文献速递胸部肿瘤放疗放疗物理与技术

深度学习在计算机断层扫描肺癌分割中应用的系统综述与荟萃分析

Systematic review and meta-analysis of deep learning applications in computed tomography lung cancer segmentation.
PubMed 文献 · Radiother Oncol · 2024-05-26

该系统综述与荟萃分析检索截至2023年11月7日的PubMed、Embase和Web of Science数据库,纳入37项研究,评估深度学习在胸部CT肺癌分割中的效能;汇总Dice评分为79%(95%CI:76%-83%),放疗研究为78%(95%CI:74%-82%),2022年后研究较前提升至82%(95%CI:81%-84%)。

要点

  • 37项研究汇总Dice评分为79%(95%CI:76%-83%),提示中等准确度。
  • 放疗相关研究Dice评分为78%(95%CI:74%-82%),略低于总体汇总值。
  • 2022年后研究Dice评分从75%(95%CI:70%-81%)提升至82%(95%CI:81%-84%)。

核心结论

  • 荟萃分析显示深度学习算法在肺癌分割中效能有前景但存在差异,早期阶段效能更高。
  • 作者指出亟需持续开发定制化深度学习模型以改善不同临床场景下的分割准确度,尤其是挑战更大的晚期癌症阶段。

研究设计与样本

  • 系统综述与荟萃分析,检索PubMed、Embase和Web of Science截至2023年11月7日,纳入37项研究。
  • 使用医学影像人工智能清单(CLAIM)和诊断准确性质量评价工具第二版(QUADAS-2)评估研究质量。
  • 汇总Dice相似系数等关键性能指标,并分析临床场景、算法类型和图像处理技术等影响因素。

主要发现

  • 37项研究汇总Dice评分为79%(95%CI:76%-83%),提示中等准确度。
  • 放疗研究Dice评分为78%(95%CI:74%-82%),略低于总体汇总值。
  • 2022年后研究Dice评分从75%(95%CI:70%-81%)提升至82%(95%CI:81%-84%)。
  • 影响性能的关键因素包括算法类型、分辨率调整和图像裁剪。
  • QUADAS-2评估发现78%的研究因数据区间遗漏存在不明确风险,8%的研究因排除结节大小存在泛化性担忧;CLAIM标准平均得分为27.24分(满分42分)。

关键数值与推荐

  • 汇总Dice评分79%(95%CI:76%-83%),对应37项研究总体。
  • 放疗研究Dice评分78%(95%CI:74%-82%)。
  • 2022年后研究Dice评分82%(95%CI:81%-84%),较前(75%,95%CI:70%-81%)提升。
  • CLAIM标准平均得分27.24分(满分42分)。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • QUADAS-2评估显示78%的研究因数据区间遗漏存在不明确风险。
  • 8%的研究因排除结节大小存在泛化性担忧。
  • CLAIM标准评估显示平均得分27.24分(满分42分),提示有待改进之处。

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: Accurate segmentation of lung tumors on chest computed tomography (CT) scans is crucial for effective diagnosis and treatment planning. Deep Learning (DL) has emerged as a promising tool in medical imaging, particularly for lung cancer segmentation. However, its efficacy across different clinical settings and tumor stages remains variable. METHODS: We conducted a comprehensive search of PubMed, Embase, and Web of Science until November 7, 2023. We assessed the quality of these studies by using the Checklist for Artificial Intelligence in Medical Imaging and the Quality Assessment of Diagnostic Accuracy Studies-2 tools. This analysis included data from various clinical settings and stages of lung cancer. Key performance metrics, such as the Dice similarity coefficient, were pooled, and factors affecting algorithm performance, such as clinical setting, algorithm type, and image processing techniques, were examined. RESULTS: Our analysis of 37 studies revealed a pooled Dice score of 79 % (95 % CI: 76 %-83 %), indicating moderate accuracy. Radiotherapy studies had a slightly lower score of 78 % (95 % CI: 74 %-82 %). A temporal increase was noted, with recent studies (post-2022) showing improvement from 75 % (95 % CI: 70 %-81 %). to 82 % (95 % CI: 81 %-84 %). Key factors affecting performance included algorithm type, resolution adjustment, and image cropping. QUADAS-2 assessments identified ambiguous risks in 78 % of studies due to data interval omissions and concerns about generalizability in 8 % due to nodule size exclusions, and CLAIM criteria highlighted areas for improvement, with an average score of 27.24 out of 42. CONCLUSION: This meta-analysis demonstrates DL algorithms' promising but varied efficacy in lung cancer segmentation, particularly higher efficacy noted in early stages. The results highlight the critical need for continued development of tailored DL models to improve segmentation accuracy across diverse clinical settings, especially in advanced cancer stages with greater challenges. As recent studies demonstrate, ongoing advancements in algorithmic approaches are crucial for future applications.

来源:Radiother Oncol,查看原文。版权归原作者所有。

引用

  1. Wang TW, Hong JS, Huang JW, et al. Systematic review and meta-analysis of deep learning applications in computed tomography lung cancer segmentation. Radiother Oncol. 2024. PMID: 38806113. doi:10.1016/j.radonc.2024.110344

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。