Multimodal deep learning approaches for precision oncology: a comprehensive review
2025

Multimodal Deep Learning Approaches for Precision Oncology

Sample size: 651 publication Evidence: high

Author Information

Author(s): Huan Yang, Minglei Yang, Jiani Chen, Guocong Yao, Quan Zou, Linpei Jia

Primary Institution: Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China

Conclusion

This review highlights the potential of multimodal deep learning to enhance precision oncology by integrating diverse data sources for improved cancer diagnosis, treatment, and prognosis.

Supporting Evidence

  • Multimodal deep learning has been identified as a cornerstone of precision oncology.
  • 651 articles were reviewed to assess the applications of multimodal deep learning in cancer research.
  • Key applications include tumor segmentation, detection, diagnosis, prognosis, treatment selection, and therapy response monitoring.

Takeaway

This study looks at how combining different types of medical data can help doctors better understand and treat cancer.

Methodology

The review synthesizes findings from 651 articles on multimodal deep learning applications in oncology, discussing data integration techniques and their clinical implications.

Limitations

The review notes challenges such as data incompleteness, high dimensionality, and the need for effective fusion methods.

Digital Object Identifier (DOI)

10.1093/bib/bbae699

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication