Optimal Fractionation Scheduling for Radiotherapy Treatments with Reinforcement Learning, Tumor Growth Modeling and Outcome Modeling

<b>Objective:</b> Radiotherapy is a primary method for cancer treatment, wherein radiation doses are divided into multiple sessions or fractions to effectively target tumors and minimize damage to surrounding tissues. <b>Methods:</b> In this study, we leverage reinforcement l...

Full description

Saved in:
Bibliographic Details
Main Authors: Mélanie Ghislain, Florian Martin, Manon Dausort, Damien Dasnoy-Sumell, Ana Maria Barragan Montero, Benoît Macq
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Biomedicines
Subjects:
Online Access:https://www.mdpi.com/2227-9059/13/6/1367
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432161341407232
author Mélanie Ghislain
Florian Martin
Manon Dausort
Damien Dasnoy-Sumell
Ana Maria Barragan Montero
Benoît Macq
author_facet Mélanie Ghislain
Florian Martin
Manon Dausort
Damien Dasnoy-Sumell
Ana Maria Barragan Montero
Benoît Macq
author_sort Mélanie Ghislain
collection DOAJ
description <b>Objective:</b> Radiotherapy is a primary method for cancer treatment, wherein radiation doses are divided into multiple sessions or fractions to effectively target tumors and minimize damage to surrounding tissues. <b>Methods:</b> In this study, we leverage reinforcement learning (RL) to enhance treatment planning with the aim of improving the adaptability and robustness of RL agents given the inherent inaccuracies in tumor growth models. A 2D simulation model of tumor growth is employed, where tabular RL techniques are used to determine the optimal treatment strategies. We emphasize the significance of tissue damage predictions and incorporate the Lyman NTCP model to assess treatment outcomes, analyzing complications across three simulated body sites: the rectum, head and neck and lung. <b>Results:</b> For all the tumor sites, the RL approach significantly reduces healthy tissue damage by 10.7%, 49.1% and 37.5%, respectively, for rectal, head and neck and lung cancers compared with the baseline treatment. <b>Conclusions:</b> The RL-based approach in radiotherapy not only achieves tumor eradication but also significantly reduces healthy tissue damage compared with traditional treatment methods. This study demonstrates the potential of reinforcement learning to optimize treatment planning in radiotherapy, offering a promising path towards more personalized and effective cancer treatments.
format Article
id doaj-art-37f6b1ef4abc4655b9dddc27e5485575
institution Kabale University
issn 2227-9059
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Biomedicines
spelling doaj-art-37f6b1ef4abc4655b9dddc27e54855752025-08-20T03:27:26ZengMDPI AGBiomedicines2227-90592025-06-01136136710.3390/biomedicines13061367Optimal Fractionation Scheduling for Radiotherapy Treatments with Reinforcement Learning, Tumor Growth Modeling and Outcome ModelingMélanie Ghislain0Florian Martin1Manon Dausort2Damien Dasnoy-Sumell3Ana Maria Barragan Montero4Benoît Macq5Institute for Information and Communication Technologies, Electronics and Applied Mathematics (ICTEAM), UCLouvain, 1348 Louvain-La-Neuve, BelgiumInstitute for Information and Communication Technologies, Electronics and Applied Mathematics (ICTEAM), UCLouvain, 1348 Louvain-La-Neuve, BelgiumInstitute for Information and Communication Technologies, Electronics and Applied Mathematics (ICTEAM), UCLouvain, 1348 Louvain-La-Neuve, BelgiumInstitute for Information and Communication Technologies, Electronics and Applied Mathematics (ICTEAM), UCLouvain, 1348 Louvain-La-Neuve, BelgiumMolecular Imaging, Radiotherapy and Oncology Institute, UCLouvain, 1200 Woluwe-Saint-Lambert, BelgiumInstitute for Information and Communication Technologies, Electronics and Applied Mathematics (ICTEAM), UCLouvain, 1348 Louvain-La-Neuve, Belgium<b>Objective:</b> Radiotherapy is a primary method for cancer treatment, wherein radiation doses are divided into multiple sessions or fractions to effectively target tumors and minimize damage to surrounding tissues. <b>Methods:</b> In this study, we leverage reinforcement learning (RL) to enhance treatment planning with the aim of improving the adaptability and robustness of RL agents given the inherent inaccuracies in tumor growth models. A 2D simulation model of tumor growth is employed, where tabular RL techniques are used to determine the optimal treatment strategies. We emphasize the significance of tissue damage predictions and incorporate the Lyman NTCP model to assess treatment outcomes, analyzing complications across three simulated body sites: the rectum, head and neck and lung. <b>Results:</b> For all the tumor sites, the RL approach significantly reduces healthy tissue damage by 10.7%, 49.1% and 37.5%, respectively, for rectal, head and neck and lung cancers compared with the baseline treatment. <b>Conclusions:</b> The RL-based approach in radiotherapy not only achieves tumor eradication but also significantly reduces healthy tissue damage compared with traditional treatment methods. This study demonstrates the potential of reinforcement learning to optimize treatment planning in radiotherapy, offering a promising path towards more personalized and effective cancer treatments.https://www.mdpi.com/2227-9059/13/6/1367reinforcement learningradiotherapy treatment planningtumor growth simulationcancer complication
spellingShingle Mélanie Ghislain
Florian Martin
Manon Dausort
Damien Dasnoy-Sumell
Ana Maria Barragan Montero
Benoît Macq
Optimal Fractionation Scheduling for Radiotherapy Treatments with Reinforcement Learning, Tumor Growth Modeling and Outcome Modeling
Biomedicines
reinforcement learning
radiotherapy treatment planning
tumor growth simulation
cancer complication
title Optimal Fractionation Scheduling for Radiotherapy Treatments with Reinforcement Learning, Tumor Growth Modeling and Outcome Modeling
title_full Optimal Fractionation Scheduling for Radiotherapy Treatments with Reinforcement Learning, Tumor Growth Modeling and Outcome Modeling
title_fullStr Optimal Fractionation Scheduling for Radiotherapy Treatments with Reinforcement Learning, Tumor Growth Modeling and Outcome Modeling
title_full_unstemmed Optimal Fractionation Scheduling for Radiotherapy Treatments with Reinforcement Learning, Tumor Growth Modeling and Outcome Modeling
title_short Optimal Fractionation Scheduling for Radiotherapy Treatments with Reinforcement Learning, Tumor Growth Modeling and Outcome Modeling
title_sort optimal fractionation scheduling for radiotherapy treatments with reinforcement learning tumor growth modeling and outcome modeling
topic reinforcement learning
radiotherapy treatment planning
tumor growth simulation
cancer complication
url https://www.mdpi.com/2227-9059/13/6/1367
work_keys_str_mv AT melanieghislain optimalfractionationschedulingforradiotherapytreatmentswithreinforcementlearningtumorgrowthmodelingandoutcomemodeling
AT florianmartin optimalfractionationschedulingforradiotherapytreatmentswithreinforcementlearningtumorgrowthmodelingandoutcomemodeling
AT manondausort optimalfractionationschedulingforradiotherapytreatmentswithreinforcementlearningtumorgrowthmodelingandoutcomemodeling
AT damiendasnoysumell optimalfractionationschedulingforradiotherapytreatmentswithreinforcementlearningtumorgrowthmodelingandoutcomemodeling
AT anamariabarraganmontero optimalfractionationschedulingforradiotherapytreatmentswithreinforcementlearningtumorgrowthmodelingandoutcomemodeling
AT benoitmacq optimalfractionationschedulingforradiotherapytreatmentswithreinforcementlearningtumorgrowthmodelingandoutcomemodeling