Fully automated multi-parametric brain tumour segmentation using superpixel based classification

Abstract This paper presents a fully automated brain tissue classification method for normal and abnormal tissues and its associated region from Fluid Attenuated Inversion Recovery modality of Magnetic Resonance (MR) images. The proposed regional classification method is able to simultaneously detect and segment tumours to pixel-level accuracy. The region-based features considered in this study are statistical, texton histograms, and fractal features. This is the first study to address the class imbalance problem at the regional level using Random Majority Down-sampling-Synthetic Minority Over-sampling Technique (RMD-SMOTE). A comparison of benchmark supervised techniques including Support Vector Machine, AdaBoost and Random Forest (RF) classifiers is presented, where the RF-based regional classifier is selected in the proposed approach due to its better generalization performance. The robustness of the proposed method is evaluated on the standard publicly available BRATS 2012 dataset using five standard benchmark measures. We demonstrate that the proposed method consistently outperforms three benchmark tumour classification methods in terms of Dice score and obtains significantly better results as compared to its SVM and AdaBoost counterparts in terms of precision and specificity at the 5% confidence interval. The promising results of the proposed method support its application for early detection and diagnosis of brain tumours in clinical settings.

[1]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[2]  Ezequiel Geremia,et al.  Spatial Decision Forests for Glioma Segmentation in Multi-Channel MR Images , 2011 .

[3]  Douglas C. Miller,et al.  Gliomas: predicting time to progression or survival with cerebral blood volume measurements at dynamic susceptibility-weighted contrast-enhanced perfusion MR imaging. , 2008, Radiology.

[4]  Anil K. Jain.  Fundamentals of Digital Image Processing , 2018, Control of Color Imaging Systems.

[5]  Eiji Kohmura,et al.  GC/MS-based metabolomic analysis of cerebrospinal fluid (CSF) from glioma patients , 2013, Journal of Neuro-Oncology.

[6]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  E. Holland.  Progenitor cells and glioma formation , 2001, Current opinion in neurology.

[8]  Bjoern H Menze,et al.  Patch-based Segmentation of Brain Tissues , 2013 .

[9]  Martin Vetterli,et al.  Adaptive wavelet thresholding for image denoising and compression , 2000, IEEE Trans. Image Process..

[10]  Yoav Freund,et al.  A Short Introduction to Boosting , 1999 .

[11]  José V. Manjón,et al.  Automated Glioblastoma Segmentation Based on a Multiparametric Structured Unsupervised Classification , 2015, PloS one.

[12]  Jean-Marc Constans,et al.  TUMOR SEGMENTATION FROM A MULTISPECTRAL MRI IMAGES BY USING SUPPORT VECTOR MACHINE CLASSIFICATION , 2007, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[13]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[14]  Pablo A. Estévez,et al.  A review of feature selection methods based on mutual information , 2013, Neural Computing and Applications.

[15]  Michael Kistler,et al.  The Virtual Skeleton Database: An Open Access Repository for Biomedical Research and Collaboration , 2013, Journal of medical Internet research.

[16]  Liang Zhao,et al.  Brain tumor segmentation based on GMM and active contour method with a model-aware edge map , 2012 .

[17]  Mark R Gilbert,et al.  Imaging techniques in neuro-oncology. , 2004, Seminars in oncology nursing.

[18]  T. Arbel,et al.  Probabilistic Gabor and Markov Random Fields Segmentation of B rain Tumours in MRI Volumes , 2012 .

[19]  V. R. Simi,et al.  Segmentation of Glioblastoma Multiforme from MR Images – A comprehensive review , 2015 .

[20]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[22]  Rudolf Mester,et al.  Contour-Relaxed Superpixels , 2013, EMMCVPR.

[23]  Amitava Chatterjee,et al.  Hybrid multiresolution Slantlet transform and fuzzy c-means clustering approach for normal-pathological brain MR image segregation. , 2008, Medical engineering & physics.

[24]  Mohammed Elmogy,et al.  Brain tumor segmentation based on a hybrid clustering technique , 2015 .

[25]  Arturo Garcia-Perez,et al.  Localized active contour model with background intensity compensation applied on automatic MR brain tumor segmentation , 2017, Neurocomputing.

[26]  Dong Hye Ye,et al.  Context-sensitive Classication Forests for Segmentation of Brain Tumor Tissues , 2012 .

[27]  G. Reifenberger,et al.  The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary , 2016, Acta Neuropathologica.

[28]  Wei Wu,et al.  Brain tumor detection and segmentation in a CRF (conditional random fields) framework with pixel-pairwise affinity and superpixel-level features , 2013, International Journal of Computer Assisted Radiology and Surgery.

[29]  Wankai Deng,et al.  MRI brain tumor segmentation with region growing method based on the gradients and variances along and inside of the boundary curve , 2010, 2010 3rd International Conference on Biomedical Engineering and Informatics.

[30]  Bradley J. Erickson,et al.  Automated Segmentation of Hyperintense Regions in FLAIR MRI Using Deep Learning , 2016, Tomography.

[31]  Sabine Van Huffel,et al.  Hierarchical non‐negative matrix factorization to characterize brain tumor heterogeneity using multi‐parametric MRI , 2015, NMR in biomedicine.

[32]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[33]  Umit Ilhan,et al.  Brain tumor segmentation based on a new threshold approach , 2017 .

[34]  Achim Zeileis,et al.  Bias in random forest variable importance measures: Illustrations, sources and a solution , 2007, BMC Bioinformatics.

[35]  Brian B. Avants,et al.  Optimal Symmetric Multimodal Templates and Concatenated Random Forests for Supervised Brain Tumor Segmentation (Simplified) with ANTsR , 2014, Neuroinformatics.

[36]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[37]  S. Bauer,et al.  A survey of MRI-based medical image analysis for brain tumor studies , 2013, Physics in medicine and biology.

[38]  Sim Heng Ong,et al.  Automated brain tumor segmentation using kernel dictionary learning and superpixel-level features , 2016, 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[39]  Zoran Obradovic,et al.  A robust data scaling algorithm to improve classification accuracies in biomedical data , 2016, BMC Bioinformatics.

[40]  Guang Yang,et al.  Automated brain tumour detection and segmentation using superpixel-based extremely randomized trees in FLAIR MRI , 2016, International Journal of Computer Assisted Radiology and Surgery.

[41]  Hoo-Chang Shin,et al.  Hybrid Clustering and Logistic Regression for Multi-Modal Brain Tumor Segmentation , 2012 .

[42]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[43]  R. Meier,et al.  A Hybrid Model for Multimodal Brain Tumor Segmentation , 2013 .

[44]  Michael A. Yassa.  Neurocognitive aging and the human hippocampus , 2010 .

[45]  Kashif Rajpoot,et al.  Brain tumor classification from multi-modality MRI using wavelets and machine learning , 2017, Pattern Analysis and Applications.

[46]  Mie Sato,et al.  A gradient magnitude based region growing algorithm for accurate segmentation , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).