[Radiomics and automation in radiotherapy]

Area of Science:

• Oncology and Radiotherapy
• Medical Physics
• Artificial Intelligence in Healthcare

Background:

• Rising global cancer incidence and aging populations increase workload in oncology and radiotherapy.
• Shortages of skilled professionals, like medical physicists, exacerbate workload challenges.
• Patients generate vast amounts of complex data, particularly from medical imaging, requiring advanced analysis.

Purpose of the Study:

• To highlight the critical role of radiomics in automating radiotherapy workflows.
• To emphasize radiomics' contribution to personalized and individualized cancer treatment.
• To address the challenges posed by increasing data volume and limited human resources in radiotherapy.

Main Methods:

• Utilizing artificial intelligence for automated data extraction from medical images.
• Applying radiomics to analyze morphological and functional data from tumors.
• Integrating AI-driven insights into treatment planning and patient management.

Main Results:

• Demonstrated the potential of AI to handle large, complex datasets in radiotherapy.
• Showcased radiomics as a key technology for extracting previously indiscernible image information.
• Highlighted the feasibility of automating laborious data extraction processes.

Conclusions:

• Radiomics is essential for automating processes in radiotherapy, particularly for treatment planning.
• AI-driven radiomics facilitates a more personalized and individualized approach to cancer treatment.
• The integration of radiomics is vital for managing increasing workloads and data complexity in oncology.