Multifractal Texture Estimation for Detection and Segmentation of Brain Tumors

By Atiq Islam, Syed M. S. Reza, Khan Mohammad Iftekharuddin. IEEE Transactions on Biomedical Engineering, 2013

299 citations recorded by the source corpus.

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.

Subfields: Biophysics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/8ad026c6d26714b6fe32c7ad6a4485b7c55b10d5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

1. A. Işın
2. Melike Šah
3. Cem Direkoǧlu
4. Paul Bentley
5. Ben Glocker
6. Mattias Paul Heinrich
7. Liang Chen

In Computer Vision and Pattern Recognition

1. Mattias Paul Heinrich
2. A. Işın
3. Melike Šah
4. Cem Direkoǧlu
5. Bjoern H Menze
6. Adriano Pinto
7. Paul Bentley
8. Victor Alves

Citations in the corpus

• Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images (2016, background): “A variety of features were proposed in the literature: encoding context [15], [16], [21], first-order and fractals-based texture [14], [15], [18], [21], [22], gradients [14], [15], brain symmetry [14], [15], [19], and physical properties [19].”
• Review of MRI-based Brain Tumor Image Segmentation Using Deep Learning Methods (2016, methodology): “By using these features different types of classifiers; neural networks (NN), support vector machines (SVM) 10,23 , AdaBoost 22 , k-nearest neighbor classifier (kNN) 20 , self-organizing maps (SOM) 20 , random forests (RFs) 19, 24 are implemented all producing viable segmentation results.”
• ISLES 2015 - A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI (2016, methodology): “In the second set, local texture features such as piece1061 wise triangular prism surface area, multi-fractal Brownian mo1062 tion (Islam et al., 2013) and structure tensor based local gradi1063 ents are extracted to capture the surface variation of the brain 1064”
• Brain tumor detection and classification using machine learning: a comprehensive survey (2021, background): “[154] 2013 Gabor-like multiscale texton features BRATS2012 0.”