Over the past few years, challenges remain in producing an accurate brain structures segmentation due to the imag- ing nature of Magnetic Resonance images, that is known to exhibit similar intensity characteristics among subcortical structures such as the hippocampus, amygdala and caudate nucleus. Lack of a distinct image attributes that separate adjacent structures often hinders the accuracy of the segmentation. Therefore, researches have been directed to infer prior knowledge about the possible shape and spatial location to promote accurate segmentation. Realizing the importance of prior information, this focused review aims to introduce brain structures segmentation from the perspective of how the prior information has been utilized in the segmentation methods. A critical analysis on the methodology of the brain segmentation approaches, its’ advantages and issues pertaining to these methods has been discussed in detail. This review also provides an insight to the current happenings and future directions in brain structure segmentation.
White matter (WM) lesions are diffuse WM abnormalities that appear as hyperintense (bright) regions in cranial magnetic resonance imaging (MRI). WM lesions are often observed in older populations and are important indicators of stroke, multiple sclerosis, dementia and other brain-related disorders. In this paper, a new automated method for WM lesions segmentation is presented. In the proposed method, the presence of WM lesions is detected as outliers in the intensity distribution of the fluid-attenuated inversion recovery (FLAIR) MR images using an adaptive outlier detection approach. Outliers are detected using a novel adaptive trimmed mean algorithm and box-whisker plot. In addition, pre- and postprocessing steps are implemented to reduce false positives attributed to MRI artifacts commonly observed in FLAIR sequences. The approach is validated using the cranial MRI sequences of 38 subjects. A significant correlation (R=0.9641, P value=3.12×10(-3)) is observed between the automated approach and manual segmentation by radiologist. The accuracy of the proposed approach was further validated by comparing the lesion volumes computed using the automated approach and lesions manually segmented by an expert radiologist. Finally, the proposed approach is compared against leading lesion segmentation algorithms using a benchmark dataset.