The specialist area of medical imaging is gaining significance in the prevalent times due to the ever-increasing need of automated and speedy diagnosis in the shortest period of time. According to the literature available, researchers have suggested that clustering, Fuzzy K-C-Means (FCM), Magnetic Resonance Imaging (MRI), K-means methods are extremely effective for timely detection and segmentation of brain tumor with the help of MRI scanned images. Some of the major limitations of these methods include complexity, ambiguous nature of the fuzzy boundaries, and diversified nature of the infarct areas or regions. This paper proposes a new technique for overcoming these drawbacks or limitations by using Conditional Random Field (CRF) based framework. The suggested method combines the information in Tumor 1 (T1) and FLAIR in probabilistic domain, so that the foreground and back ground are identified. The performance of the proposed method is validated using peal signal to noise ratio, sensitivity, specificity, accuracy, Jacard coefficient and Dice coefficient. CRF based framework is an efficient and simple method that can be incorporated for modelling shapes and for observing the functions of energy.

Brain Tumor, MRI Images, Fuzzy C-means clustering, Energy function, Conditional Random Field (CRF).

[1]. Vasupradha Vijay, A.R.Kavitha, S.Roselene Rebecca. "Automated Brain Tumor Segmentation and Detection in MRI Using Enhanced Darwinian Particle Swarm Optimization(EDPSO)", Procedia Computer Science, 2016
[2]. C.Hema Sundara Rao, P.V.Naganjaneyulu, K.Satya Prasad." Brain Tumor Detection and Segmentation Using Conditional Random Field", 2017 IEEE 7th International Advance Computing Conference (IACC), 2017
[3]. Navpreet Kaur, Manvinder Sharma. "Brain tumor detection using self-adaptive K-means clustering", 2017 International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS), 2017
[4]. Heena Hooda, Om Prakash Verma, Tripti Singhal. "Brain tumor segmentation: A performance analysis using K-Means, Fuzzy C-Means and Region growing algorithm", 2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies, 2014
[5]. Yu Zheng, Like Liu, Long hao wang, Xing Xie. "Learning transportation mode from raw gps data for geographic applications on the web", Proceeding of the 17th international conference on World Wide Web - WWW `08, 2008
[6]. Ahirwar, Anamika. "Study of Techniques used for Medical Image Segmentation and Computation of Statistical Test for Region Classification of Brain MRI", International Journal of Information Technology and Computer Science, 2013.