Scholarlink

<p>In medical image classification, traditional convolutional neural networks often struggle to capture key lesion information effectively and typically have a large number of parameters. Existing medical classification models are typically designed for specific diseases, resulting in poor generalization. To address this issue, we propose a generalized medical image classification model based on U-Net. By integrating the Laplace module, Cross-Skip connection structure, and Inception module, the model enhances the joint modeling of local details and global semantics, significantly improving classification performance and generalization ability. Experimental results indicate that the model exhibits excellent classification performance on the MedMNIST and BreaKHis datasets, achieving an approximately 3% improvement over existing state-of-the-art methods.</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

LUF-Net:A U-Net Based Medical Classification Model

  • 期刊论文

  • 发表日期：

    2025年9月5日

查看全文
  • Yu Wang,
  • Haoji Wang,
  • ZhiLin Liu

摘要

In medical image classification, traditional convolutional neural networks often struggle to capture key lesion information effectively and typically have a large number of parameters. Existing medical classification models are typically designed for specific diseases, resulting in poor generalization. To address this issue, we propose a generalized medical image classification model based on U-Net. By integrating the Laplace module, Cross-Skip connection structure, and Inception module, the model enhances the joint modeling of local details and global semantics, significantly improving classification performance and generalization ability. Experimental results indicate that the model exhibits excellent classification performance on the MedMNIST and BreaKHis datasets, achieving an approximately 3% improvement over existing state-of-the-art methods.