Scholarlink

<p>This is a narrative review that provides a perspective on the recent advances in deep learning (DL)-driven multimodal data integration for lung cancer. Lung cancer remains the most prevalent malignancy and the leading cause of cancer-related mortality worldwide. Despite growing awareness and therapeutic innovations, the majority of cases are diagnosed at advanced stages, resulting in persistently poor survival rates. In recent years, artificial intelligence (AI) has demonstrated transformative potential in oncology research, particularly through the integration of heterogeneous biomedical data modalities. The fusion of radiological imaging, histopathological slides, genomic and transcriptomic profiles, and electronic health records has consistently outperformed unimodal approaches by capturing complementary biological and clinical information. DL-based multimodal integration frameworks have shown promise in improving diagnostic accuracy, stratifying patients according to therapeutic response, and predicting long-term prognosis, thereby contributing to precision oncology. By leveraging the synergistic strengths of diverse data sources, multimodal AI models can enable more accurate and individualized strategies for diagnosis, treatment planning, and longitudinal disease monitoring, ultimately improving clinical outcomes for patients with lung cancer.</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

A review of deep learning-based multimodal data integration of lung cancer

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月25日

查看全文
  • Ya Qin,
  • Simin Wang,
  • Dan Wu,
  • Yanhua Fei,
  • Weiping Ding,
  • Qiong Wang,
  • Runwei Guan,
  • Xiao Liang

摘要

This is a narrative review that provides a perspective on the recent advances in deep learning (DL)-driven multimodal data integration for lung cancer. Lung cancer remains the most prevalent malignancy and the leading cause of cancer-related mortality worldwide. Despite growing awareness and therapeutic innovations, the majority of cases are diagnosed at advanced stages, resulting in persistently poor survival rates. In recent years, artificial intelligence (AI) has demonstrated transformative potential in oncology research, particularly through the integration of heterogeneous biomedical data modalities. The fusion of radiological imaging, histopathological slides, genomic and transcriptomic profiles, and electronic health records has consistently outperformed unimodal approaches by capturing complementary biological and clinical information. DL-based multimodal integration frameworks have shown promise in improving diagnostic accuracy, stratifying patients according to therapeutic response, and predicting long-term prognosis, thereby contributing to precision oncology. By leveraging the synergistic strengths of diverse data sources, multimodal AI models can enable more accurate and individualized strategies for diagnosis, treatment planning, and longitudinal disease monitoring, ultimately improving clinical outcomes for patients with lung cancer.