Bladder Cancer Radiation Oncology of the Future: Prognostic Modelling, Radiomics, and Treatment Planning With...

Area of Science:

• Oncology
• Medical Imaging
• Artificial Intelligence

Background:

• Radiation oncology patient care can be enhanced by machine learning (ML) and artificial intelligence (AI).
• Recent advancements in ML/AI are particularly relevant for bladder cancer treatment.

Purpose of the Study:

• To review recent ML/AI advances applicable to bladder cancer care.
• To identify potential next steps for clinical implementation of these technologies.

Main Methods:

• Review of studies applying algorithms to clinical records, pathology, and radiology data.
• Analysis of AI applications in auto-contouring and treatment plan workflows.
• Discussion of methods for improving algorithm interpretability and reliability.

Main Results:

• Algorithms can generate accurate predictive models for prognosis and clinical outcomes using diverse patient data.
• AI demonstrates utility in automating tasks like contouring and streamlining treatment planning.
• Emerging methods focus on enhancing the trustworthiness of AI tools.

Conclusions:

• ML and AI hold significant potential to advance bladder cancer care in radiation oncology.
• Further development is needed for routine clinical integration, focusing on interpretability and reliability.
• These technologies can optimize patient outcomes and treatment efficiency.