Xu Xin, Ba Ling, Lin Lin, Song Yan, Zhao Chunshan, Yao Shuangzhe, Cao Hailong, Chen Xin, Mu Jinbao, Yang Lu, Feng Yue, Wang Yufeng, Wang Bangmao, Zheng Zhongqing
Department of Gastroenterology and Hepatology, Tianjin Medical University General Hospital, Anshan Road No.154, Tianjin, 300052, China.
Tianjin Yujin Artificial Intelligence Medical Technology Co.,Ltd, Tianjin, China.
Surg Endosc. 2025 Sep 2. doi: 10.1007/s00464-025-12080-x.
INTRODUCTION: Colorectal cancer (CRC) ranks as the second deadliest cancer globally, impacting patients' quality of life. Colonoscopy is the primary screening method for detecting adenomas and polyps, crucial for reducing long-term CRC risk, but it misses about 30% of cases. Efforts to improve detection rates include using AI to enhance colonoscopy. This study assesses the effectiveness and accuracy of a real-time AI-assisted polyp detection system during colonoscopy. MATERIALS AND METHODS: The study included 390 patients aged 40 to 75 undergoing colonoscopies for either colorectal cancer screening (risk score ≥ 4) or clinical diagnosis. Participants were randomly assigned to an experimental group using software-assisted diagnosis or a control group with physician diagnosis. The software, a medical image processing tool with B/S and MVC architecture, operates on Windows 10 (64-bit) and supports real-time image handling and lesion identification via HDMI, SDI, AV, and DVI outputs from endoscopy devices. Expert evaluations of retrospective video lesions served as the gold standard. Efficacy was assessed by polyp per colonoscopy (PPC), adenoma per colonoscopy (APC), adenoma detection rate (ADR), and polyp detection rate (PDR), while accuracy was measured using sensitivity and specificity against the gold standard. RESULTS: In this multicenter, randomized controlled trial, computer-aided detection (CADe) significantly improved polyp detection rates (PDR), achieving 67.18% in the CADe group versus 56.92% in the control group. The CADe group identified more polyps, especially those 5 mm or smaller (61.03% vs. 56.92%). In addition, the CADe group demonstrated higher specificity (98.44%) and sensitivity (95.19%) in the FAS dataset, and improved sensitivity (95.82% vs. 77.53%) in the PPS dataset, with both groups maintaining 100% specificity. These results suggest that the AI-assisted system enhances PDR accuracy. CONCLUSION: This real-time computer-aided polyp detection system enhances efficacy by boosting adenoma and polyp detection rates, while also achieving high accuracy with excellent sensitivity and specificity.
引言：结直肠癌（CRC）是全球第二大致命癌症，影响患者生活质量。结肠镜检查是检测腺瘤和息肉的主要筛查方法，对降低长期CRC风险至关重要，但仍有大约30%的病例会被漏诊。提高检测率的努力包括使用人工智能来增强结肠镜检查。本研究评估了一种实时人工智能辅助息肉检测系统在结肠镜检查中的有效性和准确性。 材料与方法：该研究纳入了390名年龄在40至75岁之间因结直肠癌筛查（风险评分≥4）或临床诊断而接受结肠镜检查的患者。参与者通过软件辅助诊断被随机分配到实验组，或通过医生诊断被分配到对照组。该软件是一种具有B/S和MVC架构的医学图像处理工具，运行于Windows 10（64位）系统，支持通过内窥镜设备的HDMI、SDI、AV和DVI输出进行实时图像处理和病变识别。对回顾性视频病变的专家评估作为金标准。通过每例结肠镜检查的息肉数（PPC）、每例结肠镜检查的腺瘤数（APC）、腺瘤检出率（ADR）和息肉检出率（PDR）评估疗效，同时使用针对金标准的敏感性和特异性来衡量准确性。 结果：在这项多中心随机对照试验中，计算机辅助检测（CADe）显著提高了息肉检出率（PDR），CADe组达到67.18%，而对照组为56.92%。CADe组发现了更多息肉，尤其是那些5毫米及以下的息肉（61.03%对56.92%）。此外，CADe组在FAS数据集中表现出更高的特异性（98.44%）和敏感性（95.19%），在PPS数据集中敏感性有所提高（95.82%对77.53%），两组特异性均保持在100%。这些结果表明，人工智能辅助系统提高了PDR准确性。 结论：这种实时计算机辅助息肉检测系统通过提高腺瘤和息肉检出率增强了疗效，同时在敏感性和特异性方面也具有很高的准确性。
Ther Adv Gastrointest Endosc. 2025-8-30
Lancet Gastroenterol Hepatol. 2021-10
Chin Med J (Engl). 2024-6-20
Gastrointest Endosc. 2024-10
Nat Rev Gastroenterol Hepatol. 2024-2
Zotero 插件