A Novel Machine Learning Approach for Detecting the Brain Abnormalities from MRI Structural Images

Research output: A Conference proceeding or a Chapter in BookConference contribution

4 Citations (Scopus)

Abstract

In this study, we present the investigations being pursued in our research laboratory on magnetic resonance images (MRI) of various states of brain by extracting the most significant features, and to classify them into normal and abnormal brain images. We propose a novel method based ondeep and extreme machine learning on wavelet transform to initially decompose the images, and then use various features selection and search algorithms to extract the most significant features of brain from the MRI images. By using a comparative study with different classifiers to detect the abnormality of brain images from publicly available neuro-imaging dataset, we found that a principled approach involving wavelet based feature extraction, followed by selection of most significant features using PCA technique, and the classification using deep and extreme machine learning based classifiers results in a significant improvement in accuracy and faster training and testing time as compared to previously reported studies.
Original languageEnglish
Title of host publicationPattern Recognition in Bioinformatics
EditorsTetsuo Shibuya, Hisashi Kashima, Jun Sese, Shandar Ahmad
Place of PublicationBerlin Heidellberg
PublisherSpringer
Pages94-105
Number of pages12
Volume7632
ISBN (Print)9783642341229
DOIs
Publication statusPublished - 2012
Event7thIAPR International Conference in Pattern Recognition in Bioinformatics, PRIB 2012 - Tokyo, Tokyo, Japan
Duration: 8 Nov 201210 Nov 2012

Conference

Conference7thIAPR International Conference in Pattern Recognition in Bioinformatics, PRIB 2012
Abbreviated titlePRIB 2012
CountryJapan
CityTokyo
Period8/11/1210/11/12

Fingerprint

Magnetic resonance
Learning systems
Brain
Feature extraction
Classifiers
Neuroimaging
Research laboratories
Wavelet transforms
Testing

Cite this

Singh, L., Chetty, G., & Sharma, D. (2012). A Novel Machine Learning Approach for Detecting the Brain Abnormalities from MRI Structural Images. In T. Shibuya, H. Kashima, J. Sese, & S. Ahmad (Eds.), Pattern Recognition in Bioinformatics (Vol. 7632, pp. 94-105). Berlin Heidellberg: Springer. https://doi.org/10.1007/978-3-642-34123-6_9
Singh, Lavneet ; Chetty, Girija ; Sharma, Dharmendra. / A Novel Machine Learning Approach for Detecting the Brain Abnormalities from MRI Structural Images. Pattern Recognition in Bioinformatics. editor / Tetsuo Shibuya ; Hisashi Kashima ; Jun Sese ; Shandar Ahmad. Vol. 7632 Berlin Heidellberg : Springer, 2012. pp. 94-105
@inproceedings{7926782888ae47c88d966b60db22b1f4,
title = "A Novel Machine Learning Approach for Detecting the Brain Abnormalities from MRI Structural Images",
abstract = "In this study, we present the investigations being pursued in our research laboratory on magnetic resonance images (MRI) of various states of brain by extracting the most significant features, and to classify them into normal and abnormal brain images. We propose a novel method based ondeep and extreme machine learning on wavelet transform to initially decompose the images, and then use various features selection and search algorithms to extract the most significant features of brain from the MRI images. By using a comparative study with different classifiers to detect the abnormality of brain images from publicly available neuro-imaging dataset, we found that a principled approach involving wavelet based feature extraction, followed by selection of most significant features using PCA technique, and the classification using deep and extreme machine learning based classifiers results in a significant improvement in accuracy and faster training and testing time as compared to previously reported studies.",
keywords = "Deep Machine Learning, Extreme Machine Learning, MRI, PCA",
author = "Lavneet Singh and Girija Chetty and Dharmendra Sharma",
year = "2012",
doi = "10.1007/978-3-642-34123-6_9",
language = "English",
isbn = "9783642341229",
volume = "7632",
pages = "94--105",
editor = "Tetsuo Shibuya and Hisashi Kashima and Jun Sese and Shandar Ahmad",
booktitle = "Pattern Recognition in Bioinformatics",
publisher = "Springer",
address = "Netherlands",

}

Singh, L, Chetty, G & Sharma, D 2012, A Novel Machine Learning Approach for Detecting the Brain Abnormalities from MRI Structural Images. in T Shibuya, H Kashima, J Sese & S Ahmad (eds), Pattern Recognition in Bioinformatics. vol. 7632, Springer, Berlin Heidellberg, pp. 94-105, 7thIAPR International Conference in Pattern Recognition in Bioinformatics, PRIB 2012, Tokyo, Japan, 8/11/12. https://doi.org/10.1007/978-3-642-34123-6_9

A Novel Machine Learning Approach for Detecting the Brain Abnormalities from MRI Structural Images. / Singh, Lavneet; Chetty, Girija; Sharma, Dharmendra.

Pattern Recognition in Bioinformatics. ed. / Tetsuo Shibuya; Hisashi Kashima; Jun Sese; Shandar Ahmad. Vol. 7632 Berlin Heidellberg : Springer, 2012. p. 94-105.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - A Novel Machine Learning Approach for Detecting the Brain Abnormalities from MRI Structural Images

AU - Singh, Lavneet

AU - Chetty, Girija

AU - Sharma, Dharmendra

PY - 2012

Y1 - 2012

N2 - In this study, we present the investigations being pursued in our research laboratory on magnetic resonance images (MRI) of various states of brain by extracting the most significant features, and to classify them into normal and abnormal brain images. We propose a novel method based ondeep and extreme machine learning on wavelet transform to initially decompose the images, and then use various features selection and search algorithms to extract the most significant features of brain from the MRI images. By using a comparative study with different classifiers to detect the abnormality of brain images from publicly available neuro-imaging dataset, we found that a principled approach involving wavelet based feature extraction, followed by selection of most significant features using PCA technique, and the classification using deep and extreme machine learning based classifiers results in a significant improvement in accuracy and faster training and testing time as compared to previously reported studies.

AB - In this study, we present the investigations being pursued in our research laboratory on magnetic resonance images (MRI) of various states of brain by extracting the most significant features, and to classify them into normal and abnormal brain images. We propose a novel method based ondeep and extreme machine learning on wavelet transform to initially decompose the images, and then use various features selection and search algorithms to extract the most significant features of brain from the MRI images. By using a comparative study with different classifiers to detect the abnormality of brain images from publicly available neuro-imaging dataset, we found that a principled approach involving wavelet based feature extraction, followed by selection of most significant features using PCA technique, and the classification using deep and extreme machine learning based classifiers results in a significant improvement in accuracy and faster training and testing time as compared to previously reported studies.

KW - Deep Machine Learning

KW - Extreme Machine Learning

KW - MRI

KW - PCA

U2 - 10.1007/978-3-642-34123-6_9

DO - 10.1007/978-3-642-34123-6_9

M3 - Conference contribution

SN - 9783642341229

VL - 7632

SP - 94

EP - 105

BT - Pattern Recognition in Bioinformatics

A2 - Shibuya, Tetsuo

A2 - Kashima, Hisashi

A2 - Sese, Jun

A2 - Ahmad, Shandar

PB - Springer

CY - Berlin Heidellberg

ER -

Singh L, Chetty G, Sharma D. A Novel Machine Learning Approach for Detecting the Brain Abnormalities from MRI Structural Images. In Shibuya T, Kashima H, Sese J, Ahmad S, editors, Pattern Recognition in Bioinformatics. Vol. 7632. Berlin Heidellberg: Springer. 2012. p. 94-105 https://doi.org/10.1007/978-3-642-34123-6_9