一覧に戻る

タイトル
  • en Diagnosis of Breast Cancer from Mammogram Images Based on CNN
作成者
    • en Dong, Lin
    • 所属 ja 九州大学大学院芸術工学府コミュニケーションデザイン科学部門 en Department of Communication Design Science, Kyushu University
    • ja 井上，光平 en Inoue, Kohei ja-Kana イノウエ, コウヘイ
    • 所属 ja 九州大学大学院芸術工学研究院コミュニケーションデザイン科学部門 : 准教授 en Department of Communication Design Science, Kyushu University : Associate Professor
アクセス権 open access
権利情報
主題
  • Other en Mammography
  • Other en Convolutional Neural Networks
  • Other en Transfer Learning
  • Other en Image Classification
  • Other en Data Augmentation
内容注記
  • Abstract en Breast cancer has become the most common malignant tumor with the highest incidence of death in women. The MIBCAD (Medical Image Based Computer-Aided Diagnosis) system currently in use has a low diagnostic accuracy rate of only 85%. Furthermore, this system has major limitations for image processing of mammogram. To address these issues, this paper proposed a breast cancer diagnosis method based on an improved CNN (Convolutional Neural Networks). To avoid the image overfitting problem, transfer learning and data augmentation methods were used. The image classification accuracy was improved by using different CNN structures and changing the classifier type. Our results showed that the classification accuracy of the model reached 91.4%, which was significantly improved compared with the existing MIBCAD system.
出版者 en The Institute of Industrial Applications Engineers en IIAE ja 産業応用工学会
日付
    Issued2020-10-25
言語
  • eng
資源タイプ journal article
出版タイプ VoR
資源識別子 HDL https://hdl.handle.net/2324/4113193
関連
  • isIdenticalTo DOI https://doi.org/10.12792/jiiae.8.117
収録誌情報
    • EISSN 2187-8811
    • PISSN 2188-1758
      • en Journal of the Institute of Industrial Applications Engineers
      • 巻8 号4 開始ページ117 終了ページ121
ファイル
    • 4113193.pdf
    • 754KB (application/pdf)
      • Available2020-12-03
コンテンツ更新日時 2023-12-20