Automated Treatment Planning for Interstitial HDR Brachytherapy for Locally Advanced Cervical Cancer using Deep Reinforcement Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913892537466880 |
|---|---|
| author | Moradi, Mohammadamin Jiang, Runyu Liu, Yingzi Madondo, Malvern Wu, Tianming Sohn, James J. Yang, Xiaofeng Hasan, Yasmin Tian, Zhen |
| author_facet | Moradi, Mohammadamin Jiang, Runyu Liu, Yingzi Madondo, Malvern Wu, Tianming Sohn, James J. Yang, Xiaofeng Hasan, Yasmin Tian, Zhen |
| contents | High-dose-rate (HDR) brachytherapy plays a critical role in the treatment of locally advanced cervical cancer but remains highly dependent on manual treatment planning expertise. The objective of this study is to develop a fully automated HDR brachytherapy planning framework that integrates reinforcement learning (RL) and dose-based optimization to generate clinically acceptable treatment plans with improved consistency and efficiency. We propose a hierarchical two-stage autoplanning framework. In the first stage, a deep Q-network (DQN)-based RL agent iteratively selects treatment planning parameters (TPPs), which control the trade-offs between target coverage and organ-at-risk (OAR) sparing. The agent's state representation includes both dose-volume histogram (DVH) metrics and current TPP values, while its reward function incorporates clinical dose objectives and safety constraints, including D90, V150, V200 for targets, and D2cc for all relevant OARs (bladder, rectum, sigmoid, small bowel, and large bowel). In the second stage, a customized Adam-based optimizer computes the corresponding dwell time distribution for the selected TPPs using a clinically informed loss function. The framework was evaluated on a cohort of patients with complex applicator geometries. The proposed framework successfully learned clinically meaningful TPP adjustments across diverse patient anatomies. 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%. These findings are notable given that score improvements were achieved while maintaining full target coverage and reducing CTV hot spots in most cases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_11957 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Automated Treatment Planning for Interstitial HDR Brachytherapy for Locally Advanced Cervical Cancer using Deep Reinforcement Learning Moradi, Mohammadamin Jiang, Runyu Liu, Yingzi Madondo, Malvern Wu, Tianming Sohn, James J. Yang, Xiaofeng Hasan, Yasmin Tian, Zhen Medical Physics Machine Learning High-dose-rate (HDR) brachytherapy plays a critical role in the treatment of locally advanced cervical cancer but remains highly dependent on manual treatment planning expertise. The objective of this study is to develop a fully automated HDR brachytherapy planning framework that integrates reinforcement learning (RL) and dose-based optimization to generate clinically acceptable treatment plans with improved consistency and efficiency. We propose a hierarchical two-stage autoplanning framework. In the first stage, a deep Q-network (DQN)-based RL agent iteratively selects treatment planning parameters (TPPs), which control the trade-offs between target coverage and organ-at-risk (OAR) sparing. The agent's state representation includes both dose-volume histogram (DVH) metrics and current TPP values, while its reward function incorporates clinical dose objectives and safety constraints, including D90, V150, V200 for targets, and D2cc for all relevant OARs (bladder, rectum, sigmoid, small bowel, and large bowel). In the second stage, a customized Adam-based optimizer computes the corresponding dwell time distribution for the selected TPPs using a clinically informed loss function. The framework was evaluated on a cohort of patients with complex applicator geometries. The proposed framework successfully learned clinically meaningful TPP adjustments across diverse patient anatomies. 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%. These findings are notable given that score improvements were achieved while maintaining full target coverage and reducing CTV hot spots in most cases. |
| title | Automated Treatment Planning for Interstitial HDR Brachytherapy for Locally Advanced Cervical Cancer using Deep Reinforcement Learning |
| topic | Medical Physics Machine Learning |
| url | https://arxiv.org/abs/2506.11957 |