An online deep convolutional polyp lesion prediction over Narrow Band Imaging (NBI)
An online deep convolutional polyp lesion prediction over Narrow Band Imaging (NBI)
复制标题
基于窄带成像 (NBI) 的在线深度卷积息肉病变预测
DOI：
10.1109/embc44109.2020.9176534
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
F. Martínez
中科院分区：
文献类型：
--
作者：
F. Sierra;Yesid Gutiérrez;F. Martínez
息肉是诊断胃肠道肿瘤的主要生物标志物，表现为沿着肠道的异常隆起。在常规结肠镜检查中，根据微血管和表面纹理模式对此类息肉进行定位和粗略表征。窄带成像（NBI）序列已成为补充技术，以加强根据血管结构的可疑粘膜表面的描述。然而，大量误导性息肉表征，以及评估期间的专家依赖性，降低了有效疾病治疗的可能性。此外，结肠镜检查期间的挑战，例如突然的相机运动、强度变化和伪影，使诊断任务变得困难。这项工作介绍了一个强大的帧级卷积策略，能够表征和预测NBI序列上的增生，腺瘤和锯齿状息肉。该策略在总共76个视频上进行了评估，实现了90.79%的平均准确率，以区分这三类。值得注意的是，该方法实现了100%的准确率来区分中间锯齿状息肉，即使对于专家胃肠病学家来说，其评估也具有挑战性。该方法也有利于支持息肉切除决策，在评估dataset.Clinical relevance上获得满分-所提出的方法支持在常规结肠镜检查期间息肉的可观察组织学表征，避免可能演变为癌症的潜在肿块的错误分类。
Polyps, represented as abnormal protuberances along intestinal track, are the main biomarker to diagnose gastrointestinal cancer. During routine colonoscopies such polyps are localized and coarsely characterized according to microvascular and surface textural patterns. Narrow-band imaging (NBI) sequences have emerged as complementary technique to enhance description of suspicious mucosa surfaces according to blood vessels architectures. Nevertheless, a high number of misleading polyp characterization, together with expert dependency during evaluation, reduce the possibility of effective disease treatments. Additionally, challenges during colonoscopy, such as abrupt camera motions, changes of intensity and artifacts, difficult the diagnosis task. This work introduces a robust frame-level convolutional strategy with the capability to characterize and predict hyperplastic, adenomas and serrated polyps over NBI sequences. The proposed strategy was evaluated over a total of 76 videos achieving an average accuracy of 90,79% to distinguish among these three classes. Remarkably, the approach achieves a 100% of accuracy to differentiate intermediate serrated polyps, whose evaluation is challenging even for expert gastroenterologist. The approach was also favorable to support polyp resection decisions, achieving perfect score on evaluated dataset.Clinical relevance— The proposed approach supports observable hystological characterization of polyps during a routine colonoscopy avoiding misclassification of potential masses that could evolve in cancer.