Sparse Nonlocal Texture Mean for Allocation of Irregularity in Images of Brain

Đã xuất bản năm 2017

Tác giả: Đào Nam Anh
Tạp chí: Advances in Intelligent Systems and Computing
ISSN: 2194-5357
Xếp loại: Scopus
Fulltext: Chưa có

Tóm tắt bằng tiếng việt :


 
Dao Nam Anh, Sparse Nonlocal Texture Mean for Allocation of Irregularity in Images of Brain, Information Systems Design and Intelligent Applications, Advances in Intelligent Systems and Computing 672, Springer, Singapore, ISSN 2194-5357,  pp 618-628, 2018. ISSN 2194-5365 (electronic), ISBN 978-981-10-7511-7 ISBN 978-981-10-7512-4 (eBook), doi: 978-981-10-7512-4_61, old name: Advances in Intelligent and Soft ComputingScopus index, impact factor, pptx.

The medical image analysis for irregularity studies has always been a refreshing research topic for the need of efficient and precise diagnosis. A new method based on patch analysis for detection of disorder in images of brain is introduced with machine learning techniques. In the method a sparse nonlocal texture mean filter is proposed to evaluate the similarity of each spot in the image. The spot-based similarity allows initial identification of place of abnormality which is then refined by the support vector machines to efficiently perform extraction of disorder’s region. Experimental results on a benchmark’s real data are assessed and compared objectively to ensure sufficient certainty of the method.
 

Tóm tắt bằng tiếng anh :


 
Dao Nam Anh, Sparse Nonlocal Texture Mean for Allocation of Irregularity in Images of Brain, Information Systems Design and Intelligent Applications, Advances in Intelligent Systems and Computing 672, Springer, Singapore, ISSN 2194-5357,  pp 618-628, 2018. ISSN 2194-5365 (electronic), ISBN 978-981-10-7511-7 ISBN 978-981-10-7512-4 (eBook), doi: 978-981-10-7512-4_61, old name: Advances in Intelligent and Soft ComputingScopus index, impact factor, pptx.

The medical image analysis for irregularity studies has always been a refreshing research topic for the need of efficient and precise diagnosis. A new method based on patch analysis for detection of disorder in images of brain is introduced with machine learning techniques. In the method a sparse nonlocal texture mean filter is proposed to evaluate the similarity of each spot in the image. The spot-based similarity allows initial identification of place of abnormality which is then refined by the support vector machines to efficiently perform extraction of disorder’s region. Experimental results on a benchmark’s real data are assessed and compared objectively to ensure sufficient certainty of the method.