Research perspective and review towards brain tumour segmentation and classification using different image modalities

ABSTRACT

Previously, the brain tumour segmentation is carried out as the manual process for detecting the brain tumour from the huge quantity of Medical Resonance Images (MRI) that is obtained from the clinical practices. But, these types of manual segmentation require more time and become a tedious process. While analysing the medical images, the challenges occur in detecting the brain tumours through MRI. This recognition process becomes difficult because of certain complexities and the presence of numerous varieties of tumour tissues. This analysis is aimed to summarise the semi-automatic methods for segmenting and classifying the brain tumour MRI and other modalities. The main purpose of this paper is to provide a literature review of brain tumour segmentation and classification using different imaging modalities. At first, the different tumour segmentation and feature extraction techniques are depicted. Further, the recent trend of deep and machine learning methods in this field is reviewed and categorised. The datasets used in different contributions, the simulated platforms, and the performance measures analysed are clearly evaluated and sorted out. Finally, the unsolved challenges under this field are observed, and future advancements to improve MRI-based brain tumour detection methods in the regular clinical routine are considered.

KEYWORDS:

• Brain tumour segmentation
• brain tumour classification
• different image modalities
• medical resonance images
• machine learning
• deep learning methods

Disclosure statement

No potential conflict of interest was reported by the author(s).

Correction Statement

This article has been republished with minor changes. These changes do not impact the academic content of the article.

Additional information

Notes on contributors

Mayuri Popat

Mayuri Popat is working as an Assistant Professor in U & P.U. Patel Department of Computer Engineering, Chandubhai S Patel Institute of Technology,Charotar University of Science and Technology (CHARUSAT) - Changa. She is currently pursuing her PhD from Charusat University. She has total 11 years of teaching experience. She received her B.E. Degree in Information Technology from Government Engineering College Modasa in 2010 and M.Tech. Degree from Dept. of Computer Engineering, Dharamsinh Desai University Nadiad Gujarat in 2013. She Secured First Rank in XXVII Gujarat Science Congress in Poster presentation of Proposed Idea jointly organized by Charotar University of Science and Technology and Gujarat Science Academy (G.S.A) in the year 2012. Her Research area includes segmentation and classification in Computer Vision and Machine Learning. She has published one book chapter with the name “Video-Based Human Authentication System for Access Control” in the book named “Artificial Intelligence Paradigms for Smart Cyber-Physical Systems”in IGI Global.

Sanskruti Patel

Sanskruti Patel is currently working as an Associate Professor at the Smt. ChandabenMohanbhai Patel Institute of Computer Applications, Charotar University of Science and Technology (CHARUSAT) - Changa. Her area of research is artificial intelligence, deep learning and computer vision. She has completed her Bachelor in Mathematics in 2002 and Masters in Computer Applications in 2005. She has completed her Ph.D. in the area of fuzzy expert systems in the year 2013. She is having 16 years of experience including academics and research. She is a research supervisor in Charotar University of Science and Technology (CHARUSAT). She is actively engaged as an expert in various talks, journal reviewer, academic committees, IQAC etc.