Development and Validation of an Automatic Image-Recognition Endoscopic Report Generation System: A Multicenter Study.
Development and Validation of an Automatic Image-Recognition Endoscopic Report Generation System: A Multicenter Study.
复制标题
自动图像识别内镜报告生成系统的开发与验证：一项多中心研究
DOI：
10.14309/ctg.0000000000000282
复制
发表时间：
2020-12-22
影响因子：
3.6
通讯作者：
Zuo XL
中科院分区：
文献类型：
--
作者：
Qu JY;Li Z;Su JR;Ma MJ;Xu CQ;Zhang AJ;Liu CX;Yuan HP;Chu YL;Lang CC;Huang LY;Lu L;Li YQ;Zuo XL
传统的胃肠道（GI）内窥镜检查报告由医生撰写，耗时长，可能存在明显的异质性或遗漏，影响了效率和多中心会诊的潜力。我们的目的是通过多中心数据库开发和验证基于图像重建的结构化报告生成系统（ISRGS），并评估其诊断性能。首先，我们开发和评估了ISRGS结合实时视频捕获，网站识别，病变检测，子特征分析，结构化报告生成。GI病变患者的白色光和色素内镜图像符合研究入选条件。共使用来自9家三级医院的46，987张图像进行训练，验证和多中心测试（6：2：2）。此外，前瞻性地从山东大学齐鲁医院招募了5，699张图像，以在前瞻性测试集中进一步评估该系统。主要结局是多中心和前瞻性试验中GI病变的诊断性能。早期食管癌、早期胃癌、早期结直肠癌、食管静脉曲张、反流性食管炎、Barrett食管、慢性萎缩性胃炎、胃溃疡、结直肠息肉和溃疡性结肠炎的总体准确率为0.8841（95%可信区间0.8775-0.8904）和0.8965（0.8883-0.9041）。对盲肠和上消化道部位的识别准确率分别为0.9978（0.9969-0.9984）和0.8513（0.8399-0.8620）。染色判别准确率为0.9489（0.9396-0.9568）。粒度测量的相对误差为4.04%（范围0.75%-7.39%）。ISRGS是一种可靠的计算机辅助内窥镜报告生成系统，可帮助在不同医院级别工作的内窥镜医师生成标准化和准确的内窥镜报告（http：//links.lww.com/CTG/A485）。
Conventional gastrointestinal (GI) endoscopy reports written by physicians are time consuming and might have obvious heterogeneity or omissions, impairing the efficiency and multicenter consultation potential. We aimed to develop and validate an image recognition–based structured report generation system (ISRGS) through a multicenter database and to assess its diagnostic performance. First, we developed and evaluated an ISRGS combining real-time video capture, site identification, lesion detection, subcharacteristics analysis, and structured report generation. White light and chromoendoscopy images from patients with GI lesions were eligible for study inclusion. A total of 46,987 images from 9 tertiary hospitals were used to train, validate, and multicenter test (6:2:2). Moreover, 5,699 images were prospectively enrolled from Qilu Hospital of Shandong University to further assess the system in a prospective test set. The primary outcome was the diagnosis performance of GI lesions in multicenter and prospective tests. The overall accuracy in identifying early esophageal cancer, early gastric cancer, early colorectal cancer, esophageal varices, reflux esophagitis, Barrett’s esophagus, chronic atrophic gastritis, gastric ulcer, colorectal polyp, and ulcerative colitis was 0.8841 (95% confidence interval, 0.8775–0.8904) and 0.8965 (0.8883–0.9041) in multicenter and prospective tests, respectively. The accuracy of cecum and upper GI site identification were 0.9978 (0.9969–0.9984) and 0.8513 (0.8399–0.8620), respectively. The accuracy of staining discrimination was 0.9489 (0.9396–0.9568). The relative error of size measurement was 4.04% (range 0.75%–7.39%). ISRGS is a reliable computer-aided endoscopic report generation system that might assist endoscopists working at various hospital levels to generate standardized and accurate endoscopy reports (http://links.lww.com/CTG/A485).
登录
查看更多内容
影响因子：
5.7
作者：
Hamashima C;Goto R
通讯作者：
Goto R
影响因子：
9.3
作者：
Bretthauer, Michael;Aabakken, Lars;Rutter, Matthew D.
通讯作者：
Rutter, Matthew D.
影响因子：
7.7
作者：
Jamil, Laith H.;Naveed, Mariam;Wani, Sachin B.
通讯作者：
Wani, Sachin B.
影响因子：
9.8
作者：
Nagami, Yasuaki;Tominaga, Kazunari;Machida, Hirohisa;Nakatani, Masami;Kameda, Natsuhiko;Sugimori, Satoshi;Okazaki, Hirotoshi;Tanigawa, Tetsuya;Yamagami, Hirokazu;Kubo, Naoshi;Shiba, Masatsugu;Watanabe, Kenji;Watanabe, Toshio;Iguchi, Hiroyoshi;Fujiwara, Yasuhiro;Ohira, Masaichi;Hirakawa, Kosei;Arakawa, Tetsuo
通讯作者：
Arakawa, Tetsuo
影响因子：
24.5
作者：
Byrne MF;Chapados N;Soudan F;Oertel C;Linares Pérez M;Kelly R;Iqbal N;Chandelier F;Rex DK
通讯作者：
Rex DK