Scholarlink

<p>This study proposes a novel pre-training method employing the 3D formula-driven supervised learning for classifying three-dimensional computed tomography (CT) images, specifically for staging <i>chronic obstructive pulmonary disease (COPD)</i>. The proposed method leverages mathematically generated 3D images as a pre-training dataset to enhance feature extraction while addressing the scarcity of labeled training data, primarily caused by ethical concerns inherent in medical imaging. This paper evaluates the effectiveness of the proposed method in two CT image classification tasks: COVID-19 classification and COPD staging. The experimental result shows that the performance of a COVID-19 classification model pre-trained using mathematically generated 3D images is competitive to the existing model pre-trained using numerous CT lung images. The result also reveals the potential of the proposed approach for COPD staging, mitigating the data scarcity issue.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Pre-training Deep Neural Networks Using 3D Formula-Driven Supervised Learning for COPD Staging

  • 期刊论文

  • 发表日期：

    2025年8月7日

查看全文
  • Yasumasa Tamura,
  • Kohei Harada,
  • Wataru Noguchi,
  • Kaoruko Shimizu,
  • Satoshi Konno,
  • Masahito Yamamoto

摘要

This study proposes a novel pre-training method employing the 3D formula-driven supervised learning for classifying three-dimensional computed tomography (CT) images, specifically for staging chronic obstructive pulmonary disease (COPD). The proposed method leverages mathematically generated 3D images as a pre-training dataset to enhance feature extraction while addressing the scarcity of labeled training data, primarily caused by ethical concerns inherent in medical imaging. This paper evaluates the effectiveness of the proposed method in two CT image classification tasks: COVID-19 classification and COPD staging. The experimental result shows that the performance of a COVID-19 classification model pre-trained using mathematically generated 3D images is competitive to the existing model pre-trained using numerous CT lung images. The result also reveals the potential of the proposed approach for COPD staging, mitigating the data scarcity issue.