Ability of artificial intelligence to detect T1 esophageal squamous cell carcinoma from endoscopic videos and the effects of real-time assistance.
Ability of artificial intelligence to detect T1 esophageal squamous cell carcinoma from endoscopic videos and the effects of real-time assistance.
复制标题
DOI：
10.1038/s41598-021-87405-6
复制
发表时间：
2021-04-08
影响因子：
4.6
通讯作者：
Fujisaki J
中科院分区：
文献类型：
--
作者：
Shiroma S;Yoshio T;Kato Y;Horie Y;Namikawa K;Tokai Y;Yoshimizu S;Yoshizawa N;Horiuchi Y;Ishiyama A;Hirasawa T;Tsuchida T;Akazawa N;Akiyama J;Tada T;Fujisaki J
使用具有深度学习的人工智能（AI）进行诊断可能在内窥镜检查中有用。我们研究了AI从食管胃镜（EGD）视频中检测浅表食管鳞状细胞癌（ESCC）的能力。我们回顾性地收集了8428张食管癌的EGD图像，通过深度学习开发了一个卷积神经网络。我们评估了AI诊断系统的检测准确性，并与18名内镜医生的检测结果进行了比较。我们使用144个EGD视频进行两个验证集。首先，我们使用64 EGD观察视频ESCC使用白色光成像（WLI）和窄带成像（NBI）。然后，我们使用来自40名患者（20名浅表ESCC和20名非ESCC）的80个EGD视频对该系统进行了评估。在第一组中，AI系统正确诊断了100%的ESCC。在第二组中，它正确地检测了85%（17/20）的ESCC。其中WLI和NBI的检出率分别为75%（15/20）和55%（11/22），阳性预测值为36.7%。内镜医师正确检测到45%（25-70%）ESCC。在AI实时辅助下，内窥镜医生的灵敏度在没有AI辅助的情况下显著提高（p < 0.05）。AI可以从EGD视频中以高灵敏度检测浅表ESCC，并且通过AI实时支持提高了内窥镜医生的灵敏度。
Diagnosis using artificial intelligence (AI) with deep learning could be useful in endoscopic examinations. We investigated the ability of AI to detect superficial esophageal squamous cell carcinoma (ESCC) from esophagogastroduodenoscopy (EGD) videos. We retrospectively collected 8428 EGD images of esophageal cancer to develop a convolutional neural network through deep learning. We evaluated the detection accuracy of the AI diagnosing system compared with that of 18 endoscopists. We used 144 EGD videos for the two validation sets. First, we used 64 EGD observation videos of ESCCs using both white light imaging (WLI) and narrow-band imaging (NBI). We then evaluated the system using 80 EGD videos from 40 patients (20 with superficial ESCC and 20 with non-ESCC). In the first set, the AI system correctly diagnosed 100% ESCCs. In the second set, it correctly detected 85% (17/20) ESCCs. Of these, 75% (15/20) and 55% (11/22) were detected by WLI and NBI, respectively, and the positive predictive value was 36.7%. The endoscopists correctly detected 45% (25–70%) ESCCs. With AI real-time assistance, the sensitivities of the endoscopists were significantly improved without AI assistance (p < 0.05). AI can detect superficial ESCCs from EGD videos with high sensitivity and the sensitivity of the endoscopist was improved with AI real-time support.
登录
查看更多内容
影响因子：
7.7
作者：
Ohmori, Masayasu;Ishihara, Ryu;Tada, Tomohiro
通讯作者：
Tada, Tomohiro
影响因子：
7.7
作者：
Fukuda, Hiromu;Ishihara, Ryu;Tada, Tomohiro
通讯作者：
Tada, Tomohiro
影响因子：
7.7
作者：
Guo, LinJie;Xiao, Xiao;Hu, Bing
通讯作者：
Hu, Bing
影响因子：
28.2
作者：
Agrawal N;Jiao Y;Bettegowda C;Hutfless SM;Wang Y;David S;Cheng Y;Twaddell WS;Latt NL;Shin EJ;Wang LD;Wang L;Yang W;Velculescu VE;Vogelstein B;Papadopoulos N;Kinzler KW;Meltzer SJ
通讯作者：
Meltzer SJ
影响因子：
7.7
作者：
Kondo, H;Fukuda, H;Yoshida, S
通讯作者：
Yoshida, S