Review on Multi Atlas Based Segmentation Using Joint Label Fusion for Alzheimer Disease

Basically this paper states about multi atlas segmentation and joint label fusion is better than any other methods for biomedical images. In this paper the images of brain are segmented in multi atlases and then joint label fusion is used. A target image is segmented by referring to atlases, i. e. , expert-labeled sample images. As an extension, multi-atlas-based segmentation makes use of more than one atlas to compensate for potential bias associated with using a single atlas and applies label fusion to produce the final segmentation. This method requires higher computational costs but, as extensive empirical studies have verified in the recent literature. It is more accurate than single atlas-based segmentation. Enabled by the availability and low cost of multicore processors, multi-atlas label fusion (MALF) is becoming more accessible to the medical image analysis community. Recently, the concept has also been applied in computer vision for segmenting natural images. Errors produced by atlas-based segmentation can be attributed to dissimilarity in the structure (e. g. , anatomy) and appearance between the atlas and the target image.