Scholarlink

This chapter investigates the use of a GAN-based model for private data preservation to facilitate the sharing of datasets containing medical images for research purposes. The aim of the study is to strike a balance between our two main objectives: preserving data confidentiality (data anonymization) and maintaining the efficiency of deep learning models that are trained from this anonymized data. Experimental results and evaluations show the potential of our tailored model for generating artificial data toward lung disease analysis, while competing with the current CGAN-based state-of-the-art approach.

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

Searching the Balance Between Privacy Data Preservation and Lung Disease Classification Efficiency

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Iyed Dhahri,
  • Adnane Cabani,
  • Mahmoud Melkemi,
  • Karim Hammoudi

摘要

This chapter investigates the use of a GAN-based model for private data preservation to facilitate the sharing of datasets containing medical images for research purposes. The aim of the study is to strike a balance between our two main objectives: preserving data confidentiality (data anonymization) and maintaining the efficiency of deep learning models that are trained from this anonymized data. Experimental results and evaluations show the potential of our tailored model for generating artificial data toward lung disease analysis, while competing with the current CGAN-based state-of-the-art approach.