# New Insights into Automatic Treatment Planning for Cancer Radiotherapy Using Explainable Artificial Intelligence

arXiv: https://arxiv.org/abs/2508.14229 · HTML: https://mlsanity.com/paper/2508.14229/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Builds on (most cited first, 10 of 10)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Recurrent Q-Learning for Partially Observable MDPs](https://mlsanity.com/paper/1507.06527/) (2015)
- [Superhuman Artificial Intelligence Can Improve Human Decision Making by Increasing Novelty](https://mlsanity.com/paper/2303.07462/) (2023)
- [Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks](https://mlsanity.com/paper/2410.02331/) (2024)
- [TorchEsegeta: Framework for Interpretability and Explainability of Image-based Deep Learning Models](https://mlsanity.com/paper/2110.08429/) (2021)
- [Actor Critic with Experience Replay-based automatic treatment planning for prostate cancer intensity modulated radiotherapy](https://mlsanity.com/paper/2502.00346/) (2025)
- [Patient-Specific Deep Reinforcement Learning for Automatic Replanning in Head-and-Neck Cancer Proton Therapy](https://mlsanity.com/paper/2506.10073/) (2025)
- [Robust Recurrent Reinforcement Learning under Evolving Hidden Disturbances with Application to Rover Wheel Slip](https://mlsanity.com/paper/2307.15931/) (2023)
- [Guidelines For The Choice Of The Baseline in XAI Attribution Methods](https://mlsanity.com/paper/2503.19813/) (2025)

## Built on by (most cited first, 1 of 1)

- [A Machine-to-Machine Knowledge-Guided LLM Agent for Generalizable Radiotherapy Treatment Planning](https://mlsanity.com/paper/2606.00922/) (2026)

## Abstract (arXiv)

Objective: This study aims to uncover the opaque decision-making process of an artificial intelligence (AI) agent for automatic treatment planning. Approach: We examined a previously developed AI agent based on the Actor-Critic with Experience Replay (ACER) network, which automatically tunes treatment planning parameters (TPPs) for inverse planning in prostate cancer intensity modulated radiotherapy. We selected multiple checkpoint ACER agents from different stages of training and applied an explainable AI (EXAI) method to analyze the attribution from dose-volume histogram (DVH) inputs to TPP-tuning decisions. We then assessed each agent's planning efficacy and efficiency and evaluated their policy and final TPP tuning spaces. Combining these analyses, we systematically examined how ACER agents generated high-quality treatment plans in response to different DVH inputs. Results: Attribution analysis revealed that ACER agents progressively learned to identify dose-violation regions from DVH inputs and promote appropriate TPP-tuning actions to mitigate them. Organ-wise similarities between DVH attributions and dose-violation reductions ranged from 0.25 to 0.5 across tested agents. Agents with stronger attribution-violation similarity required fewer tuning steps (~12-13 vs. 22), exhibited a more concentrated TPP-tuning space with lower entropy (~0.3 vs. 0.6), converged on adjusting only a few TPPs, and showed smaller discrepancies between practical and theoretical tuning steps. Putting together, these findings indicate that high-performing ACER agents can effectively identify dose violations from DVH inputs and employ a global tuning strategy to achieve high-quality treatment planning, much like skilled human planners. Significance: Better interpretability of the agent's decision-making process may enhance clinician trust and inspire new strategies for automatic treatment planning.