文献速递技术与安全

探索放射学中人工智能的环境可持续性:范围综述

Exploring environmental sustainability of artificial intelligence in radiology: A scoping review.
PubMed 文献 · Eur J Radiol · 2025-11-19

该范围综述遵循乔安娜布里格斯研究所方法学,检索2014至2024年英法文文献,最终纳入13篇(9篇研究论文、4篇综述),归纳出能耗、碳足迹、计算资源和水消耗四个主题,并汇总了轻量化模型架构、量化与剪枝等可持续性策略及将碳与能耗指标纳入AI评估等更广泛建议。

要点

  • 纳入13篇文献,四个主题为能耗(n=10)、碳足迹(n=6)、计算资源(n=9)和水消耗(n=2)。
  • 报告的指标包括CO2当量排放、训练时间、功率使用效率、等效驾车距离、能源需求和水消耗。
  • 可持续性策略包括轻量化模型架构、量化和剪枝、高效优化器及早停。

核心结论

  • 放射学中可持续AI的研究仍然稀少但正在快速增长,本综述强调了关键指标和策略,以指导未来研究和实践走向更透明、一致且对环境负责的AI开发。

研究设计与样本

  • 范围综述,遵循乔安娜布里格斯研究所方法学,检索MEDLINE、Embase、CINAHL和Web of Science,聚焦2014至2024年英文和法文出版物,由两名独立评审员评估标题、摘要和全文,四名评审员进行数据提取和分析。

诊断标准与关键数值

  • 共检索到3723条结果,其中13条符合纳入标准:9篇研究论文和4篇综述。
  • 四个主题:能耗(n=10)、碳足迹(n=6)、计算资源(n=9)和水消耗(n=2)。
  • 报告的指标包括CO2当量排放、训练时间、功率使用效率、等效驾车距离、能源需求和水消耗。

临床应用与阅片要点

  • 可持续性策略包括轻量化模型架构、量化和剪枝、高效优化器及早停。
  • 更广泛的建议包括将碳和能耗指标纳入AI评估、转向云计算以及为放射学AI系统开发生态标签。

局限性

  • 放射学中可持续AI的研究仍然稀少。

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)。

英文原文(摘要)· 点击展开

OBJECTIVE: Artificial intelligence (AI) is increasingly used in radiology, but its environmental implications have not been sufficiently studied, so far. This study aims to synthesize existing literature on the environmental sustainability of AI in radiology and highlights strategies proposed to mitigate its impact.

METHODS: A scoping review was conducted following the Joanna Briggs Institute methodology. Searches across MEDLINE, Embase, CINAHL, and Web of Science focused on English and French publications from 2014 to 2024, targeting AI, environmental sustainability, and medical imaging. Eligible studies addressed environmental sustainability of AI in medical imaging. Conference abstracts, non-radiological or non-human studies, and unavailable full texts were excluded. Two independent reviewers assessed titles, abstracts, and full texts, while four reviewers conducted data extraction and analysis.

RESULTS: The search identified 3,723 results, of which 13 met inclusion criteria: nine research articles and four reviews. Four themes emerged: energy consumption (n = 10), carbon footprint (n = 6), computational resources (n = 9), and water consumption (n = 2). Reported metrics included CO2-equivalent emissions, training time, power use effectiveness, equivalent distance travelled by car, energy demands, and water consumption. Strategies to enhance sustainability included lightweight model architectures, quantization and pruning, efficient optimizers, and early stopping. Broader recommendations encompassed integrating carbon and energy metrics into AI evaluation, transitioning to cloud computing, and developing an eco-label for radiology AI systems.

CONCLUSIONS: Research on sustainable AI in radiology remains scarce but is rapidly growing. This review highlights key metrics and strategies to guide future research and practice toward more transparent, consistent, and environmentally responsible AI development in radiology.

ABBREVIATIONS: AI, Artificial intelligence; CNN, Convolutional neural networks; CT, Computed tomography; CPU, Central Processing Unit; DL, Deep learning; FLOP, Floating-point operation; GHG, Greenhouses gas; GPU, Graphics Processing Unit; LCA, Life Cycle Assessment; LLM, Large Language Model; MeSH, Medical Subject Headings; ML, Machine learning; MRI, Magnetic resonance imaging; NLP, Natural language processing; PUE, Power Usage Effectiveness; TPU, Tensor Processing Unit; USA, United States of America; ViT, Vision Transformer; WUE, Water Usage Effectiveness.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Champendal M, Lokaj B, de Gevigney VD, et al. Exploring environmental sustainability of artificial intelligence in radiology: A scoping review. Eur J Radiol. 2025. PMID: 41275851. doi:10.1016/j.ejrad.2025.112558

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。