Event Abstract

Back to Event

Segmentation and analysis of hippocampus and ventricle in Alzheimer’s brain MR images using Minkowski weighted K-means clustering and its ratiometric index

Kayalvizhi M1*, Kavitha G1, Sujatha C.M2 and Ramakrishnan S3
  • 1 MIT annauniversity, Department of Electronics Engg, India
  • 2 CEG campus Annauniversity, India
  • 3 IIT Madras, Department of Appl. Mechanics, India

Alzheimer’s disease (AD) is the common form of dementia, affecting over 24 million people worldwide with characteristic pathology of plaques and neurofibrillary tangles. This is accompanied by hippocampal atrophy and ventricular enlargement. Although AD and mild cognitive impairment (MCI) are commonly diagnosed using sets of clinical criteria, MRI findings aid the clinical diagnosis and predict clinical progression. Ventricles are located at the centre of the brain and appear dark in T1-weighted MRI scans.The hippocampus appears to be small and has regional appearance similar to its neighbouring structures. In this work, segmentation of both the hippocampus and the ventricle are carried out by Minkowski weighted K-means clustering method. The normal (30) and abnormal (30 mild, 30moderate and 30 severe) images considered in this work are obtained from MIRIAD database. Initially, the ROI is selected from original T1 sagittal image. This multiobject segmentation approach extends the K-Means criterion using Minkowski metric as a distance measure. This formulation also uses weight updating computations. Here, four initial centroids are selected for clustering from the histogram of the image.The exponent of the Minkowksi distance measure is chosen to be 6. From the clustered output, the ventricle and hippocampus are extracted using morphology operations. The segmented images are quantified using Minkowski features which captures the topology changes. These features are calculated for hippocampus and the ventricles of different normal and abnormal images and analysed.The prominent feature is correlated with the Mini-Mental State Examination (MMSE) score. Results show that Minkowski metric weighted K-Means method is able to delineate the boundary of the hippocampus and ventricle from normal and abnormal conditions.The accuracy of segmentation is high (81%). It is observed that the Minkowski area of segmented hippocampus and ventricle provide significant discrimination of normal and abnormal subjects. The ratio of hippocampus to ventricle area helps in better discrimination of severity in pathology conditions. Its correlation with MMSE is observed to be very high for normal (R=0.87) subjects.The correlation is found to be moderately high for mild (R=0.70), moderate(R=0.72) and severe (R=0.84) Alzheimer subjects. Hence this ratiometric index which takes into account of atrophy of hippocampus and the enlargement of ventricle could be used for the study of progression in neurodegenerative disorder such as AD.

Figure 1
Image
Figure 2
Image
Figure 3
Image
Figure 4
Image
Figure 5
Image

Acknowledgements

Data used in the preparation of this article were obtained from the MIRIAD database (http://miriad.drc.ion.ucl.ac.uk).
The MIRIAD investigators did not participate in analysis or writing of this report. The MIRIAD dataset is made available through the support of the UK Alzheimer's Society (Grant RF116). The original data collection was funded through an unrestricted educational grant from GlaxoSmithKline (Grant 6GKC).

References

[1]Apostolova, Liana G., Amity E. Green, Sona Babakchanian, Kristy S. Hwang, Yi-Yu Chou, Arthur W. Toga, and Paul M. Thompson. "Hippocampal atrophy and ventricular enlargement in normal aging, mild cognitive impairment and Alzheimer's disease." Alzheimer disease and associated disorders 26, no. 1 (2012): 17.
[2]Cordeiro de Amorim, Renato, and Boris Mirkin. "Minkowski metric, feature weighting and anomalous cluster initializing in K-Means clustering." Pattern Recognition 45, no. 3 (2012): 1061-1075.
[3]Michielsen, K., and Hans De Raedt. "Integral-geometry morphological image analysis." Physics Reports 347, no. 6 (2001): 461-538.
[4]Nagarajan, Mahesh B., Markus B. Huber, Thomas Schlossbauer, Gerda Leinsinger, Andrzej Krol, and Axel Wismüller. "Classification of small lesions in dynamic breast MRI: eliminating the need for precise lesion segmentation through spatio-temporal analysis of contrast enhancement." Machine vision and applications 24, no. 7 (2013): 1371-1381.

Keywords: Alzheimer’s disease, Minkowski weighted K means clustering, Hippocampus, ventricle, Minkowski functional

Conference: Neuroinformatics 2014, Leiden, Netherlands, 25 Aug - 27 Aug, 2014.

Presentation Type: Poster, to be considered for oral presentation

Topic: Neuroimaging

Citation: M K, G K, C.M S and S R (2014). Segmentation and analysis of hippocampus and ventricle in Alzheimer’s brain MR images using Minkowski weighted K-means clustering and its ratiometric index. Front. Neuroinform. Conference Abstract: Neuroinformatics 2014. doi: 10.3389/conf.fninf.2014.18.00083

Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.

The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.

Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.

For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.

Received: 27 Apr 2014; Published Online: 04 Jun 2014.

* Correspondence: Ms. Kayalvizhi M, MIT annauniversity, Department of Electronics Engg, chennai, India, kayalvizhiv@gmail.com