Automatic brain tumor detection in MRI: methodology and statistical validation

Iftekharuddin, Khan M.; Islam, Mohammad Aminul; Shaik, Jahangheer; Parra, Carlos; Ogg, Robert J.

doi:10.1117/12.595931

Cited by 16 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Higher values of accuracy, sensitivity, specificity and lower FPR indicate better performance. Dice similarity (DS) coefficient [20] is also used to evaluate the performance of the proposed method quantitatively. DS is calculated as following:…”

Section: Results and Analysismentioning

confidence: 99%

Artificial Neural Network based Lesion Segmentation of Brain MRI

Si¹,

De²,

Kumar³

2016

CAE

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%

Artificial Neural Network based Lesion Segmentation of Brain MRI

Si¹,

De²,

Kumar³

2016

CAE

View full text Add to dashboard Cite

show abstract

“…Reference [20] proposes fractional Brownian motion (fBm) model for tumor texture estimation. An fBm process, on [0 , T ] , T ∈ ℛ, is a continuous Gaussian zero-mean nonstationary stochastic process starting at t = 0.…”

Section: Background Reviewmentioning

confidence: 99%

“…Although fBm modeling has been shown useful for brain tumor texture analysis [20], considering the rough heterogeneous appearance of tumor texture in brain MRI, fBm appears homogeneous, or monofractal. In fBm process, the local degree of H is considered the same at all spatial/time variations.…”

Section: Background Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Multifractal Texture Estimation for Detection and Segmentation of Brain Tumors

Islam

Reza

Iftekharuddin

2013

IEEE Trans. Biomed. Eng.

Self Cite

251

122

View full text Add to dashboard Cite

A stochastic model for characterizing tumor texture in brain magnetic resonance (MR) images is proposed. The efficacy of the model is demonstrated in patient-independent brain tumor texture feature extraction and tumor segmentation in magnetic resonance images (MRIs). Due to complex appearance in MRI, brain tumor texture is formulated using a multiresolution-fractal model known as multifractional Brownian motion (mBm). Detailed mathematical derivation for mBm model and corresponding novel algorithm to extract spatially varying multifractal features are proposed. A multifractal feature-based brain tumor segmentation method is developed next. To evaluate efficacy, tumor segmentation performance using proposed multifractal feature is compared with that using Gabor-like multiscale texton feature. Furthermore, novel patient-independent tumor segmentation scheme is proposed by extending the well-known AdaBoost algorithm. The modification of AdaBoost algorithm involves assigning weights to component classifiers based on their ability to classify difficult samples and confidence in such classification. Experimental results for 14 patients with over 300 MRIs show the efficacy of the proposed technique in automatic segmentation of tumors in brain MRIs. Finally, comparison with other state-of-the art brain tumor segmentation works with publicly available low-grade glioma BRATS2012 dataset show that our segmentation results are more consistent and on the average outperforms these methods for the patients where ground truth is made available.

show abstract

“…Image processing techniques such as fuzzy connectedness 2 and deformable model 3 have been proposed for MRI brain tumour segmentation. Most of the previously performed studies work falls into the category of pattern recognition methods 4,5,6 . The key to successful pattern recognition methods is to extract effective features.…”

Section: Introductionmentioning

confidence: 99%

Optimal Statistical Structure Validation of Brain Tumors Using Refractive Index

Ghosh

Kundu

Chowdhury

et al. 2015

Procedia Computer Science

View full text Add to dashboard Cite

Tumour segmentation from brain MRI is more than a decade old problem in the field of medical imaging. Till date automated brain tumour segmentation happens to be a difficult task due to the variance and complexity of tumour growth. In this paper, we present this segmentation problem for the purpose of determining the exact location of brain tumour using refractive index study on the structural analysis of both tumorous and normal tissues. Initially, as per existing survey 3 kinds of features namely, intensity-based, texture-based, and symmetry-based are extracted from the structural elements. Then reduction of this feature set is performed and similar features are clustered together. Refractive index analysis is performed on each of the clusters from the MR T2 relaxation time. Deviation from a threshold value of RI for majority of pixels in a particular cluster denotes it to be the tumorous region.

show abstract

Automatic brain tumor detection in MRI: methodology and statistical validation

Cited by 16 publications

References 0 publications

Artificial Neural Network based Lesion Segmentation of Brain MRI

Artificial Neural Network based Lesion Segmentation of Brain MRI

Multifractal Texture Estimation for Detection and Segmentation of Brain Tumors

Optimal Statistical Structure Validation of Brain Tumors Using Refractive Index

Contact Info

Product

Resources

About