文献速递消化道肿瘤与早癌消化内镜

基于多模态数据深度学习模型实时自动诊断结直肠癌浸润深度(附视频)

Real-time automated diagnosis of colorectal cancer invasion depth using a deep learning model with multimodal data (with video).
PubMed 文献 · Gastrointest Endosc · 2021-12-14

本研究回顾性纳入中国3家医院数据,构建结合白光与图像增强内镜图像对的Endo-CRC深度学习系统估算结直肠癌浸润深度。内部图像测试准确率91.61%(含进展期)和93.78%(不含进展期),外部测试88.65%;医师-机器竞赛中准确率88.11%且敏感性最高;视频测试准确率100.00%。

要点

  • Endo-CRC在内部图像测试准确率91.61%(含进展期)和93.78%(不含进展期)。
  • 外部测试准确率88.65%,视频实时测试准确率100.00%。
  • 医师-机器竞赛中Endo-CRC准确率88.11%,敏感性高于所有内镜医师。

核心结论

  • Endo-CRC系统在协助结直肠癌浸润深度诊断方面具有较大潜力,可能较好地应用于临床实践。

研究设计与样本

  • 回顾性收集中国3家医院样本,将白光与图像增强内镜图像组合为图像对。
  • 训练集包括268例非浸润性和浅表性结直肠癌的337,278个图像对及82例深浸润性结直肠癌的181,934个图像对。
  • 内部测试和外部测试分别使用296,644和4,528个图像对,并与内镜医师比较;35段视频用于评估实时性能。
  • 另构建仅使用白光图像的模型W和仅使用图像增强内镜图像的模型I,与Endo-CRC比较。

主要发现

  • Endo-CRC在含进展期结直肠癌的内部图像测试中准确率为91.61%,在不含进展期结直肠癌的内部图像测试中准确率为93.78%。
  • 外部测试(不含进展期结直肠癌)准确率为88.65%。
  • 在医师-机器竞赛中,Endo-CRC达到与专家相当的准确率88.11%,且敏感性高于所有内镜医师。
  • 视频测试中Endo-CRC准确率为100.00%。
  • Endo-CRC准确率高于模型I(每图像对91.61% vs 88.27%)和模型W(91.61% vs 81.32%)。

关键数值与推荐

  • Endo-CRC内部图像测试(含进展期)准确率91.61%。
  • Endo-CRC内部图像测试(不含进展期)准确率93.78%。
  • Endo-CRC外部测试(不含进展期)准确率88.65%。
  • 医师-机器竞赛中Endo-CRC准确率88.11%。
  • Endo-CRC视频测试准确率100.00%。

临床怎么用

  • 原文结论认为Endo-CRC系统在协助结直肠癌浸润深度诊断方面具有较大潜力,可能较好地应用于临床实践。

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 AND AIMS: The optical diagnosis of colorectal cancer (CRC) invasion depth with white light (WL) and image-enhanced endoscopy (IEE) remains challenging. We aimed to construct and validate a 2-modal deep learning-based system, incorporated with both WL and IEE images (named Endo-CRC) in estimating the invasion depth of CRC. METHODS: Samples were retrospectively obtained from 3 hospitals in China. We combined WL and IEE images into image pairs. Altogether, 337,278 image pairs from 268 noninvasive and superficial CRC and 181,934 image pairs from 82 deep CRC were used for training. A total of 296,644 and 4528 image pairs were used for internal and external tests and for comparison with endoscopists. Thirty-five videos were used for evaluating the real-time performance of the Endo-CRC system. Two deep learning models, solely using either WL (model W) or IEE images (model I), were constructed to compare with Endo-CRC. RESULTS: The accuracies of Endo-CRC in internal image tests with and without advanced CRC were 91.61% and 93.78%, respectively, and 88.65% in the external test, which did not include advanced CRC. In an endoscopist-machine competition, Endo-CRC achieved an expert comparable accuracy of 88.11% and the highest sensitivity compared with all endoscopists. In a video test, Endo-CRC achieved an accuracy of 100.00%. Compared with model W and model I, Endo-CRC had a higher accuracy (per image pair: 91.61% vs 88.27% compared with model I and 91.61% vs 81.32% compared with model W). CONCLUSIONS: The Endo-CRC system has great potential for assisting in CRC invasion depth diagnosis and may be well applied in clinical practice.

来源:Gastrointest Endosc,查看原文。版权归原作者所有。

引用

  1. Lu Z, Xu Y, Yao L, et al. Real-time automated diagnosis of colorectal cancer invasion depth using a deep learning model with multimodal data (with video). Gastrointest Endosc. 2021. PMID: 34919941. doi:10.1016/j.gie.2021.11.049

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。