Presentation | 2020-01-29 [Poster Presentation] Computerized Determination Method for Histological Classification of Breast Masses on Ultrasonographic Images Using CNN Features and Morphological Features Shinya Kunieda, Akiyoshi Hizukuri, Ryohei Nakayama, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The purpose of this study was to develop a computerized determination method for histological classifications of masses on breast ultrasonographic images using CNN (Convolutional Neural Network) features and morphologic features in order to assist clinicians in determining a treatment plan. Our database consisted of 585 breast ultrasonographic images obtained from 585 patients. In our proposed method, 1,024 CNN features and eight morphologic features were first determined from a mass. An SVM (Support Vector Machine) with those features was employed to classify among histological classifications of masses. Three-fold cross validation method was used for training and testing the SVM. The classification accuracies of the proposed method were 85.8% (187/218) for invasive carcinomas, 77.1% (54/70) for noninvasive carcinomas, 83.5% (152/182) for fibroadenomas, and 85.2% (98/115) for cysts, respectively. The proposed method yielding high classification accuracies would be useful in the differential diagnosis of masses on breast ultrasonographic images as diagnosis aid. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Histological Classification / Convolutional Neural Network / Mass / Ultrasonographic Image |
Paper # | MI2019-76 |
Date of Issue | 2020-01-22 (MI) |
Conference Information | |
Committee | MI |
---|---|
Conference Date | 2020/1/29(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | OKINAWAKEN SEINENKAIKAN |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Medical Image Engineering, Analysis, Recognition, etc. |
Chair | Yoshiki Kawata(Tokushima Univ.) |
Vice Chair | Takayuki Kitasaka(Aichi Inst. of Tech.) / Hidekata Hontani(Nagoya Inst. of Tech.) |
Secretary | Takayuki Kitasaka(Yamaguchi Univ.) / Hidekata Hontani(Univ. of Hyogo) |
Assistant | Hotaka Takizawa(Tsukuba Univ.) / Yoshito Otake(NAIST) |
Paper Information | |
Registration To | Technical Committee on Medical Imaging |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Poster Presentation] Computerized Determination Method for Histological Classification of Breast Masses on Ultrasonographic Images Using CNN Features and Morphological Features |
Sub Title (in English) | |
Keyword(1) | Histological Classification |
Keyword(2) | Convolutional Neural Network |
Keyword(3) | Mass |
Keyword(4) | Ultrasonographic Image |
1st Author's Name | Shinya Kunieda |
1st Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
2nd Author's Name | Akiyoshi Hizukuri |
2nd Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
3rd Author's Name | Ryohei Nakayama |
3rd Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
Date | 2020-01-29 |
Paper # | MI2019-76 |
Volume (vol) | vol.119 |
Number (no) | MI-399 |
Page | pp.pp.53-55(MI), |
#Pages | 3 |
Date of Issue | 2020-01-22 (MI) |