Scholarlink

As diseases spread, more pressure is placed on the healthcare system. This causes significant societal challenges, including delayed diagnoses, higher costs, and unequal access to treatments. Traditional diagnostic methods are often inadequate for detecting multiple diseases simultaneously. Deep learning (DL) in medical imaging offers a comprehensive and timely solution. This review explores advancements in DL, including convolutional neural networks (CNNs), transformers, and generative adversarial networks (GANs), and highlights the potential of transfer learning and multi-modal learning to address current challenges. Furthermore, it discusses the challenges facing DL in multi-disease detection and proposes future directions for more effective and efficient diagnostic procedures.

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

Advancements in Deep Learning for Multi-disease Detection in Medical Imaging

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Fatima El Addouni,
  • Karam Ahkouk,
  • Hafsa El Aaoud,
  • Hicham El Moubtahij

摘要

As diseases spread, more pressure is placed on the healthcare system. This causes significant societal challenges, including delayed diagnoses, higher costs, and unequal access to treatments. Traditional diagnostic methods are often inadequate for detecting multiple diseases simultaneously. Deep learning (DL) in medical imaging offers a comprehensive and timely solution. This review explores advancements in DL, including convolutional neural networks (CNNs), transformers, and generative adversarial networks (GANs), and highlights the potential of transfer learning and multi-modal learning to address current challenges. Furthermore, it discusses the challenges facing DL in multi-disease detection and proposes future directions for more effective and efficient diagnostic procedures.