Brain structural disorders detection and classification approaches: a review

This paper is an effort to encapsulate the various developments in the domain of different unsupervised, supervised and half supervised brain anomaly detection approaches or techniques proposed by the researchers working in the domain of the Medical image segmentation and classification. As researchers are constantly working hard in the domain of image segregation, interpretation and computer vision in order to automate the task of tumour segmentation, anomaly detection, classification and other structural disorder prediction at an early stage with the aid of computer. The different medical imaging modalities are used by the doctors in order to diagnose the brain tumour and other structural brain disorders which are an integral part of diagnosis and prognosis process. When these different medical image modalities are used along with various image segmentation methods and machine learning approaches tends to perform brain structural disorder detection and classification in a semi-automated or fully automated manner with high accuracy. This paper presents all such approaches using various medical image modalities for the accurate detection and classification of brain tumour and other brain structural disorders. In this paper, all the major phases of any brain tumour or brain structural disorder detection and classification approach is covered begin with the comparison of various medical image pre-processing techniques then major segmentation approaches followed by the approaches based on machine learning. This paper also presents an evaluation and comparison among the various popular texture and shape based feature extraction methods used in combination with different machine learning classifiers on the BRATS 2013 dataset. The fusion of MRI modalities used along with the hybrid features extraction methods and ensemble model delivers the best result in terms of accuracy.