Feature Representation Analysis of Deep Convolutional Neural Network using Two-stage Feature Transfer―An Application for Diffuse Lung Disease Classification

• Item type: Trans(1)
• 公開日: 2018-12-20
• タイトル: Feature Representation Analysis of Deep Convolutional Neural Network using Two-stage Feature Transfer―An Application for Diffuse Lung Disease Classification
• タイトル / 言語: en
• タイトル: Feature Representation Analysis of Deep Convolutional Neural Network using Two-stage Feature Transfer―An Application for Diffuse Lung Disease Classification
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [オリジナル論文] deep convolutional neural networks, transfer learning, image recognition, textural recognition, medical imaging
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: National Institute of Advanced Industrial Science and Technology／University of Tsukuba
• 著者所属: National Institute of Advanced Industrial Science and Technology
• 著者所属: Yamaguchi University
• 著者所属: National Institute of Advanced Industrial Science and Technology／University of Electro-Communications
• 著者所属(英): en
• 著者所属(英): National Institute of Advanced Industrial Science and Technology / University of Tsukuba
• 著者所属(英): en
• 著者所属(英): National Institute of Advanced Industrial Science and Technology
• 著者所属(英): en
• 著者所属(英): Yamaguchi University
• 著者所属(英): en
• 著者所属(英): National Institute of Advanced Industrial Science and Technology / University of Electro-Communications
• 著者名: Aiga, Suzuki; Hidenori, Sakanashi; Shoji, Kido; Hayaru, Shouno
• 著者名(英): Aiga, Suzuki; Hidenori, Sakanashi; Shoji, Kido; Hayaru, Shouno
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Transfer learning is a machine learning technique designed to improve generalization performance by using pre-trained parameters obtained from other learning tasks. For image recognition tasks, many previous studies have reported that, when transfer learning is applied to deep neural networks, performance improves, despite having limited training data. This paper proposes a two-stage feature transfer learning method focusing on the recognition of textural medical images. During the proposed method, a model is successively trained with massive amounts of natural images, some textural images, and the target images. We applied this method to the classification task of textural X-ray computed tomography images of diffuse lung diseases. In our experiment, the two-stage feature transfer achieves the best performance compared to a from-scratch learning and a conventional single-stage feature transfer. We also investigated the robustness of the target dataset, based on size. Two-stage feature transfer shows better robustness than the other two learning methods. Moreover, we analyzed the feature representations obtained from DLDs imagery inputs for each feature transfer models using a visualization method. We showed that the two-stage feature transfer obtains both edge and textural features of DLDs, which does not occur in conventional single-stage feature transfer models.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Transfer learning is a machine learning technique designed to improve generalization performance by using pre-trained parameters obtained from other learning tasks. For image recognition tasks, many previous studies have reported that, when transfer learning is applied to deep neural networks, performance improves, despite having limited training data. This paper proposes a two-stage feature transfer learning method focusing on the recognition of textural medical images. During the proposed method, a model is successively trained with massive amounts of natural images, some textural images, and the target images. We applied this method to the classification task of textural X-ray computed tomography images of diffuse lung diseases. In our experiment, the two-stage feature transfer achieves the best performance compared to a from-scratch learning and a conventional single-stage feature transfer. We also investigated the robustness of the target dataset, based on size. Two-stage feature transfer shows better robustness than the other two learning methods. Moreover, we analyzed the feature representations obtained from DLDs imagery inputs for each feature transfer models using a visualization method. We showed that the two-stage feature transfer obtains both edge and textural features of DLDs, which does not occur in conventional single-stage feature transfer models.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11464803
• 書誌情報: 情報処理学会論文誌数理モデル化と応用（TOM）; 巻 11, 号 3, p. 74-83, 発行日 2018-12-20
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7780
• 出版者 / 言語: ja
• 出版者: 情報処理学会