An objective comparison of detection and segmentation algorithms for artefacts in clinical endoscopy
An objective comparison of detection and segmentation algorithms for artefacts in clinical endoscopy
复制标题
DOI：
10.1038/s41598-020-59413-5
复制
发表时间：
2020-02-17
影响因子：
4.6
通讯作者：
Rittscher, Jens
中科院分区：
文献类型：
--
作者：
Ali, Sharib;Zhou, Felix;Rittscher, Jens
我们对第一版内窥镜伪影检测挑战（EAD）的提交资料进行了全面分析。通过使用众包，该计划朝着了解应用于内窥镜检查的现有最先进计算机视觉方法的局限性迈出了一步，并促进了适用于临床翻译的新方法的开发。内窥镜检查是一种常规成像技术，用于检测、诊断和治疗中空器官疾病;食道、胃、结肠、子宫和膀胱。然而，这些器官的性质阻止成像的组织不含成像伪影，诸如气泡、像素饱和、器官镜面反射和碎片，所有这些都对任何定量分析提出了实质性挑战。因此，通过定量评估在内窥镜视频中观察到的异常粘膜表面来改善临床结果的潜力目前尚未准确实现。EAD挑战通过研究可以准确分类、定位和分割内窥镜帧中伪影的方法作为关键的先决条件任务，提高了对这一关键瓶颈问题的认识并解决了这一问题。使用多样化的多机构，多模态，多器官视频帧数据集，对23种算法的准确性和性能进行了客观排名，以进行伪影检测和分割。还评估了方法推广到未知数据集的能力。表现最好的方法（前15%）提出了深度学习策略，以协调伪影外观在大小、形态、发生和器官类型方面的变化。然而，没有一种方法在所有任务中都表现出色。详细的分析揭示了目前的培训策略的缺点，并强调需要开发新的最佳指标，以准确地量化方法的临床适用性。
We present a comprehensive analysis of the submissions to the first edition of the Endoscopy Artefact Detection challenge (EAD). Using crowd-sourcing, this initiative is a step towards understanding the limitations of existing state-of-the-art computer vision methods applied to endoscopy and promoting the development of new approaches suitable for clinical translation. Endoscopy is a routine imaging technique for the detection, diagnosis and treatment of diseases in hollow-organs; the esophagus, stomach, colon, uterus and the bladder. However the nature of these organs prevent imaged tissues to be free of imaging artefacts such as bubbles, pixel saturation, organ specularity and debris, all of which pose substantial challenges for any quantitative analysis. Consequently, the potential for improved clinical outcomes through quantitative assessment of abnormal mucosal surface observed in endoscopy videos is presently not realized accurately. The EAD challenge promotes awareness of and addresses this key bottleneck problem by investigating methods that can accurately classify, localize and segment artefacts in endoscopy frames as critical prerequisite tasks. Using a diverse curated multi-institutional, multi-modality, multi-organ dataset of video frames, the accuracy and performance of 23 algorithms were objectively ranked for artefact detection and segmentation. The ability of methods to generalize to unseen datasets was also evaluated. The best performing methods (top 15%) propose deep learning strategies to reconcile variabilities in artefact appearance with respect to size, modality, occurrence and organ type. However, no single method outperformed across all tasks. Detailed analyses reveal the shortcomings of current training strategies and highlight the need for developing new optimal metrics to accurately quantify the clinical applicability of methods.