摘要
一位新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-人工智能的新研究是一篇报道的主题。根据NewsRx记者来自中华人民共和国重庆的新闻报道，研究表明，“尽管人工智能(AI)在小肠(SB)胶囊内镜(CE)图像读取方面有好处，但缺乏关于其在胃和SB CE中的应用的信息。在这项多中心回顾性诊断研究中，胃成像数据被添加到基于深度学习(DL)的SmartScan(SS)中，该研究已经描述过。”新闻记者从第三军医大学的研究中获得一句话：“总共使用了1069个磁控胃肠道(GI)CE检查(包括2672542个胃图像)来识别胃病变，产生了一种新的AI算法，命名为SS P LUS 342全自动，验证阶段采用磁控CE(FAMCE)检查。评估高级和初级Endos Copist在SS Plus辅助阅读(SSP-AR)和常规阅读(CR)模式下的表现。SS Plus设计用于识别5种类型的胃病变和17种类型的SB病变。SS Plus将需要审查的CE图像数量减少到873.90(1000)(中位数，中位数，CR的IQR为814.50-1,000)与44322.73(42,393)(中位数，IQR为31,722.75-54,971.25)。此外，使用SP-AR，内镜检查时间为9.54分钟(8.51)(中位数，IQR为6.05-13.13)，在342个CE视频中，SS Plus识别出411个胃和422个SB病变，其中400个胃
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Artificial Intelligenc e is the subject of a report. According to news reporting originating in Chongqi ng, People's Republic of China, by NewsRx journalists, research stated, "Despite the benefits of artificial intelligence (AI) in small bowel (SB) capsule endosc opy (CE) image reading, information on its application in the stomach and SB CE is lacking. In this multicenter, retrospective diagnostic study, gastric imaging data were added to the deep learning (DL)-based SmartScan (SS), which has been described previously." The news reporters obtained a quote from the research from Third Military Medica l University, "A total of 1,069 magnetically controlled gastrointestinal (GI) CE examinations (comprising 2,672,542 gastric images) were used in the training ph ase for recognizing gastric pathologies, producing a new AI algorithm named SS P lus. 342 fully automated, magnetically controlled CE (FAMCE) examinations were i ncluded in the validation phase. The performance of both senior and junior endos copists with both the SS Plus- Assisted Reading (SSP-AR) and conventional reading (CR) modes was assessed. SS Plus was designed to recognize 5 types of gastric l esions and 17 types of SB lesions. SS Plus reduced the number of CE images requi red for review to 873.90 (1000) (median, IQR 814.50-1,000) versus 44,322.73 (42, 393) (median, IQR 31,722.75-54,971.25) for CR. Furthermore, with SSP-AR, endosco pists took 9.54 min (8.51) (median, IQR 6.05-13.13) to complete the CE video rea ding. In the 342 CE videos, SS Plus identified 411 gastric and 422 SB lesions, w hereas 400 gastric and 368 intestinal lesions were detected with CR. Moreover, j unior endoscopists remarkably improved their CE image reading ability with SSP-A R."
NETL
NSTL