2026-05-13T16:59:01Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00192960 2025-01-19T23:56:23Z 934:989:9407:9598

Feature Representation Analysis of Deep Convolutional Neural Network using Two-stage Feature Transfer―An Application for Diffuse Lung Disease Classification Feature Representation Analysis of Deep Convolutional Neural Network using Two-stage Feature Transfer―An Application for Diffuse Lung Disease Classification Aiga, Suzuki Hidenori, Sakanashi Shoji, Kido Hayaru, Shouno Aiga, Suzuki Hidenori, Sakanashi Shoji, Kido Hayaru, Shouno [オリジナル論文] deep convolutional neural networks, transfer learning, image recognition, textural recognition, medical imaging 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. 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. 情報処理学会 2018-12-20 eng journal article https://ipsj.ixsq.nii.ac.jp/records/192960 1882-7780 AA11464803 情報処理学会論文誌数理モデル化と応用（TOM） 11 3 74 83 https://ipsj.ixsq.nii.ac.jp/record/192960/files/IPSJ-TOM1103008.pdf application/pdf 5.1 MB 2020-12-20