Publication detail

Automatic 3D Segmentation of Human Brain Images Using Data-mining Techniques

UHER, V. BURGET, R.

Original Title

Automatic 3D Segmentation of Human Brain Images Using Data-mining Techniques

English Title

Automatic 3D Segmentation of Human Brain Images Using Data-mining Techniques

Type

conference paper

Language

en

Original Abstract

This paper proposes a method for automatic 3D segmentation of human brain CT scans using data mining techniques. The brain scans are processed in 2D and 3D. The proposed method has several steps – image pre-processing, segmentation, feature extraction from segments, data mining, and post-processing. The method introduced is implemented in 3D image processing extension for the RapidMiner platform, and both are provided as open source. With testing data the resultant performance selection of tissue slices from the brain image was 98.08% when compared to human expert results.

English abstract

This paper proposes a method for automatic 3D segmentation of human brain CT scans using data mining techniques. The brain scans are processed in 2D and 3D. The proposed method has several steps – image pre-processing, segmentation, feature extraction from segments, data mining, and post-processing. The method introduced is implemented in 3D image processing extension for the RapidMiner platform, and both are provided as open source. With testing data the resultant performance selection of tissue slices from the brain image was 98.08% when compared to human expert results.

Keywords

Image processing, 3D segmentation, visualization, CT, brain scan, RapidMiner, open source, data mining

RIV year

2012

Released

04.07.2012

ISBN

978-1-4673-1118-2

Book

Proceedings of the 35th International Conference on Telecommunications and Signal Processing - TSP'2012

Edition

1

Edition number

1

Pages from

578

Pages to

580

Pages count

3

Documents

BibTex


@inproceedings{BUT93237,
  author="Václav {Uher} and Radim {Burget}",
  title="Automatic 3D Segmentation of Human Brain Images Using Data-mining Techniques",
  annote="This paper proposes a method for automatic 3D segmentation of human brain CT scans using data mining techniques. The brain scans are processed in 2D and 3D. The proposed method has several steps – image pre-processing, segmentation, feature extraction from segments, data mining, and post-processing. The method introduced is implemented in 3D image processing extension for the RapidMiner platform, and both are provided as open source. With testing data the resultant performance selection of tissue slices from the brain image was 98.08% when compared to human expert results.",
  booktitle="Proceedings of the 35th International Conference on Telecommunications and Signal Processing - TSP'2012",
  chapter="93237",
  edition="1",
  howpublished="online",
  year="2012",
  month="july",
  pages="578--580",
  type="conference paper"
}