文献速递消化道肿瘤与早癌消化内镜

人工智能评估胃癌风险:深度学习算法可靠检测和评分肠上皮化生

Artificial intelligence for evaluating the risk of gastric cancer: reliable detection and scoring of intestinal metaplasia with deep learning algorithms.
PubMed 文献 · Gastrointest Endosc · 2023-06-29

研究采用ResNet50深度卷积神经网络对5753张胃活检组织图像进行肠上皮化生(IM)评分。模型区分有无IM的敏感度97.7%、特异度94.6%;区分评分0-1与2-3的敏感度98.5%、特异度94.9%。病理医师与AI评分仅438张(7.6%)不同,AI倾向漏诊小灶IM但可识别病理医师遗漏的微小IM区域。

要点

  • ResNet50区分有无IM的敏感度97.7%、特异度94.6%。
  • 区分IM评分0-1与2-3的敏感度98.5%、特异度94.9%。
  • 病理医师与AI评分仅438张(7.6%)不同,AI可识别病理医师遗漏的微小IM。

核心结论

  • 研究提示该AI系统有助于准确、可靠、可重复地评估胃癌风险,并有望实现全球标准化。

研究设计与样本

  • 对苏木精-伊红染色切片进行扫描,图像按每份胃活检组织样本分割并标注IM评分。
  • IM评分标准为0分(无IM)、1分(轻度IM)、2分(中度IM)、3分(重度IM)。
  • 共准备5753张图像,采用ResNet50深度卷积神经网络模型进行分类。

主要发现

  • ResNet50区分有IM与无IM图像的敏感度为97.7%、特异度为94.6%。
  • 作为OLGIM系统III或IV期标准的IM评分2和3,被ResNet50分类的比例为18%。
  • ResNet50区分IM评分0-1与2-3的敏感度为98.5%、特异度为94.9%。
  • 病理医师与AI系统的IM评分仅438张图像(7.6%)不同。
  • ResNet50倾向于漏诊小灶IM,但成功识别了病理医师复核时遗漏的微小IM区域。

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: Gastric cancer (GC) is associated with chronic gastritis. To evaluate the risk, the Operative Link on Gastric Intestinal Metaplasia Assessment (OLGIM) system was constructed and showed a higher GC risk in stage III or IV patients, determined by the degree of intestinal metaplasia (IM). Although the OLGIM system is useful, evaluating the degree of IM requires substantial experience to produce precise scoring. Whole-slide imaging is becoming routine, but most artificial intelligence (AI) systems in pathology are focused on neoplastic lesions. METHODS: Hematoxylin and eosin-stained slides were scanned. Images were divided into each gastric biopsy tissue sample and labeled with an IM score. IM was scored as follows: 0 (no IM), 1 (mild IM), 2 (moderate IM), and 3 (severe IM). Overall, 5753 images were prepared. A deep convolutional neural network (DCNN) model, ResNet50, was used for classification. RESULTS: ResNet50 classified images with and without IM with a sensitivity of 97.7% and specificity of 94.6%. IM scores 2 and 3, involved as criteria of stage III or IV in the OLGIM system, were classified by ResNet50 in 18%. The respective sensitivity and specificity values of classifying IM between scores 0 and 1 and 2 and 3 were 98.5% and 94.9%, respectively. The IM scores classified by pathologists and the AI system were different in only 438 images (7.6%), and we found that ResNet50 tended to miss small foci of IM but successfully identified minimal IM areas that pathologists missed during the review. CONCLUSIONS: Our findings suggested that this AI system would contribute to evaluating the risk of GC accuracy, reliability, and repeatability with worldwide standardization.

来源:Gastrointest Endosc,查看原文。版权归原作者所有。

引用

  1. Iwaya M, Hayashi Y, Sakai Y, et al. Artificial intelligence for evaluating the risk of gastric cancer: reliable detection and scoring of intestinal metaplasia with deep learning algorithms. Gastrointest Endosc. 2023. PMID: 37392953. doi:10.1016/j.gie.2023.06.056

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。