Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Human-Centric Intelligent Treatment Planning for Radiation Therapy

Adnan Jafar, Xun Jia

TL;DR

The complexity of treatment planning is explored and Human-Centric Intelligent Treatment Planning (HCITP), an AI-driven framework under human oversight, which integrates clinical guidelines, automates plan generation, and enables direct interactions with operators is introduced.

Abstract

Current radiation therapy treatment planning is limited by suboptimal plan quality, inefficiency, and high costs. This perspective paper explores the complexity of treatment planning and introduces Human-Centric Intelligent Treatment Planning (HCITP), an AI-driven framework under human oversight, which integrates clinical guidelines, automates plan generation, and enables direct interactions with operators. We expect that HCITP will enhance efficiency, potentially reducing planning time to minutes, and will deliver personalized, high-quality plans. Challenges and potential solutions are discussed.

Towards Human-Centric Intelligent Treatment Planning for Radiation Therapy

TL;DR

The complexity of treatment planning is explored and Human-Centric Intelligent Treatment Planning (HCITP), an AI-driven framework under human oversight, which integrates clinical guidelines, automates plan generation, and enables direct interactions with operators is introduced.

Abstract

Current radiation therapy treatment planning is limited by suboptimal plan quality, inefficiency, and high costs. This perspective paper explores the complexity of treatment planning and introduces Human-Centric Intelligent Treatment Planning (HCITP), an AI-driven framework under human oversight, which integrates clinical guidelines, automates plan generation, and enables direct interactions with operators. We expect that HCITP will enhance efficiency, potentially reducing planning time to minutes, and will deliver personalized, high-quality plans. Challenges and potential solutions are discussed.
Paper Structure (15 sections, 3 figures, 1 table)

This paper contains 15 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Current Treatment Planning Practice and its Limitations
  3. Existing Efforts using AI to Advance Treatment Planning
  4. Human-Centric Intelligent Treatment Planning
  5. Considerations on Human-Centric Intelligent Treatment Planning
  6. Conclusion
  7. Acknowledgements
  8. Author Contributions
  9. Competing Interests
  10. Figure Legends
  11. Table Legend

Figures (3)

  • Figure 1: Relationship between control parameters, LINAC, and dose distribution in RT. A set of control parameters is input to the LINAC to control its motion and beam properties, generating a carefully sculpted dose distribution conformal to the target, while sparing doses to nearby organs. The treatment planning process refers to determining the LINAC control parameters for the patient-specific anatomy to yield a clinically acceptable dose distribution.
  • Figure 2: Current treatment planning workflow. After a physician defines a prescription, a planner repeatedly interacts with the TPS to define the objectives, which typically include adequate tumor coverage and maintaining normal tissue doses within tolerance levels. This interaction guides the TPS towards a solution that best meets these objectives while respecting the physical constraints of the LINAC, such as mechanical motion limits. The planner then discusses with plan evaluator about plan quality. This workflow causes several issues affecting treatment outcomes.
  • Figure 3: New treatment planning workflow enabled by HCITP. Under the guidance of the Evaluation Module, the Execution Module autonomously operates the TPS to generate a plan. Human evaluator reviews the plan and provides feedback though the Conversation Module.