用于头颈癌 MRI 引导自适应放疗中纵向大体肿瘤体积分割的深度学习
Deep Learning for Longitudinal Gross Tumor Volume Segmentation in MRI-Guided Adaptive Radiotherapy for Head and Neck Cancer
AI总结：
本文提出基于 SegResNet 的纵向 GTV 分割模型集合，结合混合数据训练与掩膜感知注意力，在头颈癌 MRgART 放疗前和放疗中分割任务中取得优异成绩并获得第一。
摘要：
准确分割大体肿瘤体积（GTV）对于头颈癌有效的 MRI 引导自适应放疗（MRgART）至关重要。然而，在治疗过程中手动分割 GTV 既耗时，又容易受到观察者间差异的影响。深度学习（DL）有潜力通过自动勾画 GTV 来克服这些挑战。在本研究中，我们的团队 UW LAIR 同时应对放疗前（pre-RT）（任务 1）和放疗中（mid-RT）（任务 2）肿瘤体积分割的挑战。为此，我们开发了一系列用于纵向 GTV 分割的 DL 模型。两个任务中模型的主干均为带有深度监督的 SegResNet。对于任务 1，我们使用 pre-RT 与 mid-RT MRI 数据组成的混合数据集训练模型；与仅使用 pre-RT MRI 数据训练的模型相比，这使内部测试集上的聚合 Dice 相似系数（DSCagg）得到改善。在任务 2 中，我们引入了掩膜感知注意力模块，使 pre-RT GTV 掩膜能够影响从 mid-RT 数据学习到的中间特征。与将 mid-RT MRI 和 pre-RT GTV 掩膜拼接作为输入的基线方法相比，这种基于注意力的方法带来了轻微提升。在最终测试阶段，由 10 个 pre-RT 分割模型组成的集成在任务 1 中取得 0.794 的平均 DSCagg，其中原发 GTV（GTVp）为 0.745，转移淋巴结（GTVn）为 0.844。对于任务 2，由 10 个 mid-RT 分割模型组成的集成取得 0.733 的平均 DSCagg，其中 GTVp 为 0.607，GTVn 为 0.859，使我们获得第一名。总之，我们提出了一组 DL 模型，可促进 MRgART 中的 GTV 分割，并有可能简化放射肿瘤学工作流程。我们的代码和模型权重可在 https://github.com/xtie97/HNTS-MRG24-UWLAIR 获取。
英文摘要：
Accurate segmentation of gross tumor volume (GTV) is essential for effective MRI-guided adaptive radiotherapy (MRgART) in head and neck cancer. However, manual segmentation of the GTV over the course of therapy is time-consuming and prone to interobserver variability. Deep learning (DL) has the potential to overcome these challenges by automatically delineating GTVs. In this study, our team, $\textit{UW LAIR}$, tackled the challenges of both pre-radiotherapy (pre-RT) (Task 1) and mid-radiotherapy (mid-RT) (Task 2) tumor volume segmentation. To this end, we developed a series of DL models for longitudinal GTV segmentation. The backbone of our models for both tasks was SegResNet with deep supervision. For Task 1, we trained the model using a combined dataset of pre-RT and mid-RT MRI data, which resulted in the improved aggregated Dice similarity coefficient (DSCagg) on an internal testing set compared to models trained solely on pre-RT MRI data. In Task 2, we introduced mask-aware attention modules, enabling pre-RT GTV masks to influence intermediate features learned from mid-RT data. This attention-based approach yielded slight improvements over the baseline method, which concatenated mid-RT MRI with pre-RT GTV masks as input. In the final testing phase, the ensemble of 10 pre-RT segmentation models achieved an average DSCagg of 0.794, with 0.745 for primary GTV (GTVp) and 0.844 for metastatic lymph nodes (GTVn) in Task 1. For Task 2, the ensemble of 10 mid-RT segmentation models attained an average DSCagg of 0.733, with 0.607 for GTVp and 0.859 for GTVn, leading us to $\textbf{achieve 1st place}$. In summary, we presented a collection of DL models that could facilitate GTV segmentation in MRgART, offering the potential to streamline radiation oncology workflows. Our code and model weights are available at https://github.com/xtie97/HNTS-MRG24-UWLAIR.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
