A fully automatic methodology for MRI brain tumour detection and segmentation

ABSTRACT

In this paper, a complete and fully automatic MRI brain tumour detection and segmentation methodology is presented as an efficient clinical-aided tool using Gaussian mixture model, Fuzzy C-Means, active contour, wavelet transform and entropy segmentation methods. The proposed algorithm is based on two main parts: the skull stripping and tumour auto-detection and segmentation. The first part was evaluated using IBSR, LPBA40 and OASIS databases, and the obtained results show that our proposed method outclasses the best popular algorithms of brain extraction with scores of 0.913, 0.954 and 0.957 for the Jaccard index, Dice coefficient and sensitivity, respectively. The second part has been evaluated using BRATS database; this methodology has achieved an accuracy of 69% of true detection, and a false detection is around 22% of healthy cases detected as tumour cases and a false detection is around 9% of tumour cases detected as healthy cases. So, the tumour segmentation performed 0.67 Jaccard index and 0.69 Dice coefficient. Our methodology is found to be a fast, effective, accurate and fully automatic one without the need to any human interaction and prior knowledge for training phases as supervised methodologies in clinical applications.

KEYWORDS:

• Skull stripping
• brain tumour detection and segmentation
• Gaussian mixture model
• Fuzzy C-Means
• stationary wavelet
• maxima entropy segmentation

Acknowledgments

The authors would like to thank Professor Badr-Eddine BENKELFAT for his helpful suggestions. Authors are also very grateful to everyone who contributed to the preparation of all the databases used in this work.

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes on Contributors

S. Tchoketch Kebir received his Engineering degree in Electronics science from the University of Science and Technology (USTHB), Algeria. He received his Master’s degree in signal processing from National Polytechnics School of Algiers (ENP), Algeria. He is working as Assistant Professor in the Department of Electrical Engineering, University of Medea, Algeria. His major research interests are signal processing, medical image processing, biomedical engineering, human interaction systems, robotics systems, etc.

S. Mekaoui is actually Professor at Houari Boumediene University of Science and Technology, Faculty of Electronics and Computer Science. He received his PhD with honours at the same Faculty. His main research interests are biomedical engineering, medical image processing, optimization of telecommunications systems, etc.

M. Bouhedda is a Senior Lecturer in the Department of Electrical Engineering at the Faculty of Technology of the University of Medea, Algeria. Mounir completed his Ph.D. and Master at Houari Boumediene University, Algiers, Algeria and his undergraduate studies at The National Polytechnic School of Algiers, Algeria. His research interests are automatic control systems, electronic instrumentation, embedded intelligent systems, etc.

ORCID

S. Tchoketch Kebir http://orcid.org/0000-0002-0335-1872

S. Mekaoui http://orcid.org/0000-0002-9828-3779

M. Bouhedda http://orcid.org/0000-0002-3051-151X