Transforming Multimodal Models into Action Models for Radiotherapy

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ferrante, Matteo, Carosi, Alessandra, Angelillo, Rolando Maria D, Toschi, Nicola
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913682710069248
author Ferrante, Matteo
Carosi, Alessandra
Angelillo, Rolando Maria D
Toschi, Nicola
author_facet Ferrante, Matteo
Carosi, Alessandra
Angelillo, Rolando Maria D
Toschi, Nicola
contents Radiotherapy is a crucial cancer treatment that demands precise planning to balance tumor eradication and preservation of healthy tissue. Traditional treatment planning (TP) is iterative, time-consuming, and reliant on human expertise, which can potentially introduce variability and inefficiency. We propose a novel framework to transform a large multimodal foundation model (MLM) into an action model for TP using a few-shot reinforcement learning (RL) approach. Our method leverages the MLM's extensive pre-existing knowledge of physics, radiation, and anatomy, enhancing it through a few-shot learning process. This allows the model to iteratively improve treatment plans using a Monte Carlo simulator. Our results demonstrate that this method outperforms conventional RL-based approaches in both quality and efficiency, achieving higher reward scores and more optimal dose distributions in simulations on prostate cancer data. This proof-of-concept suggests a promising direction for integrating advanced AI models into clinical workflows, potentially enhancing the speed, quality, and standardization of radiotherapy treatment planning.
format Preprint
id arxiv_https___arxiv_org_abs_2502_04408
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transforming Multimodal Models into Action Models for Radiotherapy
Ferrante, Matteo
Carosi, Alessandra
Angelillo, Rolando Maria D
Toschi, Nicola
Machine Learning
Artificial Intelligence
Radiotherapy is a crucial cancer treatment that demands precise planning to balance tumor eradication and preservation of healthy tissue. Traditional treatment planning (TP) is iterative, time-consuming, and reliant on human expertise, which can potentially introduce variability and inefficiency. We propose a novel framework to transform a large multimodal foundation model (MLM) into an action model for TP using a few-shot reinforcement learning (RL) approach. Our method leverages the MLM's extensive pre-existing knowledge of physics, radiation, and anatomy, enhancing it through a few-shot learning process. This allows the model to iteratively improve treatment plans using a Monte Carlo simulator. Our results demonstrate that this method outperforms conventional RL-based approaches in both quality and efficiency, achieving higher reward scores and more optimal dose distributions in simulations on prostate cancer data. This proof-of-concept suggests a promising direction for integrating advanced AI models into clinical workflows, potentially enhancing the speed, quality, and standardization of radiotherapy treatment planning.
title Transforming Multimodal Models into Action Models for Radiotherapy
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2502.04408