for the classification of malignant brain tumors in magnetic resonance (MR) images. In experimentation several high grade malignant brain tumors like Central Neuro Cytoma (CNC), Glioblastoma Multiforme (GBM), Gliomas, Intra Ventricular Malignant Mass, and Metastasis are taken into consideration having 30 images of each tumor type. The classification accuracies achieved using various combinations of FS-Classifier's are presented in detail.

show abstract

MRI feature extraction using genetic algorithms

Cited by 9 publications

References 8 publications

Image feature extraction for mass detection in digital mammography: Influence of wavelet analysis

Image feature extraction for mass detection in digital mammography: Influence of wavelet analysis

Machine Learning Assisted Methodology for Multiclass Classification of Malignant Brain Tumors

Performance analysis of Gabor-Wavelet based features in classification of high grade malignant brain tumors

Contact Info

Product

Resources

About