基于内镜图像诊断幽门螺杆菌感染的卷积神经网络模型的开发与验证:一项多中心研究
本研究基于首尔大学医院江南中心952例患者的13,403张内镜图像开发卷积神经网络模型,用于诊断幽门螺杆菌感染,并在韩国裔、非韩国裔内部验证集及江南Severance医院外部验证集中评估。模型在判断幽门螺杆菌曾感染状态时表现良好,外部验证集敏感度0.86、特异度0.88、准确率0.87。
要点
- 基于13,403张内镜图像开发CNN模型,用于诊断幽门螺杆菌感染。
- 内部验证韩国裔人群判断曾感染状态敏感度0.96、特异度0.90、准确率0.94。
- 外部验证集敏感度0.86、特异度0.88、准确率0.87,模型整体表现良好。
核心结论
- 该CNN模型在内部和外部验证数据集中诊断幽门螺杆菌感染整体表现良好,尤其在区分从未感染与曾感染组方面表现突出。
研究设计与样本
- 基于首尔大学医院江南中心952例患者的内镜图像13,403张开发CNN模型。
- 内部验证使用韩国裔411人及非韩国裔131人的独立图像数据集。
- 外部验证使用江南Severance医院160例患者的图像。
- 采用梯度加权类激活映射对模型进行可视化解释。
主要发现
- 内部验证韩国裔人群预测幽门螺杆菌曾感染状态的敏感度0.96(95%CI 0.93-0.98)、特异度0.90(95%CI 0.85-0.95)、准确率0.94(95%CI 0.91-0.96)。
- 内部验证非韩国裔人群预测曾感染状态的敏感度0.92(95%CI 0.86-0.98)、特异度0.79(95%CI 0.67-0.91)、准确率0.88(95%CI 0.82-0.93)。
- 外部验证队列进行二分类时敏感度0.86(95%CI 0.80-0.93)、特异度0.88(95%CI 0.79-0.96)、准确率0.87(95%CI 0.82-0.92)。
- 梯度加权类激活映射显示CNN模型捕捉到了各组的特征性表现。
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: Insufficient validation limits the generalizability of deep learning in diagnosing Helicobacter pylori infection with endoscopic images. The aim of this study was to develop a deep learning model for the diagnosis of H pylori infection using endoscopic images and validate the model with internal and external datasets. METHODS: A convolutional neural network (CNN) model was developed based on a training dataset comprising 13,403 endoscopic images from 952 patients who underwent endoscopy at Seoul National University Hospital Gangnam Center. Internal validation was performed using a separate dataset comprised of images of 411 individuals of Korean descent and 131 of non-Korean descent. External validation was performed with the images of 160 patients in Gangnam Severance Hospital. Gradient-weighted class activation mapping was performed to visually explain the model. RESULTS: In predicting H pylori ever-infected status, the sensitivity, specificity, and accuracy of internal validation for people of Korean descent were .96 (95% confidence interval [CI], .93-.98), .90 (95% CI, .85-.95), and .94 (95% CI, .91-.96), respectively. In the internal validation for people of non-Korean descent, the sensitivity, specificity, and accuracy in predicting H pylori ever-infected status were .92 (95% CI, .86-.98), .79 (95% CI, .67-.91), and .88 (95% CI, .82-.93), respectively. In the external validation cohort, sensitivity, specificity, and accuracy were .86 (95% CI, .80-.93), .88 (95% CI, .79-.96), and .87 (95% CI, .82-.92), respectively, when performing 2-group categorization. Gradient-weighted class activation mapping showed that the CNN model captured the characteristic findings of each group. CONCLUSIONS: This CNN model for diagnosing H pylori infection showed good overall performance in internal and external validation datasets, particularly in categorizing patients into the never- versus ever-infected groups.
引用
- Seo JY, Hong H, Ryu WS, et al. Development and validation of a convolutional neural network model for diagnosing Helicobacter pylori infections with endoscopic images: a multicenter study. Gastrointest Endosc. 2023. PMID: 36641124. doi:10.1016/j.gie.2023.01.007
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。