Large-scale automatic carbon ion treatment planning for head and neck cancers via parallel multi-agent reinforcement learning

• URL: http://arxiv.org/abs/2511.02314v1
• Date: Tue, 04 Nov 2025 06:57:31 GMT
• Title: Large-scale automatic carbon ion treatment planning for head and neck cancers via parallel multi-agent reinforcement learning
• Authors: Jueye Zhang, Chao Yang, Youfang Lai, Kai-Wen Li, Wenting Yan, Yunzhou Xia, Haimei Zhang, Jingjing Zhou, Gen Yang, Chen Lin, Tian Li, Yibao Zhang,
• Abstract summary: Intensity-modulated carbon-ion therapy (IMCT) offers superior dose conformity and OAR sparing but remains slow due to relative biological effectiveness (RBE) modeling.<n>Recent deep learning (DL) methods are limited by data bias and plan feasibility.<n>We propose a scalable multi-agent RL (MARL) framework for parallel tuning of 45 TPPs in IMCT.
• Score: 10.599617076883613
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Head-and-neck cancer (HNC) planning is difficult because multiple critical organs-at-risk (OARs) are close to complex targets. Intensity-modulated carbon-ion therapy (IMCT) offers superior dose conformity and OAR sparing but remains slow due to relative biological effectiveness (RBE) modeling, leading to laborious, experience-based, and often suboptimal tuning of many treatment-planning parameters (TPPs). Recent deep learning (DL) methods are limited by data bias and plan feasibility, while reinforcement learning (RL) struggles to efficiently explore the exponentially large TPP search space. We propose a scalable multi-agent RL (MARL) framework for parallel tuning of 45 TPPs in IMCT. It uses a centralized-training decentralized-execution (CTDE) QMIX backbone with Double DQN, Dueling DQN, and recurrent encoding (DRQN) for stable learning in a high-dimensional, non-stationary environment. To enhance efficiency, we (1) use compact historical DVH vectors as state inputs, (2) apply a linear action-to-value transform mapping small discrete actions to uniform parameter adjustments, and (3) design an absolute, clinically informed piecewise reward aligned with plan scores. A synchronous multi-process worker system interfaces with the PHOENIX TPS for parallel optimization and accelerated data collection. On a head-and-neck dataset (10 training, 10 testing), the method tuned 45 parameters simultaneously and produced plans comparable to or better than expert manual ones (relative plan score: RL $85.93\pm7.85%$ vs Manual $85.02\pm6.92%$), with significant (p-value $<$ 0.05) improvements for five OARs. The framework efficiently explores high-dimensional TPP spaces and generates clinically competitive IMCT plans through direct TPS interaction, notably improving OAR sparing.

Related papers

• Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration [56.074760766965085]
  PRISM achieves a dynamics-aware framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge.<n>Our findings suggest that disentangling data based on internal optimization regimes is crucial for scalable and robust agent alignment.
  arXiv  Detail & Related papers  (2026-01-12T05:43:20Z)
• Lung Infection Severity Prediction Using Transformers with Conditional TransMix Augmentation and Cross-Attention [13.087848666528563]
  Lung infections, particularly pneumonia, pose serious health risks that can escalate rapidly.<n>We present a novel method applicable to both CT scans and chest X-rays for assessing lung infection severity.<n>Our contributions are twofold: (i) QCross-Att-PVT, a Transformer-based architecture that integrates parallel encoders, a cross-gated attention mechanism, and a feature aggregator, and (ii) Conditional Online TransMix, a custom data augmentation strategy.
  arXiv  Detail & Related papers  (2025-10-08T11:08:34Z)
• A learning-driven automatic planning framework for proton PBS treatments of H&N cancers [2.0765076553348316]
  Inverse parameter is a learning-to-optimize (L2O) method that predicts update steps by learning from task-specific data distributions.<n>In experiments, total 97 patients with bilateral or ipsilateral H&N cancers are collected for training and testing.
  arXiv  Detail & Related papers  (2025-08-14T21:50:31Z)
• Automated Treatment Planning for Interstitial HDR Brachytherapy for Locally Advanced Cervical Cancer using Deep Reinforcement Learning [3.9838929530763076]
  The objective of this study is to develop a fully automated HDR brachytherapy planning framework.<n>We propose a hierarchical two-stage autoplanning framework.<n>For the unseen test patients, the RL-based automated planning method achieved an average score of 93.89%, outperforming the clinical plans which averaged 91.86%.
  arXiv  Detail & Related papers  (2025-06-13T17:07:30Z)
• Patient-Specific Deep Reinforcement Learning for Automatic Replanning in Head-and-Neck Cancer Proton Therapy [8.677300387603356]
  Anatomical changes during intensity-modulated proton therapy (IMPT) for head-and-neck cancer (HNC) can shift Bragg peaks, risking tumor underdosing and organ-at-risk overdosing.<n>We propose a patient-specific deep reinforcement learning framework for automated IMPT replanning.
  arXiv  Detail & Related papers  (2025-06-11T18:00:06Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• Offline Behavior Distillation [57.6900189406964]
  Massive reinforcement learning (RL) data are typically collected to train policies offline without the need for interactions. We formulate offline behavior distillation (OBD), which synthesizes limited expert behavioral data from sub-optimal RL data. We propose two naive OBD objectives, DBC and PBC, which measure distillation performance via the decision difference between policies trained on distilled data and either offline data or a near-expert policy.
  arXiv  Detail & Related papers  (2024-10-30T06:28:09Z)
• Solving Continual Offline Reinforcement Learning with Decision Transformer [78.59473797783673]
  Continuous offline reinforcement learning (CORL) combines continuous and offline reinforcement learning. Existing methods, employing Actor-Critic structures and experience replay (ER), suffer from distribution shifts, low efficiency, and weak knowledge-sharing. We introduce multi-head DT (MH-DT) and low-rank adaptation DT (LoRA-DT) to mitigate DT's forgetting problem.
  arXiv  Detail & Related papers  (2024-01-16T16:28:32Z)
• Auto-FedRL: Federated Hyperparameter Optimization for Multi-institutional Medical Image Segmentation [48.821062916381685]
  Federated learning (FL) is a distributed machine learning technique that enables collaborative model training while avoiding explicit data sharing. In this work, we propose an efficient reinforcement learning(RL)-based federated hyperparameter optimization algorithm, termed Auto-FedRL. The effectiveness of the proposed method is validated on a heterogeneous data split of the CIFAR-10 dataset and two real-world medical image segmentation datasets.
  arXiv  Detail & Related papers  (2022-03-12T04:11:42Z)
• Adaptive Stochastic ADMM for Decentralized Reinforcement Learning in Edge Industrial IoT [106.83952081124195]
  Reinforcement learning (RL) has been widely investigated and shown to be a promising solution for decision-making and optimal control processes. We propose an adaptive ADMM (asI-ADMM) algorithm and apply it to decentralized RL with edge-computing-empowered IIoT networks. Experiment results show that our proposed algorithms outperform the state of the art in terms of communication costs and scalability, and can well adapt to complex IoT environments.
  arXiv  Detail & Related papers  (2021-06-30T16:49:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.