文献速递放疗物理与技术

人工智能不确定性量化在放射治疗中的应用——范围综述

Artificial intelligence uncertainty quantification in radiotherapy applications - A scoping review.
PubMed 文献 · Radiother Oncol · 2024-09-17

本范围综述遵循PRISMA-ScR指南,系统检索7个数据库至2024年1月,初检获8980篇文献,最终纳入2015至2024年发表的56篇文献,评估人工智能不确定性量化在放射治疗中的应用。结果显示多数研究集中于自动勾画(50%),主要应用为失败检测(60%),最常用方法为蒙特卡洛丢弃法(32%),55%的研究未共享代码或数据集。结论指出自动勾画之外的不确定性量化应用缺乏多样性,需要研究共形预测等额外方法,结果可能推动报告与实施指南的制定。

要点

  • 纳入56篇文献中,50%评估自动勾画,13%评估图像合成,11%同时评估多种应用。
  • 头颈部癌是最常见疾病部位(32%),91%的研究使用影像数据,仅13%纳入放疗剂量信息。
  • 失败检测是主要应用(60%),蒙特卡洛丢弃法(32%)和集成法(16%)是最常用方法,55%未共享代码或数据集。

核心结论

  • 综述发现自动勾画之外的不确定性量化应用缺乏多样性,并明确需要研究共形预测等额外不确定性量化方法。
  • 作者认为结果可能推动放射治疗中不确定性量化的报告与实施指南的制定。

研究设计与样本

  • 遵循PRISMA-ScR范围综述报告指南,采用人群(人类癌症患者)、概念(人工智能不确定性量化的使用)、情境(放射治疗应用)框架构建检索与筛选流程。
  • 系统检索7个数据库并辅以人工整理,检索截至2024年1月,初检共获得8980篇文献供初步审查。
  • 在Covidence中进行稿件筛选与数据提取,提取类别包括一般研究特征、放射治疗特征、人工智能特征和不确定性量化特征。

主要发现

  • 共纳入2015年至2024年发表的56篇文献,涵盖10个放射治疗应用领域,其中自动勾画占50%,图像合成占13%,多种应用同时评估占11%。
  • 涵盖12个疾病部位,头颈部癌为最常见疾病部位(32%),且独立于应用领域。
  • 91%的研究使用影像数据,仅13%纳入放射治疗剂量信息。
  • 60%的研究以失败检测为主要不确定性量化应用,蒙特卡洛丢弃法为最常用方法(32%),其次为集成法(16%)。
  • 55%的研究未共享代码或数据集。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND/PURPOSE: The use of artificial intelligence (AI) in radiotherapy (RT) is expanding rapidly. However, there exists a notable lack of clinician trust in AI models, underscoring the need for effective uncertainty quantification (UQ) methods. The purpose of this study was to scope existing literature related to UQ in RT, identify areas of improvement, and determine future directions. METHODS: We followed the PRISMA-ScR scoping review reporting guidelines. We utilized the population (human cancer patients), concept (utilization of AI UQ), context (radiotherapy applications) framework to structure our search and screening process. We conducted a systematic search spanning seven databases, supplemented by manual curation, up to January 2024. Our search yielded a total of 8980 articles for initial review. Manuscript screening and data extraction was performed in Covidence. Data extraction categories included general study characteristics, RT characteristics, AI characteristics, and UQ characteristics. RESULTS: We identified 56 articles published from 2015 to 2024. 10 domains of RT applications were represented; most studies evaluated auto-contouring (50 %), followed by image-synthesis (13 %), and multiple applications simultaneously (11 %). 12 disease sites were represented, with head and neck cancer being the most common disease site independent of application space (32 %). Imaging data was used in 91 % of studies, while only 13 % incorporated RT dose information. Most studies focused on failure detection as the main application of UQ (60 %), with Monte Carlo dropout being the most commonly implemented UQ method (32 %) followed by ensembling (16 %). 55 % of studies did not share code or datasets. CONCLUSION: Our review revealed a lack of diversity in UQ for RT applications beyond auto-contouring. Moreover, we identified a clear need to study additional UQ methods, such as conformal prediction. Our results may incentivize the development of guidelines for reporting and implementation of UQ in RT.

来源:Radiother Oncol,查看原文。版权归原作者所有。

引用

  1. Wahid KA, Kaffey ZY, Farris DP, et al. Artificial intelligence uncertainty quantification in radiotherapy applications - A scoping review. Radiother Oncol. 2024. PMID: 39299574. doi:10.1016/j.radonc.2024.110542

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。