Rajan Vasant, Srinath Havish, Bong Christopher Yii Siang, Cichowski Alex, Young Christopher J, Hewett Peter J
Department of General Surgery, Logan Hospital, Meadowbrook, AUS.
Australian Institute for Machine Learning, The University of Adelaide, Adelaide, AUS.
Cureus. 2022 Mar 10;14(3):e23039. doi: 10.7759/cureus.23039. eCollection 2022 Mar.
Purpose Machine learning algorithms were hypothesized as being able to predict the quality of colonoscopy luminal images. This is to enhance training and quality indicators in endoscopy. Methods A separate study involving a randomized controlled trial of capped vs. un-capped colonoscopies provided the colonoscopy videos for this study. Videos were analyzed with an algorithm devised by the Australian Institute for Machine Learning. The image analysis validated focus measure, steerable filters-based metrics (SFIL), was used to assess luminal visualization quality and was compared with two independent clinician assessments (C1 and C2). Goodman and Kruskal's gamma (G) measure was used to assess rank correlation data using IBM SPSS Statistics for Windows, version 25.0 (IBM Corp., Armonk, NY). Results A total of 500 random colonoscopy video clips were extracted and analyzed, 88 being excluded. SFIL scores matched with C1 in 45% and C2 in 42% of cases, respectively. There was a significant correlation between SFIL and C1 (G = 0.644, p < 0.005) and SFIL and C2 (G = 0.734, p < 0.005). Conclusion This study demonstrates that machine learning algorithms can recognize the quality of luminal visualization during colonoscopy. We intend to apply this in the future to enhance colonoscopy training and as a metric for quality assessment.
目的 机器学习算法被假定能够预测结肠镜检查管腔图像的质量。这是为了提高内镜检查的培训和质量指标。方法 一项单独的研究涉及有帽与无帽结肠镜检查的随机对照试验，为该研究提供了结肠镜检查视频。视频由澳大利亚机器学习研究所设计的算法进行分析。图像分析采用经过验证的聚焦度量、基于可控滤波器的指标（SFIL）来评估管腔可视化质量，并与两名独立的临床医生评估（C1和C2）进行比较。使用IBM SPSS Statistics for Windows 25.0版（IBM公司，纽约州阿蒙克）的古德曼和克鲁斯卡尔γ（G）度量来评估等级相关数据。结果 共提取并分析了500个随机结肠镜检查视频片段，排除了88个。SFIL评分分别在45%的病例中与C1匹配，在42%的病例中与C2匹配。SFIL与C1之间存在显著相关性（G = 0.644，p < 0.005），SFIL与C2之间也存在显著相关性（G = 0.734，p < 0.005）。结论 本研究表明机器学习算法能够识别结肠镜检查期间管腔可视化的质量。我们打算在未来应用此方法来加强结肠镜检查培训，并作为质量评估的一项指标。
