Back to all papers

Progress in the Application of Artificial Intelligence in Radiotherapy: From Image Guidance to Adaptive Radiation Therapy.

November 18, 2026pubmed logopapers

Authors

Li J,Su H,Chen C

Affiliations (4)

  • Department of Tumor Radiotherapy and Chemotherapy, The First Affiliated Hospital, Wenzhou Medical University, Wenzhou, China.
  • Department of Tumor Radiotherapy and Chemotherapy, The First Affiliated Hospital, Wenzhou Medical University, Wenzhou, China. [email protected].
  • Department of Tumor Radiotherapy and Chemotherapy, The First Affiliated Hospital, Wenzhou Medical University, Wenzhou, China. [email protected].
  • Zhejiang Key Laboratory of Intelligent Cancer Biomarker Discovery and Translation, The First Affiliated Hospital, Wenzhou Medical University, Wenzhou, China. [email protected].

Abstract

Radiotherapy plays a crucial role in cancer management, integral to curative approaches for 45%-50% of malignancies. However, conventional workflows face significant challenges, including operational inefficiency, inter-observer variability, and limited personalization. This review describes the evolutionary trajectory of artificial intelligence (AI) applications within the domain of radiotherapy, with a principal focus on the cardinal paradigm shift from image-guided radiotherapy (IGRT) toward adaptive radiotherapy (ART). AI has demonstrably improved both the precision and efficiency of radiotherapy. This stems from its application across several critical areas: automating complex tasks in medical image analysis-like segmenting tumors, enhancing real-time motion management with the ability to capture target displacements down to the submillimeter level; and providing sophisticated decision support systems to aid clinicians. Within the sphere of ART, online adaptive systems leveraging magnetic resonance linear accelerators (MR-Linacs) and cone-beam computed tomography (CBCT) facilitate dynamic target delineation, dosimetric re-optimization, and cumulative dose assessment. These capabilities forge a closed-loop system based on "perception-decision-execution," effectively shifting radiotherapy beyond static planning and -toward truly personalized, dynamic treatments.

Topics

Radiotherapy, Image-GuidedArtificial IntelligenceRadiotherapy Planning, Computer-AssistedNeoplasmsJournal ArticleReview

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAISlice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.