Open AccessQuantitative metric for MR brain tumour grade classification using sample space density measure of analytic intrinsic mode function representation
Author(s) -
Kaur Taranjit,
Saini Barjinder Singh,
Gupta Savita
Publication year - 2017
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2016.1103
Subject(s) - pattern recognition (psychology) , artificial intelligence , hilbert–huang transform , feature (linguistics) , metric (unit) , segmentation , feature vector , mathematics , computer science , statistics , white noise , linguistics , philosophy , operations management , economics
In the present study, a new feature named as density measure is proposed for classification of the glioma brain tumour magnetic resonance (MR) image into low and high‐grade categories. The proposed feature is derived using improved complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and Hilbert transformation technique. The proposed feature uses the difference signal created by mapping of the fluid attenuation inversion recovery segmented region onto T1 and T1‐contrast‐enhanced MR images. This difference signal is decomposed into various intrinsic mode functions (IMFs) using improved CEEMDAN algorithm that effectively captures the texture variations existing in both tumour groups. Then, the Hilbert transformation of resulting IMF is computed that provides the analytic signal representation, thereby giving a better visualisation of the texture difference. The proposed feature is calculated from this analytic signal representation at 97% confidence level. Subsequently, this feature is utilised to calculate a quantitative metric for tumour classification. The proposed metric has been validated on 120 tumorous images taken from brain tumour image segmentation benchmark (BRATS) 2012 dataset and the images taken from Harvard Medical School repository. The results illustrate that proposed metric yields an overall classification accuracy of 100% which is better than existing state‐of‐art works.