基于深度卷积神经网络的无线胶囊内镜小肠隆起性病变自动检测与分类
本研究训练深度卷积神经网络(CNN),使用来自292例患者的30584张无线胶囊内镜(WCE)图像,并在来自93例患者的17507张独立测试图像上评估。CNN检测隆起性病变的AUC为0.911,敏感度90.7%、特异度79.8%,患者层面检出率98.6%,提示该计算机辅助系统可自动检测多种类型的小肠隆起性病变。
要点
- CNN检测WCE小肠隆起性病变的AUC为0.911,敏感度90.7%、特异度79.8%。
- 各亚类敏感度:息肉86.5%、结节92.0%、上皮性肿瘤95.8%、黏膜下肿瘤77.0%、静脉结构94.4%。
- 患者层面(n=73)隆起性病变检出率为98.6%,仍需更大 cohort 验证。
核心结论
- 基于CNN的计算机辅助系统可自动检测WCE图像中多种类型的小肠隆起性病变。
研究设计与样本
- 使用来自292例患者的30584张WCE隆起性病变图像训练深度卷积神经网络(CNN)。
- 使用来自93例患者的17507张独立测试图像评估CNN性能,其中包含来自73例患者的7507张隆起性病变图像。
主要发现
- CNN检测隆起性病变的AUC为0.911(95%CI 0.9069-0.9155)。
- 在概率评分最佳截断值0.317时,CNN检测隆起性病变的敏感度为90.7%(95%CI 90.0%-91.4%),特异度为79.8%(95%CI 79.0%-80.6%)。
- 亚组分析中,CNN检测息肉、结节、上皮性肿瘤、黏膜下肿瘤和静脉结构的敏感度分别为86.5%、92.0%、95.8%、77.0%和94.4%。
- 在73例患者的个体分析中,隆起性病变检出率为98.6%。
临床怎么用
- 该CNN系统有望辅助WCE阅片,自动检测小肠隆起性病变,但黏膜下肿瘤检测敏感度相对较低(77.0%)。
- 需在更大队列中开展患者层面分析并进一步优化诊断性能后方可用于临床。
局限性
- 需在更大队列中开展患者层面分析并进一步努力提升诊断性能。
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: Protruding lesions of the small bowel vary in wireless capsule endoscopy (WCE) images, and their automatic detection may be difficult. We aimed to develop and test a deep learning-based system to automatically detect protruding lesions of various types in WCE images. METHODS: We trained a deep convolutional neural network (CNN), using 30,584 WCE images of protruding lesions from 292 patients. We evaluated CNN performance by calculating the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity, using an independent set of 17,507 test images from 93 patients, including 7507 images of protruding lesions from 73 patients. RESULTS: The developed CNN analyzed 17,507 images in 530.462 seconds. The AUC for detection of protruding lesions was 0.911 (95% confidence interval [Cl], 0.9069-0.9155). The sensitivity and specificity of the CNN were 90.7% (95% CI, 90.0%-91.4%) and 79.8% (95% CI, 79.0%-80.6%), respectively, at the optimal cut-off value of 0.317 for probability score. In a subgroup analysis of the category of protruding lesions, the sensitivities were 86.5%, 92.0%, 95.8%, 77.0%, and 94.4% for the detection of polyps, nodules, epithelial tumors, submucosal tumors, and venous structures, respectively. In individual patient analyses (n = 73), the detection rate of protruding lesions was 98.6%. CONCLUSION: We developed and tested a new computer-aided system based on a CNN to automatically detect various protruding lesions in WCE images. Patient-level analyses with larger cohorts and efforts to achieve better diagnostic performance are necessary in further studies.
引用
- Saito H, Aoki T, Aoyama K, et al. Automatic detection and classification of protruding lesions in wireless capsule endoscopy images based on a deep convolutional neural network. Gastrointest Endosc. 2020. PMID: 32084410. doi:10.1016/j.gie.2020.01.054
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。