Brain MRI segmentation for tumor detection via entropy maximization using Grammatical Swarm

Si, Tapas; De, Arunava; Bhattacharjee, Anup Kumar

doi:10.1142/s0219691315500393

Cited by 14 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By the visual inspection and analysis of the segmented images with lesions, it is clear that the proposed method detects lesions in MRI more accurately than K-means based segmentation method. The quantitative performance is measured using confusion matrix [11]. The accuracy, sensitivity, specificity and False Positive Rate (FPR) are derived using confusion matrix.…”

Section: Results and Analysismentioning

confidence: 99%

“…The noise across the MR images is removed using median filter with size 3 × 3 [9]. After denoising, the intensity inhomogeneity is corrected using Max filter based method [5,11].…”

Section: Denoising and Iih Correctionmentioning

confidence: 99%

“…The proposed method performs better than PSO based clustering technique. T. Si et al [11] proposed a entropy maximization based segmentation method using Grammatical Swarm for lesion detection in brain MRI.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Artificial Neural Network based Lesion Segmentation of Brain MRI

Si¹,

De²,

Kumar³

2016

CAE

Self Cite

View full text Add to dashboard Cite

An Artificial Neural Network based segmentation method for lesion in brain is proposed. First, Magnetic Resonance Images (MRI) are denoised and intensity inhomogeneities are corrected in the preprocessing steps. Artificial neural network is used for training using gray levels and extracted statistical features from the training data with the labelled ground truth. The test images are segmented into lesion and healthy tissues using trained neural network. The connected component labelling algorithm is used to extract only lesion from the segmented images. The proposed method is applied on two MRI data set. The performance of the proposed method is compared with K-means algorithm. The proposed method performs better than K-means algorithm both qualitatively and quantitatively.

show abstract

Section: Results and Analysismentioning

confidence: 99%

“…The noise across the MR images is removed using median filter with size 3 × 3 [9]. After denoising, the intensity inhomogeneity is corrected using Max filter based method [5,11].…”

Section: Denoising and Iih Correctionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Neural Network based Lesion Segmentation of Brain MRI

Si¹,

De²,

Kumar³

2016

CAE

Self Cite

View full text Add to dashboard Cite

show abstract

“…In Ref. 34, a method of brain MRI segmentation for tumor detection via entropy maximization using grammatical swarm is proposed.…”

Section: Literature Review On the Existing Work And Limitationsmentioning

confidence: 99%

On curvelet CS reconstructed MR images and GA-based fuzzy conditional entropy maximization for segmentation

Roy¹,

Maity

2019

Int. J. Wavelets Multiresolut Inf. Process.

View full text Add to dashboard Cite

In many practical situations, magnetic resonance imaging (MRI) needs reconstruction of images at low measurements, far below the Nyquist rate, as sensing process may be very costly and slow enough so that one can measure the coefficients only a few times. Segmentation of such subsampled reconstructed MR images for medical analysis and diagnosis becomes a challenging task due to the inherent complex characteristics of the MR images. This paper considers reconstruction of MR images at compressive sampling (or compressed sensing (CS)) paradigm followed by its segmentation in an integrated platform. Image reconstruction is done from incomplete measurement space with random noise injection iteratively. A weighted linear prediction is done for the unobserved space followed by spatial domain denoising through adaptive recursive filtering. The reconstructed images, however, suffer from imprecise and/or missing edges, boundaries, lines, curvatures etc. and residual noise. Curvelet transform (CT) is purposely used for removal of noise and for edge enhancement through hard thresholding and suppression of approximate subbands, respectively. Then a fuzzy entropy-based clustering, using genetic algorithms (GAs), is done for segmentation of sharpen MR Image. Extensive simulation results are shown to highlight performance improvement of both image reconstruction and segmentation of the reconstructed images along with relative gain over the existing works.

show abstract

“…Brain tissue segmentation partitions the brain mainly into white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF) along with its various abnormalities. There are seven objects in a brain MRI: 1) scalp, 2) bone, 3) CSF, 4) WM, 5) GM, 6) Tumor (if present), and 7) background [12]. Brain image segmentation is an integral part of brain MR image analysis.…”

Section: Introductionmentioning

confidence: 99%

State-of-the Art Optimal Multilevel Thresholding Methods for Brain MR Image Analysis

Das¹,

Agrawal²,

Samantaray³

et al. 2020

RIA

View full text Add to dashboard Cite

The brain MR image analysis is a primary non-invasive component to detect any abnormality in the brain. It is a very important application in the field of medical image processing. For analysing brain MR images, there is a strong need to develop efficient image segmentation methods. Over the years, many image segmentation techniques have been suggested and their real life applications have also been studied. Implementation of these segmentation techniques in biomedical engineering is a major breakthrough. Intensive research works have been carried out explicitly on the analysis of human brain images and their subsequent detection of lesion cells using different segmentation methods. One of the easiest and most generally used method of segmentation is multilevel thresholding due to its precision and robustness against the other methods. To solve the problem of computational complexity for increasing threshold levels, various optimization algorithms are used for optimal multilevel thresholding. In this paper, an attempt is made to present a comprehensive review on the recent advancements in the area of brain MR image segmentation using optimal multilevel thresholding. This review is unique of its kind due to its exclusive emphasis on segmentation of brain MR image using thresholding technique only, which may not be present in the existing literature reviews. Different validation measures used for the multilevel image thresholding are discussed. A detailed comparison of the results obtained over the years is done. The merits and demerits of the methods are highlighted. This compilation aims to aid and encourage researchers to further explore the research in this direction.

show abstract

Brain MRI segmentation for tumor detection via entropy maximization using Grammatical Swarm

Cited by 14 publications

References 16 publications

Artificial Neural Network based Lesion Segmentation of Brain MRI

Artificial Neural Network based Lesion Segmentation of Brain MRI

On curvelet CS reconstructed MR images and GA-based fuzzy conditional entropy maximization for segmentation

State-of-the Art Optimal Multilevel Thresholding Methods for Brain MR Image Analysis

Contact Info

Product

Resources

About