Medical Department III (Gastroenterology, Hepatology and Metabolic Diseases), Aachen University Hospital, RWTH Aachen University, 52074 Aachen, Germany.
Endoscopy. 2010 Mar;42(3):203-7. doi: 10.1055/s-0029-1243861. Epub 2010 Jan 25.
Recent studies have shown that narrow-band imaging (NBI) is a powerful diagnostic tool for differentiating between neoplastic and nonneoplastic colorectal polyps. The aim of the present study was to develop and evaluate a computer-based method for automated classification of colorectal polyps on the basis of vascularization features.
In a prospective pilot study with 128 patients who were undergoing zoom NBI colonoscopy, 209 detected polyps were visualized and subsequently removed for histological analysis. The proposed computer-based method consists of image preprocessing, vessel segmentation, feature extraction, and classification. The results of the automated classification were compared to those of human observers blinded to the histological gold standard.
Consensus decision between the human observers resulted in a sensitivity of 93.8 % and a specificity of 85.7 %. A "safe" decision, i. e., classifying polyps as neoplastic in cases when there was interobserver discrepancy, yielded a sensitivity of 96.9 % and a specificity of 71.4 %. The overall correct classification rates were 91.9 % for the consensus decision and 90.9 % for the safe decision. With ideal settings the computer-based approach achieved a sensitivity of approximately 90 % and a specificity of approximately 70 %, while the overall correct classification rate was 85.3 %. The computer-based classification showed a specificity of 61.2 % when a sensitivity of 93.8 % was selected, and a 53.1 % specificity with a sensitivity of 96.9 %.
Automated classification of colonic polyps on the basis of NBI vascularization features is feasible, but classification by observers is still superior. Further research is needed to clarify whether the performance of the automated classification system can be improved.
最近的研究表明，窄带成像（NBI）是区分肿瘤性和非肿瘤性结直肠息肉的有力诊断工具。本研究旨在开发和评估一种基于血管生成特征的计算机自动分类结直肠息肉的方法。
在一项前瞻性试点研究中，对 128 名接受变焦 NBI 结肠镜检查的患者，共可视化了 209 个检测到的息肉，并随后切除进行组织学分析。所提出的基于计算机的方法包括图像预处理、血管分割、特征提取和分类。将自动分类的结果与对组织学金标准不知情的人类观察者的结果进行比较。
人类观察者的共识决策得出的敏感性为 93.8%，特异性为 85.7%。“安全”决策，即在存在观察者间差异的情况下将息肉归类为肿瘤性，其敏感性为 96.9%，特异性为 71.4%。共识决策的总体正确分类率为 91.9%，安全决策的总体正确分类率为 90.9%。在理想的设置下，基于计算机的方法的敏感性约为 90%，特异性约为 70%，而总体正确分类率为 85.3%。当选择敏感性为 93.8%时，基于计算机的分类显示出特异性为 61.2%，当选择敏感性为 96.9%时，特异性为 53.1%。
基于 NBI 血管生成特征对结肠息肉进行自动分类是可行的，但观察者的分类仍然更优。需要进一步研究以明确自动分类系统的性能是否可以提高。
Zotero 插件