| Presentation | 2015-03-16 Feature Analysis for Diffuse Lung Disease with Deep Convolutional Neural Network Satoshi SUZUKI, Hayaru SHOUNO, Shoji KIDO, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The computer aided diagnosis (CAD) system is desired to develop for supporing physicians to diagnose the diffuse lung diseeases (DLD). In order to devlop the system, we a DLD feature analysis method with deep convolutional neural network (DCNN) for the classification of DLDs. DCNN is a kind of multi layer neural network which can automatically extract features express the input data, however, it requires larage amount of training data. In the field of medical image analysis, the number of acquired data sometimes too few to train the learning system. Thus, we introduce a kind of semi-supervised learning (SSL) method to train the DCNN, that is we apply natural image, which we can easily collect in massive, for the unlabeled data, and the small number of the DLD image as the labeled data. We compare DCNNs with training of i) DLD CT images only, ii) natural images only, and iii) DLC CT images + natural images, and show the result of case iii) would be better DCNN feature rather than those of others. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep Convolutional Neural Network / Semi-supervised Learning / Diffuse Lung Disease image analysis |
| Paper # | MBE2014-163,NC2014-114 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2015/3/9(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 | Neurocomputing (NC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Feature Analysis for Diffuse Lung Disease with Deep Convolutional Neural Network |
| Sub Title (in English) | |
| Keyword(1) | Deep Convolutional Neural Network |
| Keyword(2) | Semi-supervised Learning |
| Keyword(3) | Diffuse Lung Disease image analysis |
| 1st Author's Name | Satoshi SUZUKI |
| 1st Author's Affiliation | Deapartment of Informatics and Engineering, University of Electro-Communications() |
| 2nd Author's Name | Hayaru SHOUNO |
| 2nd Author's Affiliation | Graduate School of Informatics and Engineering, University of Electro-Communications |
| 3rd Author's Name | Shoji KIDO |
| 3rd Author's Affiliation | Applied Medical Engineering Science, Graduate School of Medicine, Yamaguchi University |
| Date | 2015-03-16 |
| Paper # | MBE2014-163,NC2014-114 |
| Volume (vol) | vol.114 |
| Number (no) | 515 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |