Actor Critic with Experience Replay-based automatic treatment planning for prostate cancer intensity modulated radiotherapy
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929731073474560 |
|---|---|
| author | Abrar, Md Mainul Sapkota, Parvat Sprouts, Damon Jia, Xun Chi, Yujie |
| author_facet | Abrar, Md Mainul Sapkota, Parvat Sprouts, Damon Jia, Xun Chi, Yujie |
| contents | Background: Real-time treatment planning in IMRT is challenging due to complex beam interactions. AI has improved automation, but existing models require large, high-quality datasets and lack universal applicability. Deep reinforcement learning (DRL) offers a promising alternative by mimicking human trial-and-error planning.
Purpose: Develop a stochastic policy-based DRL agent for automatic treatment planning with efficient training, broad applicability, and robustness against adversarial attacks using Fast Gradient Sign Method (FGSM).
Methods: Using the Actor-Critic with Experience Replay (ACER) architecture, the agent tunes treatment planning parameters (TPPs) in inverse planning. Training is based on prostate cancer IMRT cases, using dose-volume histograms (DVHs) as input. The model is trained on a single patient case, validated on two independent cases, and tested on 300+ plans across three datasets. Plan quality is assessed using ProKnow scores, and robustness is tested against adversarial attacks.
Results: Despite training on a single case, the model generalizes well. Before ACER-based planning, the mean plan score was 6.20$\pm$1.84; after, 93.09% of cases achieved a perfect score of 9, with a mean of 8.93$\pm$0.27. The agent effectively prioritizes optimal TPP tuning and remains robust against adversarial attacks.
Conclusions: The ACER-based DRL agent enables efficient, high-quality treatment planning in prostate cancer IMRT, demonstrating strong generalizability and robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_00346 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Actor Critic with Experience Replay-based automatic treatment planning for prostate cancer intensity modulated radiotherapy Abrar, Md Mainul Sapkota, Parvat Sprouts, Damon Jia, Xun Chi, Yujie Medical Physics Artificial Intelligence Machine Learning 92C50 (Primary) 68T07 (Secondary) I.2.1; J.2; J.3 Background: Real-time treatment planning in IMRT is challenging due to complex beam interactions. AI has improved automation, but existing models require large, high-quality datasets and lack universal applicability. Deep reinforcement learning (DRL) offers a promising alternative by mimicking human trial-and-error planning. Purpose: Develop a stochastic policy-based DRL agent for automatic treatment planning with efficient training, broad applicability, and robustness against adversarial attacks using Fast Gradient Sign Method (FGSM). Methods: Using the Actor-Critic with Experience Replay (ACER) architecture, the agent tunes treatment planning parameters (TPPs) in inverse planning. Training is based on prostate cancer IMRT cases, using dose-volume histograms (DVHs) as input. The model is trained on a single patient case, validated on two independent cases, and tested on 300+ plans across three datasets. Plan quality is assessed using ProKnow scores, and robustness is tested against adversarial attacks. Results: Despite training on a single case, the model generalizes well. Before ACER-based planning, the mean plan score was 6.20$\pm$1.84; after, 93.09% of cases achieved a perfect score of 9, with a mean of 8.93$\pm$0.27. The agent effectively prioritizes optimal TPP tuning and remains robust against adversarial attacks. Conclusions: The ACER-based DRL agent enables efficient, high-quality treatment planning in prostate cancer IMRT, demonstrating strong generalizability and robustness. |
| title | Actor Critic with Experience Replay-based automatic treatment planning for prostate cancer intensity modulated radiotherapy |
| topic | Medical Physics Artificial Intelligence Machine Learning 92C50 (Primary) 68T07 (Secondary) I.2.1; J.2; J.3 |
| url | https://arxiv.org/abs/2502.00346 |