MD  >> Vol. 9 No. 2 (June 2019)

作者:  

于红梅,武建强:内蒙古医科大学,内蒙古 呼和浩特

关键词:
小型结直肠息肉光学诊断ASGESmall Colorectal Polyp Optical Diagnosis ASGE

摘要:

最近提出了小型结肠直肠息肉的光学诊断作为代替组织病理学诊断的方案。随着新分类系统的成像技术和人工智能的使用,增加了光学诊断的可行性。本综述提供了光学诊断建议,分类,结果和最新发展的最新概述。用于光学诊断小型息肉的质量基准。NICE分类已经过广泛研究并符合大多数成像技术的检测标准,但不能够诊断无柄锯齿状息肉(SSPs)。SIMPLE分类符合NBI和i-Scan的质量基准,可用于SSP的诊断。需要进一步研究其他分类系统以验证有效性。计算机辅助诊断结直肠息肉是一项非常重要的方法,患者实时结肠镜检查的质量基准正得到满足。限制包括不可忽略的诊断失败百分比,低特异性和低数量的实时诊断研究。需要进行更多研究以进一步了解人工智能的价值光学息肉诊断的一般性。总结小型结直肠息肉的光学诊断具有可行性,增强内窥镜检查并结合人工智能的诊断可以使光学诊断广泛适用,但目前处于早期发育阶段。

An optical diagnosis of small colorectal polyps has recently been proposed as a replacement for histopathological diagnosis. With the use of imaging technology and artificial intelligence in the new classification system, the feasibility of optical diagnosis has increased. This review provides an up-to-date overview of optical diagnostic recommendations, classifications, results and recent developments. Benchmark is for optical diagnosis of small polyps. The NICE classification has been extensively studied and meets the quality requirements of most imaging techniques, but it is not possible to diagnose sessile serrated polyps (SSPs). The SIMPLE classification meets the quality benchmarks of NBI and i-Scan and can be used for the diagnosis of SSP. Further research on other classification systems is needed to verify validity. Computer-aided diagnosis of colorectal polyps is a very important method, and the quality benchmark for patients with real-time colonoscopy is being met. Limitations include non-negligible percentage of diagnostic failures, low specificity and low numbers of real-time diagnostic studies. More research is needed to further understand the generality of the value of optical optometry diagnostics for artificial intelligence. It is feasible to summarize the optical diagnosis of small colorectal polyps. Enhanced endoscopy and combined with artificial intelligence diagnosis can make optical diagnosis widely applicable, but it is currently in the early development stage. 

1. 背景

对于小于或等于5 mm或小于或等于10 mm结肠息肉的组织病理学检查是昂贵而且耗时的,给患者带来了经济压力 [1] 。小肠结肠息肉的恶性潜能极低,低于2%具有晚期组织学,其中约0.05%含有高度异型增生或瘤形成,小结肠息肉具有更高的潜力 [2] 。高达7%的患者对恶性肿瘤能够用病理学诊断检测,这种息肉的组织学评估可能会被图像增强的光学诊断所取代,以预测病理学结肠镜检查期间结肠息肉。这种方法被称为切除和丢弃策略,可以为结肠镜检查实践提供显着的成本节约 [3] 。多个胃肠病学会建议实施光学息肉诊断,此诊断方法使用经验证的颜色的分类进行光学诊断。随着图像增强内窥镜的最新进展,分类系统和人工智能息肉的光学诊断可能为广泛的临床实施获得新的动力 [4] 。本次审查的目的是概述该领域的光学诊断分类和最新发展。

2. ASGE建议

为了在没有组织学评估的情况下丢弃小的息肉,美国胃肠内镜学会(ASGE)建议基于病理学和阴性预测值高于90%的监测间隔高于90%一致。最近的meta分析表明,在经验丰富的内镜医师手中,实时光学诊断结直肠息肉与基于组织病理学的监测间隔提供93%的一致性,阴性预测值超过90% [5] 。最近一项随机对照试验在五位内镜医师发现后,发现ASGE阈值在下半年得到满足。他们的研究对于标准视图和近视结肠镜检查有着高可信度诊断。在近景和标准视图类别中,高可信度诊断率分别为85.1%和72.6%,虽然ASGE的总体建议正在达到或超过,但内镜医师级别的结果可能会有所不同 [6] 。在同一项研究中,一名内镜医师没有达到ASGE关于近视结肠镜检查的建议而另一名不符合建议。标准视野结肠镜检查为一项前瞻性研究(N = 27名内镜医师)的结果相似,其中ASGE阈值总体得到满足,但只有59%的内镜医师达到了这一阈值 [7] 。虽然受过充分训练的内镜医师的总体结果很有希望,但是根据内镜医师的技术,满足ASGE采用切除和丢弃策略的建议的能力仍然存在很大差异。因此,重要的是要充分培训内镜医师进行光学诊段可以替换病理学诊断 [8] 。已经发现教学模块可以有效地提高未经训练的内窥镜技能并达到所需的阈值,有可能建立年度光学诊断或性能培训研讨会,以确保取得足够的成果。当使用NBI成像时,目前通常会满足ASGE阈值。ASGE目前建议使用NBI进行光学诊断和切除以及丢弃策略 [9] 。

FICE和常规染色内镜检查用于小型结直肠息肉的光学诊断,作为组织病理学诊断的替代,它进一步建议光学诊断应该只在严格控制的环境中由经验丰富,训练有素的人员进行,和经过审核的内镜医师使用经过验证的量表进行诊断 [10] 。在尝试光学诊断时也应该执行大量的照片文档。ESGE没有提出关于准确度或NPV等质量指标的建议。该策略包括消除对息肉的病理检查的需要和减少对患者进行的干预的量。主要缺点是误诊的可能性 [11] 。

留下患者的腺瘤。为了避免这种情况,内镜医师需要在诊断期间获得腺瘤的高NPV。无论建议如何,这种策略通常由内镜医师根据患者的临床情况在临床实践中使用 [12] 。ASGE指出,直肠乙状结肠息肉可以在结肠中发生,如果没有切除,诊断技术对腺瘤的NPV应 ≥ 90%。他们进一步指出,NBI诊断结果足以支持直肠乙状结肠息肉的“诊断和离开”策略的使用 [13] 。

为了使结肠直肠息肉的光学诊断标准化,在结肠镜检查期间使用多种分类来对息肉进行分类,新开发的成像技术已经允许创建适合他们的诊断标准 [14] 。增生性息肉,腺瘤之间的分化mas,和无柄锯齿状息肉(SSPs)最近导致更新的分类系统识别这样的病变NICE分类它用颜色和血管和表面图案,以区分腺瘤性和增生性息肉使用此分类的一个限制是它不包括SSP诊断标准 [15] 。当应用于FICE成像技术时,NICE分类显示出与病理学的整体一致性较低,这可以部分解释为NICE分类的颜色标准,不适合FICE成像作为次优对比度 [16] 。

3. 光学分析方法

为光学分析方法是一类以光辐射能与物质相互作用(发光、吸收、散射、光电子发射等)为基础的分析方法。属于仪器分析方法中的一类重要方法,可以分为光谱法和非光谱法两大类。光谱分析法,系以光辐射能与物质组成和结构之间的内在联系及其表现形式——光谱(或波谱)的测量为基础。非光谱分析法,它不包含物质内能的变化,而是基于物质引起辐射方向和物理性质的改变 [17] 。

光谱法又可分为三种基本类型:① 发光光谱法。包括原子发射光谱分析法、原子荧光光谱法、分子荧光分析法、X射线荧光分析法、电子能谱分析法等。② 吸收光谱法。包括紫外可见分光光度法、红外分光光度法、电子自旋共振和核磁共振光谱法、穆斯保尔谱法、原子吸收光谱法等。③散射光谱法。主要有拉曼散射光谱法。非光谱法包括折射法、偏振法、旋光色散法、圆二向色散法、X射线衍射法和浊度分析法等 [18] 。

4. 结直肠癌诊断的最新发展

随着内镜技术的发展尤其是窄带成像技术(NBI)可提供可靠的实时内镜下光学诊断。根据已公布的诊断标准,运用窄带成像下近焦和标准视野两种光学诊断模式做出光学诊断并得到对应的可信度值。最终研究目标是两组对比得到的组织病理诊断后其精确的高可信度光学诊断的数目 [19] 。对于大部分结直肠小息肉,窄带成像结肠镜下实时光学诊断能够代替病理诊断,近焦诊断模式增加了光学诊断可信度水准。同时提到,对于广基锯齿状息肉,来源于右侧结肠的鉴于目前内镜诊断的低可靠性,一律应做病理诊断 [20] 。光学诊断为结肠癌内镜筛选提供了典范式的改革。该研究的意义在于其在研究内镜光学诊断模式上前瞻性实验设计的尝试,为我们获得高可信度临床内镜下光学诊断提供了重要依据。同时也提醒我们高质量内镜实践训练对于NBI近焦辨认度光学诊断同样十分关键,而且能够为病人减少不必要的病理检查、咨询随访的费用和院外监测的压力 [21] 。

5. 结论

光学诊断领域正在推进新的社会准则,分类和成像技术的发展。NBI正在达到质量指标阈值,其他成像技术仍需要进一步的研究和培训。随着自发荧光和人工智能/深度学习辅助光学诊断的兴起,息肉的自动计算机辅助诊断正在出现。深度学习仍处于初期阶段,需要进一步研究以更好地了解其对光学息肉诊断的广泛临床实施的价值。此外,光学技术提高内镜诊断水平的优势为提高分辨率。

文章引用:
于红梅, 武建强. 结直肠癌的光学诊断[J]. 医学诊断, 2019, 9(2): 52-56. https://doi.org/10.12677/MD.2019.92010

参考文献

[1] Backes, Y., Schwartz, M.P., Ter, F.B., et al. (2018) Multicentre Prospective Evaluation of Real-Time Optical Diagnosis of T1 Colo-rectal Cancer in Large Non-Pedunculated Colorectal Polyps Using Narrow Band Imaging (the OPTICAL Study). Gut, 68, 271-279.
https://doi.org/10.1136/gutjnl-2017-314723
[2] Vleugels, J.L.A., Greuter, M.J.E., Hazewinkel, Y., Coupé, V.M.H. and Dekker, E. (2017) Implementation of an Optical Diagnosis Strategy Saves Costs and Does Not Impair Clinical Outcomes of a Fecal Im-munochemical Test-Based Colorectal Cancer Screening Program. Endoscopy International Open, 5, E1197-E1207.
https://doi.org/10.1055/s-0043-113565
[3] Von, R.D., Kaltenbach, T., Rastogi, A., et al. (2017) Simplifying Resect and Discard Strategies for Real-Time Assessment of Diminutive Colorectal Polyps. Clinical Gastroenterology & Hepatology, 16, 706-714.
[4] Carvalho, S., Gueiral, N., Nogueira, E., et al. (2017) Glucose Diffusion in Colorectal Mucosa: A Comparative Study between Normal and Cancer Tissues. Journal of Biomedical Optics, 22, 91506.
[5] Amit, R. (2013) Optical Diagnosis of Small Colorectal Polyp Histology with High-Definition Colonoscopy Using Narrow Band Imaging. Clinical Endoscopy, 46, 120-129.
https://doi.org/10.5946/ce.2013.46.2.120
[6] Vlugt, M.V.D., Doorn, S.C.V., Wang, J., et al. (2016) Optical Diagnosis of Ma-lignant Colorectal Polyps: Is It Feasible? Endoscopy International Open, 4, E778-E783.
https://doi.org/10.1055/s-0042-107667
[7] Wilson, A. (2015) Optical Diagnosis of Small Colorectal Polyps during Colonos-copy: When to Resect and Discard? Best Practice & Research Clinical Gastroenterology, 29, 639-649.
https://doi.org/10.1016/j.bpg.2015.06.007
[8] Gupta, N., Early, D.S., Bansal, A., et al. (2012) Tu1739 In-Vivo Optical Diag-nosis of Colon Polyp Histology Using High-Definition White Light Endoscopy (HD-WLE, Can the ASGE Preservation of Innovative Endoscopic Innovation (PIVI) Targets Be Met? Gastrointestinal Endoscopy, 75, AB507-AB507.
https://doi.org/10.1016/j.gie.2012.03.1385
[9] Sano, Y., Ikematsu, H., Fu, K.I., et al. (2009) Meshed Capillary Vessels by Use of Narrow-Band Imaging for Differential Diagnosis of Small Colorectal Polyps. Gastrointestinal Endoscopy, 69, 278-283.
https://doi.org/10.1016/j.gie.2008.04.066
[10] Vu, H.T., Sayuk, G.S., Hollander, T.G., et al. (2015) Resect and Discard Ap-proach to Colon Polyps: Real-World Applicability among Academic and Community Gastroenterologists. Digestive Diseases & Sciences, 60, 502-508.
https://doi.org/10.1007/s10620-014-3376-z
[11] Kaltenbach, T., Rex, D.K., Wilson, A., et al. (2015) Implementation of Optical Diagnosis for Colorectal Polyps: Standardization of Studies Is Needed. Clinical Gastroenterology & Hepatology, 13, 6-10.e1.
https://doi.org/10.1016/j.cgh.2014.10.009
[12] Navadgi, S. (2013) Narrow-Band Imaging with Dual Focus Magnification in Differentiating Colorectal Neoplasia. Digestive Endoscopy: Official Journal of the Japan Gastroenterological Endoscopy Society, 25, 16-20.
https://doi.org/10.1111/den.12075
[13] Repici, A., Hassan, C., Radaelli, F., et al. (2013) Accuracy of Narrow-Band Imaging in Predicting Colonoscopy Surveillance Intervals and Histology of Distal Diminutive Polyps: Results from a Multicenter, Prospective Trial. Gastrointestinal Endoscopy, 78, 106-114.
https://doi.org/10.1016/j.gie.2013.01.035
[14] Paggi, S., Rondonotti, E., Amato, A., et al. (2012) Resect and Discard Strategy in Clinical Practice: A Prospective Cohort Study. Endoscopy, 44, 899-904.
https://doi.org/10.1055/s-0032-1309891
[15] Muirhead, L.J., Kinross, J., Balog, J., et al. (2014) Tu1477 near Real Time Characterisation of Colorectal Cancer and Adenomatous Polyps Using Rapid Evaporative Ionisation Mass Spectrometry (Reims). Gastrointestinal Endoscopy, 79, AB554-AB554.
https://doi.org/10.1016/j.gie.2014.02.923
[16] Bhandari, P., Thayalasekaran, S., Helmut, N., Kiesslich, R. and Sanduleanu, S. (2016) PWE-115 Detection and Characterisation of Colorectal Polyps Using High Def-inition White Light and I-Scan: Evidence and Delphi Process-Based Consensus Recommendations. Gastrointestinal Endoscopy, 83, AB537-AB538.
https://doi.org/10.1016/j.gie.2016.03.1092
[17] Hazewinkel, Y. and Dekker, E. (2011) Colonoscopy: Basic Principles and Novel Techniques. Nature Reviews Gastroenterology & Hepatology, 8, 554-564.
https://doi.org/10.1038/nrgastro.2011.141
[18] Gupta, N., Bansal, A., Rao, D., et al. (2012) Accuracy of in Vivo Optical Diag-nosis of Colon Polyp Histology by Narrow-Band Imaging in Predicting Colonoscopy Surveillance Intervals. Gastrointestinal En-doscopy, 75, 494-502.
https://doi.org/10.1016/j.gie.2011.08.002
[19] Koo, J.S. (2014) Equipment-Based Image-Enhanced En-doscopy for Differentiating Colorectal Polyps. Clinical Endoscopy, 47, 330-333.
https://doi.org/10.5946/ce.2014.47.4.330
[20] Wallace, M.B., Crook, J.E., Coe, S., et al. (2014) Accuracy of in Vivo Colorectal Polyp Discrimination by Using Dual-Focus High-Definition Narrow-Band Imaging Colonoscopy. Gastrointestinal Endoscopy, 80, 1072-1087.
https://doi.org/10.1016/j.gie.2014.05.305
[21] Bae, S.I. and Kim, Y.S. (2014) Colon Cancer Screening and Sur-veillance in Inflammatory Bowel Disease. Clinical Endoscopy, 47, 509-515.
https://doi.org/10.5946/ce.2014.47.6.509