[论文解读] An Artificial Intelligence-Driven Agent for Real-Time Head-and-Neck IMRT Plan Generation using Conditional Generative Adversarial Network (cGAN)

Xinyi Li, Yang Sheng+7 more|arXiv (Cornell University)|Sep 27, 2020

Advanced Radiotherapy Techniques参考文献 34被引用 36

一句话总结

本文提出了一种基于条件生成对抗网络（cGAN）的AI驱动代理，可在3秒内实现全自动、实时的头颈部调强放射治疗（IMRT）计划生成。通过采用新型金字塔结构生成器（PyraNet）和定制化DenseNet判别器，系统可从3D CT数据同时预测9个射野强度图，其剂量学质量与临床治疗计划系统（TPS）计划相当，关键器官剂量无显著差异。

ABSTRACT

Purpose: To develop an Artificial Intelligence (AI) agent for fully-automated rapid head and neck (H&N) IMRT plan generation without time-consuming inverse planning.$$$$ Methods: This AI agent was trained using a conditional Generative Adversarial Network architecture. The generator, PyraNet, is a novel Deep Learning network that implements 28 classic ResNet blocks in pyramid-like concatenations. The discriminator is a customized 4-layer DenseNet. The AI agent first generates customized 2D projections at 9 template beam angles from 3D CT volume and structures of a patient. These projections are then stacked as 4D inputs of PyraNet, from which 9 radiation fluence maps are generated simultaneously. Finally, the predicted fluence maps are imported into a commercial treatment planning system (TPS) for plan integrity checks. The AI agent was built and tested upon 231 oropharyngeal plans from a TPS plan library. Only the primary plans in the sequential boost regime were studied. A customized Harr wavelet loss was adopted for fluence map comparison. Isodose distributions in test AI plans and TPS plans were qualitatively evaluated. Key dosimetric metrics were statistically compared.$$$$ Results: All test AI plans were successfully generated. Isodose gradients outside of PTV in AI plans were comparable with TPS plans. After PTV coverage normalization, $D_{mean}$ of parotids and oral cavity in AI plans and TPS plans were comparable without statistical significance. AI plans achieved comparable $D_{max}$ at 0.01cc of brainstem and cord+5mm without clinically relevant differences, but body $D_{max}$ was higher than the TPS plan results. The AI agent needs ~3s per case to predict fluence maps.$$$$ Conclusions: The developed AI agent can generate H&N IMRT plans with satisfying dosimetry quality. With rapid and fully automated implementation, it holds great potential for clinical applications.

研究动机与目标

• 通过开发全自动AI驱动的计划系统，消除头颈部IMRT中耗时的逆向计划优化过程。
• 解决口咽癌序贯增量放疗方案中对快速、一致且高质量IMRT计划生成的临床需求。
• 实现实时计划生成，同时不牺牲靶区覆盖或危及器官的保护。
• 利用定量和定性剂量学指标，将AI生成的计划与临床TPS计划进行验证。

提出的方法

• 采用条件生成对抗网络（cGAN）架构，其中新型生成器网络（PyraNet）基于28个残差块（ResNet blocks）以金字塔状连接方式构建。
• 判别器为4层定制化DenseNet，用于区分真实与生成的射野强度图。
• AI代理首先从3D CT影像和结构集生成9个标准角度的2D射野投影。
• 这些2D投影被堆叠为4D输入张量，送入PyraNet以同时生成9个射野强度图。
• 采用定制化的Harr小波损失函数，以提高AI生成计划与TPS计划之间射野强度图的相似性。
• 将生成的射野强度图导入商业TPS系统进行完整性检查和剂量学评估。

实验结果

研究问题

• RQ1 AI代理能否在实时条件下生成剂量学质量与临床TPS计划相当的头颈部IMRT计划？
• RQ2 与临床计划相比，所提出的基于cGAN的方法在维持靶区覆盖和危及器官保护方面表现如何？
• RQ3 AI代理的推理速度如何？是否具备支持临床工作流程集成的能力？
• RQ4 AI生成的射野强度图在保留等剂量线梯度特性方面，与TPS计划相比程度如何？

主要发现

• 所有231例测试病例均在约3秒内成功生成，证明了实时可行性。
• AI生成计划中PTV外的等剂量线梯度在定性上与临床TPS计划相当。
• 在PTV覆盖度归一化后，AI计划与TPS计划在腮腺和口腔腔的平均剂量无统计学显著差异。
• 脑干和脊髓+5 mm处0.01 cc体积的最大剂量在AI与TPS计划间相当，无临床相关差异。
• AI计划的体最大剂量略高于TPS计划，但无临床意义。
• 采用定制化Harr小波损失显著提升了射野强度图的保真度，有助于实现一致的剂量学结果。