新型人工智能辅助结肠镜诊断复合模型对结肠常见病变诊断价值的临床研究

目的 研究新型人工智能辅助结肠镜诊断复合模型对常见结肠病变的诊断价值。方法 前瞻性地收集大量高质量结肠镜内镜下检测的完整视频，作为分析验证数据，以模拟临床实时使用人工智能辅助结肠镜诊断复合模型行结肠镜检查的环境，评价该复合模型在结肠常见病变中的诊断效能。结果 将模型测试结果与病理结果对比，该模型对病变整体诊断的准确度、特异度、灵敏度分别为95.5%、90.6%和96.8%。在不同病变类型中，对腺瘤性息肉诊断的准确度、敏感度、特异度分别为95.9%、90.4%和98.4%;非腺瘤性息肉诊断的准确度、敏感度和特异度分别为97.9%、90.5%、99.4%;对结直肠癌的准确度、敏感度、特异度分别为94.0%、94.4%、92.6%;对结肠憩室诊断的准确度、敏感度、特异度分别为97.2%、91.8%、98.7%;对溃疡性结肠炎的准确度、敏感度和特异度分别为93.7%、87.7%和94.5%;对结直肠黏膜下肿物诊断的准确性相对较低为91.8%,敏感度和特异度分别为84.0%、93.4%。结论 本团队研发的新型人工智能辅助结肠镜诊断复合模型可准确快速识别包括腺瘤性息肉、非腺瘤性息肉、结直肠癌、结肠...     

基于人工智能的结肠镜质量控制研究进展

近年来，人工智能技术在医学领域快速发展，并在多个领域取得了显著成就。人工评估结肠镜质量不仅浪费时间还存在主观偏差和错误，因此很难进一步提高腺瘤检出率，导致结直肠癌发生率仍然较高。人工智能技术在临床试验中表明，计算机辅助技术有助于客观评估结肠镜质量，提高病变检出率。本文就人工智能技术在结肠镜质量控制中的相关研究进行系统性阐述。     

人工智能技术在结肠镜退镜速度实时监控中的应用

目的构建一种基于计算机视觉的结肠镜退镜速度实时监控系统,并验证其可行性和性能。方法从武汉大学人民医院消化内镜中心数据库选取2018年5—10月期间的35938张肠镜图片和63个结肠镜检查视频。肠镜图片分成体外/体内/不合格和回盲部/非盲肠两个数据集,分别从第一个、第二个数据集中选取3594张和2000张图片用于深度学习模型的测试,其余图片用于训练模型;选取3个结肠镜检查视频资料评价实时监控系统自动监控退镜速度的可行性,剩余60个结肠镜检查视频资料用于评估实时监控系统的性能。结果深度学习模型对于结肠镜检查图片分类识别体外/体内/不合格图片的准确率分别为90.79%(897/988)、99.92%(1300/1301)、99.08%(1293/1305),总体准确率为97.11%(3490/3594);分类识别回盲部/非盲肠图片的准确率分别为96.70%(967/1000)、94.90%(949/1000),总体准确率为95.80%(1916/2000)。在其可行性评价方面,3个结肠镜视频资料显示退镜速度与图片处理间隔时间呈线性关系,提示该监控系统可在结肠镜退出过程中自动监控退镜速度。在其性能评价方面,结肠镜退镜速度实时监控系统正确预测了所有60个肠镜检查的开始时间和结束时间,分析显示结肠镜平均退镜速度和退镜时间呈明显负相关(R=-0.661,P<0.001),退镜时间不足5 min、5~6 min和超过6 min视频的平均退镜速度的95%置信区间分别为43.90~49.74、40.19~45.43和34.89~39.11,故将39.11设为安全退镜速度,将45.43设为预警退镜速度。结论构建的结肠镜退镜速度实时监控系统可用于实时监控结肠镜退镜速度,可在结肠镜检查中辅助内镜医师进行实时监测,以提高结肠镜检查质量。     

人工智能辅助结肠镜检查在下消化道病变的应用进展

随着我国科技的进步及人民生活质量的逐渐提高,结直肠癌已跃升为前五高发的癌症,严重影响人民的健康及预期寿命。结直肠癌的形成需要一个很漫长的过程,因此,早发现、早诊断及早治疗极其重要,其中规范化的结肠镜检查是发现早期结直肠癌最有效的方法。近年来,人工智能辅助消化内镜检查正成为研究的热点,其应用在结直肠癌早诊早治方面有明显的成效。本文就人工智能辅助结肠镜检查的优缺点及存在的问题进行综述,并对未来人工智能辅助内镜诊断结直肠癌中的应用方向进行展望。     

人工智能在诊断结直肠癌癌前病变中的应用

人工智能(artificial intelligence, AI)与深度卷积神经网络(convolutional neural networks, CNN)的出现极大推动了医学中图像分析领域的发展，特别是在消化道内镜中，使其在癌前病变的发现及鉴别中具有较高的应用价值。近期研究表明，计算机辅助诊断技术使结直肠腺瘤的检出率及息肉光学组织学诊断的准确性大幅度提高，从而指导结直肠息肉的治疗及随访。本文就当前关于计算机辅助诊断技术在识别并鉴别结直肠癌癌前病变中的研究进展作一综述。     

异丙酚静脉麻醉辅助结肠镜检查的应用研究

目的 探讨应用异丙酚作镇静麻醉辅助结肠镜检查的可行性，评价其效果和安全性。方法 将2210例结肠镜检查患者随机分为2组：麻醉组（2000例）静脉注射异丙酚至患者进入4级镇静状态后进行结肠镜检查。对照组（210例）按常规进行结肠镜检查。观察2组检查前，检查开始后1，5，20min和检查结束后的血压，脉搏，血氧饱和度以及检查反应和入镜时间。结果 检查过程中，麻醉组的平均收缩压各时段无明显变化（P＞0．05），对照组变化明显（P＜0．01）。2组的平均舒张压，脉搏和血氧饱和度在相应各时段的变化均无显著性差异（P＞0．05）。麻醉组的入镜时间和检查反应明显优于对照组（P＜0．01）。结论 异丙酚辅助结肠镜检查是安全有效，其入镜时间和检查反应优于普通检查。     

计算机辅助检测系统提高腺瘤检出率的回顾性研究

目的　探讨基于双流算法开发的新型息肉检测系统在结肠镜检查中的作用。方法　研究回顾性纳入2023年3月至6月解放军总医院第一医学中心在计算机辅助检测（computer‑aided detection,CADe）系统辅助下行结肠镜检查的833例受试者为试验组,2022年3月至6月在同一操作间接受常规结肠镜检查的770例受试者为对照组。主要观察指标是腺瘤检出率,次要观察指标包括息肉检出率、腺瘤检出数和息肉检出数。结果　试验组腺瘤检出率［29.3%（244/833）比21.7%（167/770）,χ2=12.133,P<0.001］和息肉检出率［47.9%（399/833）比37.9%（292/770）,χ2=16.241, P<0.001］显著高于对照组。对于≤5 mm的腺瘤［23.5%（196/833）比16.1%（124/770）,χ2=13.808,P<0.001］和平坦型腺瘤［15.1%（126/833）比7.3%（56/770）, χ2=24.519, P<0.001］,试验组检出率显著高于对照组。试验组每例腺瘤检出数［0（0,1）枚比0（0,1）枚,Z=-3.698,P<0.001］和每例息肉检出数［0（0,1）枚比0（0,1）枚,Z=-4.424,P<0.001］与对照组相比差异有统计学意义。与无CADe系统辅助相比,CADe系统显著提高低年资医师腺瘤检出率［29.5%（167/566）比18.9%（89/472）, χ2=15.709, P<0.001］和息肉检出率［47.3%（268/566）比33.3%（157/472）,χ2=21.123,P<0.001］;在高年资医师中,有无CADe系统辅助的腺瘤检出率［28.8%（77/267）比26.2%（78/298）,χ2=0.502,P=0.479］ 和息肉检出率［49.1%（131/267）比45.3%（135/298）,χ2=0.800,P=0.371］差异无统计学意义。结论　CADe系统可显著提高腺瘤和息肉的检出率,尤其对于微小和平坦型病变检出具有明显优势。低年资医师相较于高年资医师使用CADe系统的获益更大。     

人工智能在结直肠息肉性质鉴别中的应用进展

在信息化和智能化浪潮的推动下,计算机辅助内镜下病变的发现和鉴别因具有较高的诊断准确率而日益受到关注,特别是深度学习和卷积神经网络的出现,极大推动了智能化内镜的发展。结直肠息肉的人工智能化检测,是人工智能消化内镜应用领域中发展最快的方向,近年来不断涌现结直肠息肉智能检测和性质鉴别的突破性研究成果。本文就目前国内外关于计算机辅助诊断和人工智能在结直肠息肉性质鉴别中的研究进展进行综述。     

结肠镜检查对直肠溃疡的诊断价值

直肠溃疡由多种疾病所致,其临床表现相似,但凭临床表现,确定其病因不无困难。本文回顾性分析我院1988年4月至2001年4月期间收集的68例直肠溃疡病例,分析结肠镜检查对直肠溃疡病因诊断价值。 1.一般情况:在68例病例中,男44例(64.7％);女24列(35.3％)。年龄6～81岁,平均(47.8±16.0)岁。 2.最后诊断:(1)溃疡性直肠炎25例,占38.2％,其最后     

Artificial intelligence in colonoscopy

Colorectal cancer remains a leading cause of morbidity and mortality in the United States. Advances in artificial intelligence (AI), specifically computer aided detection and computer-aided diagnosis offer promising methods of increasing adenoma detection rates with the goal of removing more pre-cancerous polyps. Conversely, these methods also may allow for smaller non-cancerous lesions to be diagnosed in vivo and left in place, decreasing the risks that come with unnecessary polypectomies. This review will provide an overview of current advances in the use of AI in colonoscopy to aid in polyp detection and characterization as well as areas of developing research.     

肠镜人工智能系统临床应用专家共识（2023，武汉）

肠镜是检出、诊断和治疗结直肠癌及癌前病变、炎症性肠病等疾病的临床一线工具。人工智能技术在肠镜的质量控制和辅助诊断中起到重要作用,但国内外至今尚无肠镜人工智能系统临床应用的相关共识。2023年中华医学会消化内镜学分会大数据协作组组织全国领域内权威专家讨论,结合国内外最新循证医学证据,形成肠镜人工智能系统临床应用专家共识意见,旨在为临床医师应用肠镜人工智能时提供合理的决策依据。共识意见包括人工智能在肠道准备评估、息肉识别、息肉分型、退镜质量控制等9个部分的应用推荐,共12条陈述,以及肠镜人工智能系统临床应用要求。     

Use of artificial intelligence in improving adenoma detection rate during colonoscopy: Might both endoscopists and pathologists be further helped

Colonoscopy remains the standard strategy for screening for colorectal cancer around the world due to its efficacy in both detecting adenomatous or precancerous lesions and the capacity to remove them intra-procedurally. Computeraided detection and diagnosis(CAD), thanks to the brand new developed innovations of artificial intelligence, and especially deep-learning techniques, leads to a promising solution to human biases in performance by guarantying decision support during colonoscopy. The application of CAD on real-time colonoscopy helps increasing the adenoma detection rate, and therefore contributes to reduce the incidence of interval cancers improving the effectiveness of colonoscopy screening on critical outcome such as colorectal cancer related mortality. Furthermore, a significant reduction in costs is also expected. In addition, the assistance of the machine will lead to a reduction of the examination time and therefore an optimization of the endoscopic schedule. The aim of this opinion review is to analyze the clinical applications of CAD and artificial intelligence in colonoscopy, as it is reported in literature, addressing evidence, limitations, and future prospects.     

人工智能在肺结节良恶性鉴别诊断中的价值分析

目的评价人工智能(artificial intelligence, AI)风险评估对肺结节良恶性鉴别诊断的价值。 方法收集2018年8月至2019年12月唐都医院行胸部CT检查，发现肺结节患者310例，将患者CT影像数据DICOM文件拷贝输入到"FACT人工智能"软件系统对结节进行分析，获得结节的部位、数量、特征(磨玻璃、亚实性、实性)、大小、密度、以及恶性风险概率AI值和Lung-rads分级；其中39例肺结节经过多学科讨论，建议采用外科手术、经皮肺穿刺或者支气管镜下活检等，271例患者进行随访。 结果31例肺结节病理诊断良性14例，分别为结核8例，隐球菌2例，炎性结节4例；恶性25例，分别肺鳞癌2例，腺癌23例。进一步分析，恶性病变的AI风险概率明显高于良性病变(P<0.05)；结节AI风险概率与肺结节特点(磨玻璃、亚实性、实性)显著相关(P<0.05)，而与数量及边缘毛刺征无显著相关性(P>0.05)；肺结节特点(磨玻璃、亚实性、实性)在良恶性之间存在显著性差异(P<0.05)，而密度和体积之间在在良恶性之间无显著性差异(P>0.05)。肺结节Lung-rads分级与AI风险概率之间具有显著的相关性(P<0.05)。 结论依据人工智能自动分析良恶性概率AI值对肺结节良恶性鉴别诊断具有一定的价值，值得临床借鉴。     

人工智能在消化内镜中的临床应用现状

随着人工智能（artificial intelligence,AI）技术的不断发展,以大数据为支撑兼具强大计算能力和学习能力的AI技术已用于解决复杂的医学问题。利用AI分析大量非结构化医学数据,并执行临床任务,开始出现在胃肠镜检查中。即使与专业的内镜医师相比,AI技术也能够表现出优异的灵敏度和准确率,计算机辅助检查和计算机辅助诊断技术有望改变传统的内镜检查模式。本文就AI技术在消化系统内镜中的应用进行探讨。     

Artificial intelligence technologies for the detection of colorectal lesions: The future is now

Several studies have shown a significant adenoma miss rate up to 35% during screening colonoscopy, especially in patients with diminutive adenomas. The use of artificial intelligence(AI) in colonoscopy has been gaining popularity by helping endoscopists in polyp detection, with the aim to increase their adenoma detection rate(ADR) and polyp detection rate(PDR) in order to reduce the incidence of interval cancers. The efficacy of deep convolutional neural network(DCNN)-based AI system for polyp detection has been trained and tested in ex vivo settings such as colonoscopy still images or videos. Recent trials have evaluated the real-time efficacy of DCNN-based systems showing promising results in term of improved ADR and PDR. In this review we reported data from the preliminary ex vivo experiences and summarized the results of the initial randomized controlled trials.     

人工智能专家系统在呼吸系统疾病诊治中的应用进展

人工智能是电子计算机应用的重要方面,医学专家系统是人工智能在医学方面的重要应用分支。本文对人工智能专家系统的概念、结构、发展及其在呼吸病诊治中的应用和评价进行综述。     

Utilization of artificial intelligence for tuberculosis screening in Nepal

Backgrounds: Tuberculosis (TB) is an infectious disease that needs to be diagnosed and enrolled for treatment. Artificial intelligence for TB (AI4TB) software screens TB suspected cases at the point of care and helps in quick diagnosis. This study aims to explore the significance and usefulness of AI4TB by comparing its performance with different diagnostic test results.MethodsA cross-sectional study was conducted among 197 participants who had symptoms suggestive to TB. The chest X-ray images were analyzed by AI4TB software and human expert readers. The bacteriological test results were obtained, and Kappa test was applied to calculate the inter-reader reliability. The sensitivity, specificity, positive predictive value and negative predictive value was calculated and ROC curve was generated.ResultsAmong 85 sputum smear microscopy, about 21% of the had sputum positivity rate. At 0.4 threshold: 62.4%, at 0.5 threshold: 58.4% and at 0.6 threshold: 50.3% symptoms suggestive cases were identified having abnormal X-ray images. Reader-I identified 28.4% and Reader-II identified 37.1% of the symptoms suggestive cases of TB as positive cases. There was a significant substantial agreement between two human expert readers (k-0.783, p-value: <0.001). The ROC curve explored the fair sensitivity accuracy of the AI4TB test results at 0.5 threshold level (AUC = 0.72) and at 0.6 threshold level (AUC = 0.77).ConclusionThe sensitivity of the AI4TB was higher compared to different human readers. AI4TB can be the relevant screening tool for the TB symptoms suggestive cases prior to the laboratory test in the countries like Nepal with deficient health manpower.