| Presentation | 2016-05-19 Automatic classification of breast density on CT images by using deep CNN Takuya Kano, Xiangrong Zhou, Hiromi Koyasu, Ryuziro Yokoyama, Takeshi Hara, Masayuki Matsuo, Hiroshi Fujita, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Breast density has been used as an important risk factor of breast cancer and routinely measured on 2D mammography. 3D CT images have been also expected as another image modality for breast density measurements. This research work proposed a novel method to classify a CT case directly into four categories of breast density by using an end-to-end mapping without any dependence on image segmentations. The deep convolutional neural network (CNN) was used as a core part for the classification and was trained on parameters by minimizing the classification errors to the human decisions. The processing flow of the proposed method can be described as localizing left and right breast regions on CT image firstly, and then, sampling a large number of 2D sections from the 3D breast regions for breast density classification based on the deep CNN, and making a final decision based on statistic of classification results of 2D sections. 40 CT cases from 30 to 60 years old women were used in the experiment. We used holdout validation to train and test the performance of the breast density classification, and confirmed that the breast density of 16 CT cases were classified correctly from total 20 test CT cases. In conclusion, the potential possibility of breast density classification on CT images was demonstrated. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | 3D CT images / breast region localization / breast density classification / convolutional neural network / deep learning |
| Paper # | SIP2016-5,IE2016-5,PRMU2016-5,MI2016-5 |
| Date of Issue | 2016-05-12 (SIP, IE, PRMU, MI) |
| Conference Information | |
| Committee | PRMU / IE / MI / SIP |
|---|---|
| Conference Date | 2016/5/19(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Eisaku Maeda(NTT) / Seishi Takamura(NTT) / Yoshitaka Masutani(Hiroshima City Univ.) / Osamu Houshuyama(NEC) |
| Vice Chair | Shuji Senda(NEC) / Seiichi Uchida(Kyushu Univ.) / Takayuki Hamamoto(Tokyo Univ. of Science) / Atsuro Ichigaya(NHK) / Yoshiki Kawata(Tokushima Univ.) / Yuichi Kimura(Kinki Univ.) / Makoto Nakashizuka(Chiba Inst. of Tech.) / Masahiro Okuda(Univ. of Kitakyushu) |
| Secretary | Shuji Senda(Mie Univ.) / Seiichi Uchida(DENSO IT Lab.) / Takayuki Hamamoto(NTT) / Atsuro Ichigaya(Chiba Inst. of Tech.) / Yoshiki Kawata(Aichi Inst. of Tech.) / Yuichi Kimura(Nagoya Inst. of Tech.) / Makoto Nakashizuka(NEC) / Masahiro Okuda(Ritsumeikan Univ.) |
| Assistant | Kazuaki Kondo(Kyoto Univ.) / Akisato Kimura(NTT) / Keita Takahashi(Nagoya Univ.) / Kei Kawamura(KDDI R&D Labs.) / Ryo Haraguchi(NCVC) / Yasushi Hirano(Yamaguchi Univ.) / Takamichi Miyata(Chiba Inst. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Image Engineering / Technical Committee on Medical Imaging / Technical Committee on Signal Processing |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Automatic classification of breast density on CT images by using deep CNN |
| Sub Title (in English) | |
| Keyword(1) | 3D CT images |
| Keyword(2) | breast region localization |
| Keyword(3) | breast density classification |
| Keyword(4) | convolutional neural network |
| Keyword(5) | deep learning |
| 1st Author's Name | Takuya Kano |
| 1st Author's Affiliation | Gifu University(Gifu Univ.) |
| 2nd Author's Name | Xiangrong Zhou |
| 2nd Author's Affiliation | Gifu University(Gifu Univ.) |
| 3rd Author's Name | Hiromi Koyasu |
| 3rd Author's Affiliation | Gifu University Hospital(Gifu Univ. Hosp.) |
| 4th Author's Name | Ryuziro Yokoyama |
| 4th Author's Affiliation | Gifu University(Gifu Univ.) |
| 5th Author's Name | Takeshi Hara |
| 5th Author's Affiliation | Gifu University(Gifu Univ.) |
| 6th Author's Name | Masayuki Matsuo |
| 6th Author's Affiliation | Gifu University Hospital(Gifu Univ. Hosp.) |
| 7th Author's Name | Hiroshi Fujita |
| 7th Author's Affiliation | Gifu University(Gifu Univ.) |
| Date | 2016-05-19 |
| Paper # | SIP2016-5,IE2016-5,PRMU2016-5,MI2016-5 |
| Volume (vol) | vol.116 |
| Number (no) | SIP-36,IE-37,PRMU-38,MI-39 |
| Page | pp.pp.21-25(SIP), pp.21-25(IE), pp.21-25(PRMU), pp.21-25(MI), |
| #Pages | 5 |
| Date of Issue | 2016-05-12 (SIP, IE, PRMU, MI) |