Endoscopic Diagnosis and Treatment Department, The Second Affiliated Hospital of Shandong University of Traditional Chinese Medicine, 250001 Jinan City, Shandong Province, China.
Office of Invitation to Bid, The Second Affiliated Hospital of Shandong University of Traditional Chinese Medicine, 250001 Jinan City, Shandong Province, China.
Comput Math Methods Med. 2022 Jun 18;2022:9018939. doi: 10.1155/2022/9018939. eCollection 2022.
To explore the efficacy of digestive endoscopy (DEN) based on artificial intelligence (AI) system in diagnosing early esophageal carcinoma.
The clinical data of 300 patients with suspected esophageal carcinoma treated in our hospital from January 2018 to January 2020 were retrospectively analyzed; among them, 198 were diagnosed with esophageal carcinoma after pathological examination, and 102 had benign esophageal lesion. An AI system based on convolutional neural network (CNN) was adopted to assess the DEN images of patients with early esophageal carcinoma. A total of 200 patients (148 with early esophageal carcinoma and 52 with benign esophageal lesion) were selected as the learning group for the Inception V3 image classification system to learn; and the rest 100 patients (50 with early esophageal carcinoma and 50 with benign esophageal lesion) were included in the diagnosis group for the Inception V3 system to assist the narrow-band imaging (NBI) with diagnosis. The diagnosis results from Inception V3-assisted NBI were compared with those from imaging physicians, and the diagnostic efficacy diagram was drawn.
The diagnosis rate of AI-NBI was significantly faster than that of physician diagnosis (0.02 ± 0.01 vs. 5.65 ± 0.32 s (mean rate of two physicians), < 0.001); between AI-NBI diagnosis and physician diagnosis, no statistical differences in sensitivity (90.0% vs. 92.0%), specificity (92.0% vs. 94.0%), and accuracy (91.0% vs. 93.0%) were observed ( > 0.05); and according to the ROC curves, AUC (95% CI) of AI-NBI diagnosis = 0.910 (0.845-0.975), and AUC (95% CI) of physician diagnosis = 0.930 (0.872-0.988).
CNN-based AI system can assist NBI in screening early esophageal carcinoma, which has a good application prospect in the clinical diagnosis of early esophageal carcinoma.
探讨基于人工智能（AI）系统的消化内镜（DEN）在诊断早期食管癌中的疗效。
回顾性分析我院 2018 年 1 月至 2020 年 1 月收治的 300 例疑似食管癌患者的临床资料；其中，198 例经病理检查诊断为食管癌，102 例为良性食管病变。采用基于卷积神经网络（CNN）的 AI 系统评估早期食管癌患者的 DEN 图像。共选择 200 例患者（148 例早期食管癌，52 例良性食管病变）作为 Inception V3 图像分类系统的学习组进行学习；其余 100 例患者（50 例早期食管癌，50 例良性食管病变）纳入诊断组，协助窄带成像（NBI）诊断。将 Inception V3 辅助 NBI 的诊断结果与影像医师的诊断结果进行比较，并绘制诊断效能图。
AI-NBI 的诊断速度明显快于医师诊断（0.02±0.01 比 5.65±0.32s（两位医师的平均诊断速度），<0.001）；AI-NBI 诊断与医师诊断的灵敏度（90.0%比 92.0%）、特异度（92.0%比 94.0%）和准确率（91.0%比 93.0%）差异均无统计学意义（>0.05）；根据 ROC 曲线，AI-NBI 诊断的 AUC（95%CI）=0.910（0.845-0.975），医师诊断的 AUC（95%CI）=0.930（0.872-0.988）。
基于 CNN 的 AI 系统可辅助 NBI 筛查早期食管癌，在早期食管癌的临床诊断中具有较好的应用前景。
