TY - GEN
T1 - Classification of Brain Tissues Using Enhanced GBC and SDOST for Brain lesion detection
AU - Panda, Abhilash
AU - Mishra, Tusar Kanti
AU - Phaniharam, Vishnu Ganesh
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/10
Y1 - 2018/10
N2 - Diagnosis is a significant step in curing a dangerous disease like brain lesion. Segmentation of internal structures of brain which are taken using magnetic resonance imaging technique carries a major role in the analysis of brain lesion. This brain MRI segmentation is mainly affected by the challenges like noise in the image, bias field or intensity heterogeneity and partial volume effect. In this paper, a novel transform called Symmetric Discrete Orthonormal Stockwell Transform (SDOST) is used as denoising tool as well as feature extractor. This Stockwell transform removes noise and extracts the non-redundant multiresolution features from the MR images. These extracted features are used to train an enhanced classifier called as Grammatical Bee Colony (GBC). This enhanced GBC, a binary classifier which is used to partition the image into healthy tissues or lesions. Experimental simulation on different databases of brain MRI proves the efficiency of the contemplated method.
AB - Diagnosis is a significant step in curing a dangerous disease like brain lesion. Segmentation of internal structures of brain which are taken using magnetic resonance imaging technique carries a major role in the analysis of brain lesion. This brain MRI segmentation is mainly affected by the challenges like noise in the image, bias field or intensity heterogeneity and partial volume effect. In this paper, a novel transform called Symmetric Discrete Orthonormal Stockwell Transform (SDOST) is used as denoising tool as well as feature extractor. This Stockwell transform removes noise and extracts the non-redundant multiresolution features from the MR images. These extracted features are used to train an enhanced classifier called as Grammatical Bee Colony (GBC). This enhanced GBC, a binary classifier which is used to partition the image into healthy tissues or lesions. Experimental simulation on different databases of brain MRI proves the efficiency of the contemplated method.
UR - https://www.scopus.com/pages/publications/85084158145
UR - https://www.scopus.com/pages/publications/85084158145#tab=citedBy
U2 - 10.1109/I2CT42659.2018.9058069
DO - 10.1109/I2CT42659.2018.9058069
M3 - Conference contribution
AN - SCOPUS:85084158145
T3 - 2018 4th International Conference for Convergence in Technology, I2CT 2018
BT - 2018 4th International Conference for Convergence in Technology, I2CT 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th International Conference for Convergence in Technology, I2CT 2018
Y2 - 27 October 2018 through 28 October 2018
ER -