A region-based segmentation of tumour from brain CT images using nonlinear support vector machine classifier

Nanthagopal, A. Padma; Rajamony, R. Sukanesh

doi:10.3109/03091902.2012.682638

Cited by 15 publications

(17 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The existing methods are: Sharma et al () proposed the co‐occurrence texture features by means of bidirectional associative memory type artificial neural network, achieving an segmentation accuracy of 94.4%. Padma et al () proposed the optimal dominant gray level run length texture features by means of SVM classifier, achieving an accuracy of 95.2%. Padma et al () proposed the combined co‐occurrence, gray level and new edge features by means of SVM classifier, achieving an accuracy of 96.4%.…”

Section: Resultsmentioning

confidence: 99%

“…Padma et al () proposed the optimal dominant gray level run length texture features by means of SVM classifier, achieving an accuracy of 95.8%. Padma et al () proposed the combined co‐occurrence, gray level and new edge features by means of SVM classifier, achieving an accuracy of 96.25%. Padma et al () proposed the dominant gray level run length and gray level co‐occurrence texture features by using SVM classifier, achieving an accuracy of 97.08%.…”

Section: Discussionmentioning

confidence: 99%

“…Harrison et al (2005) proposed the texture features based on histogram, gradient, run‐length matrix, co‐occurrence matrix, autoregressive model and wavelet‐derived parameters to represent the lymphoma tissue changes during chemotherapy response monitoring. Padma et al () proposed the combined dominant gray level run length and gray level co‐occurrence texture features by means of SVM classifier to segment the and classify the benign and malignant tumor brain CT images. Padma et al () proposed the wavelet based combined dominant gray level run length and gray level co‐occurrence texture features by means of both SVM and PNN classifier to segment and classify the benign and malignant tumor brain CT images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Performance comparison of texture feature analysis methods using PNN classifier for segmentation and classification of brain CT images

Padma¹,

Giridharan

2016

Int. J. Imaging Syst. Technol.

View full text Add to dashboard Cite

A computer software system is designed for the segmentation and classification of benign and malignant tumor slices in brain computed tomography images. In this paper, we present a texture analysis methods to find and select the texture features of the tumor region of each slice to be segmented by support vector machine (SVM). The images considered for this study belongs to 208 benign and malignant tumor slices. The features are extracted and selected using Student's t-test. The reduced optimal features are used to model and train the probabilistic neural network (PNN) classifier and the classification accuracy is evaluated using k fold cross validation method. The segmentation results are also compared with the experienced radiologist ground truth. Quantitative analysis between ground truth and segmented tumor is presented in terms of quantitative measure of segmentation accuracy and the overlap similarity measure of Jaccard index. The proposed system provides some newly found texture features have important contribution in segmenting and classifying benign and malignant tumor slices efficiently and accurately. The experimental results show that the proposed hybrid texture feature analysis method using Probabilistic Neural Network (PNN) based classifier is able to achieve high segmentation and classification accuracy effectiveness as measured by Jaccard index, sensitivity, and specificity.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance comparison of texture feature analysis methods using PNN classifier for segmentation and classification of brain CT images

Padma¹,

Giridharan

2016

Int. J. Imaging Syst. Technol.

View full text Add to dashboard Cite

show abstract

“…There are multiple mathematical means that can be used to incorporate multiple parameters in an intelligent fashion, giving different weight to different parameters. The most reliable method is the use of the SVM [16][17][18][19]. The SVM is an artificial intelligence tool that depends on supervised learning to develop algorithms to analyze data, find a pattern and use it for classification.…”

Section: Pattern Recognition and Multiparameter Testing Using Svm Learningmentioning

confidence: 99%

Company Profile: NeoGenomics Laboratories, Inc.

Albitar

Bacharach

2012

Personalized Medicine

View full text Add to dashboard Cite

NeoGenomics Laboratories, Inc. is a publicly traded high-complexity national clinical laboratory company that specializes in cancer diagnostic testing, focused on molecular and genomic approaches. NeoGenomics has been associated with innovation in providing world-class pathology and cancer genetic diagnostic services for pathologists, oncologists, urologists and gastroenterologists, as well as hospitals throughout the USA. The company mission also includes the integration of technical advances in molecular methodologies including computer-aided pattern-recognition mathematical algorithms in order to integrate data from multiple analytes and thereby develop precise (personalized) predictive tools for the diagnosis of disease, prognosis and response to therapy. The company has a unique business model in that it is committed to partnering with routine diagnostic laboratories, thereby providing them with the option of technical-component-only testing for esoteric biomarkers and allowing local control of the professional component, in the interpretation and the review of raw data. The company, through innovative research and development, is dedicated to the cost-effective delivery of leading-edge, high-quality patient care through the application of precise and personalized laboratory medicine.

show abstract

“…Padma et al [1] proposed co-occurrence, gray level and new edge features by means of SVM classifier for segmentation of tumor from brain CT images. The method is applied on real data of 80 tumor images and it is inferred that better accuracy had been achieved compared with the fuzzy c-means clustering method.…”

Section: Literature Surveymentioning

confidence: 99%

Segmentation and Classification of Brain Tumor CT Images Using SVM with Weighted Kernel Width

Rezaei

Agahi

2017

Computer Science &Amp; Information Technology (CS &Amp; IT)

View full text Add to dashboard Cite

In this article a method is proposed for segmentation and classification of benign and malignant tumor slices in brain Computed Tomography (CT) images. In this study image noises are removed using median and wiener filter and brain tumors are segmented using Support Vector Machine (SVM). Then a two-level discrete wavelet decomposition of tumor image is performed and the approximation at the second level is obtained to replace the original image to

show abstract

A region-based segmentation of tumour from brain CT images using nonlinear support vector machine classifier

Cited by 15 publications

References 19 publications

Performance comparison of texture feature analysis methods using PNN classifier for segmentation and classification of brain CT images

Performance comparison of texture feature analysis methods using PNN classifier for segmentation and classification of brain CT images

Company Profile: NeoGenomics Laboratories, Inc.

Segmentation and Classification of Brain Tumor CT Images Using SVM with Weighted Kernel Width

Contact Info

Product

Resources

About