A Morphological Segmentation Based Features for Brain MRI Retrieval

Abstract

Retrieval of domain specific images is an important research area. Human brain MR Image retrieval of similar MR Images is an important application in Radiology field of medical diagnostics. Morphological segmentation is proposed for highlighting and extraction of the region based features of human brain T2 - weighted MR Images. Further fuzzy representation of these features and its use in retrieval of brain MRI is demonstrated in this paper. Segmentation results show a marked improvement in the quality of segmentation as compared to Fuzzy c-means clustering method and confirmed with manual segmentation. Further its use in retrieval has also found to give better retrieval results in terms of precision and average rank.