Model-guided segmentation of corpus callosum in MR images (original) (raw)

Classification of brain MR images using Corpus Callosum Shape measurements

The corpus callosum is the largest white matter structure in the brain, which connects the two cerebral hemispheres and facilitates the inter-hemispheric communication. Abnormal anatomy of corpus callosum has been revealed for various brain related diseases. Being an important biomarker, Magnetic Resonance Imaging of the brain followed by corpus callosum segmentation and feature extraction has found to be important for the diagnosis of many neurological diseases. This paper focuses on classification of T1-weighted mid-sagittal MR images of brain for dementia patients. The corpus callosum is segmented using K-means clustering algorithm and corresponding shape based measurements are used as features. Based on these shape based measurements, a neural network is trained separately for male and female dataset. The input data consists of 54 female and 42 male patients. This paper reports classification accuracy up to 92% for female patients and 94% for male patients using neural network classifier.

K-means clustering approach for the segmentation of corpus callosum from MR images

Abstract-The corpus callosum is one of the most important structures in human brain. Most of the neurological disorders reflect directly or indirectly on the morphological features of Corpus Callosum. The mid-sagittal brain Magnetic Resonance images fully describe the anatomical structure of corpus callosum. Often considered challenging task of segmenting Corpus Callosum from Magnetic Resonance images has proved the importance of studies on Corpus Callosum segmentation. In this paper, a K-means clustering algorithm is proposed for segmentation of the region of Corpus Callosum. The results of segmentation can be used further for feature extraction and classification for medical diagnosis. Keywords-Corpus Callosum, K-means clustering, Segmentation and Magnetic Resonance Image