A Novel Pixel Counting Technique to Assess the Volumetric Changes in Human Brain Morphology

K. Nithyakalyani^1*, R. Kalpana², S. Sudhakar³ and N. Vigneswaran⁴

¹Department of Biomedical Engineering, Vel Tech Multi Tech Dr.RR Dr.SR Engineering College, Chennai. India. ²Department of Biomedical Engineering,Rajalakshmi Engg.,College, Chennai,India. ³Department of Electronics and communication Engineering, Balaji Institute of Engineering and Technology, Chennai, India. ⁴Faculty of Electrical and Electronics Engineering, Universiti Malaysia Pahang, Pekan 26600,Malaysia

ABSTRACT: Morphometric measurements such as volume, thickness and sulcal depth are used to provide valuable information about cortical characteristics in both healthy and diseased conditions of the brain. Relevantly, the focus of this paper is to illustrate the morphometric method of assessing the volume changes in the brain caused by aging and/ or pathological condition. Using the T1-weighted magnetic resonance images of the brain, the clustering technique is adopted towards segmenting the image into separate compartments of white and gray matters (WM and GM) and the cerebral-spinal fluid (CSF). The clustering technique pursued includes the traditional K-means and fuzzy Cmeans algorithm by considering the Euclidean distance metric toward grouping of entities of similar pattern vectors. The method evolved allows the underlying volume measurement of clustered regions by pixel-counting technique. Comparison of volume measurement of segmented cerebral tissues among male and female subjects undergoing ageing process and with cerebral pathogenic states is exercised. The volumetric changes among the male and female subjects are also considered The results reveal distinct details thereof. Specifically, the volumetric assessment indicated proves to be a viable technique toward understanding the gender differences, geriatric changes in the brain as well as the conditions of brain tissues vis-à-vis neuro-related issues. Clinical data gathered and computed results on the proposed method are furnished to illustrate the efficacy of the method and its short comings.

KEYWORDS: White matter; Gray matter; Cerebrospinal fluid; K-means; Fuzzy C-means clustering technique; Pixel counting technique

This work is licensed under a Creative Commons Attribution 4.0 International License.