Presentation | 2015-03-02 Image Feature Extraction and Construction of a Classifier for Discriminating Pulmonary Nodules in X-CT Images Ryuta MORI, Takumi NAITO, Hidekata HONTANI, Shingo IWANO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this article, the authors report about a method for classifying pulmonary nodules in three-dimensional X-CT images and about image features used for the classification. The classification method firstly segments the nodules in given three-dimensional X-CT images and then extracts nine kinds of image features that are represented by a fifty-one vector, which is input to the classifier. Given 309 training images of pulmonary nodules with five-grade evaluations, the authors constructed the classifier using a kernel SVM. Its classification ratio was about 75%. The F-score of each of the image features was evaluated and was used for selecting ons that contributed the classification well. In this article, it is reported that which images features contributed to the classification and that how the classification performance changed with respect to the change of the number of the input image features. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Computed Aided Diagnosis / CT images / lung nodules / classification / SVM |
Paper # | MI2014-61 |
Date of Issue |
Conference Information | |
Committee | MI |
---|---|
Conference Date | 2015/2/23(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Medical Imaging (MI) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Image Feature Extraction and Construction of a Classifier for Discriminating Pulmonary Nodules in X-CT Images |
Sub Title (in English) | |
Keyword(1) | Computed Aided Diagnosis |
Keyword(2) | CT images |
Keyword(3) | lung nodules |
Keyword(4) | classification |
Keyword(5) | SVM |
1st Author's Name | Ryuta MORI |
1st Author's Affiliation | Nagoya Institute of Technology() |
2nd Author's Name | Takumi NAITO |
2nd Author's Affiliation | Nagoya Institute of Technology |
3rd Author's Name | Hidekata HONTANI |
3rd Author's Affiliation | Nagoya Institute of Technology |
4th Author's Name | Shingo IWANO |
4th Author's Affiliation | Graduate School of Medicine, Nagoya University |
Date | 2015-03-02 |
Paper # | MI2014-61 |
Volume (vol) | vol.114 |
Number (no) | 482 |
Page | pp.pp.- |
#Pages | 4 |
Date of Issue |