School of Electrical, Computer, and Telecommunication Engineering, Faculty of Engineering and Information Scinces, University of Wollongong, North Avenue, Wollongong, NSW, Australia.
School of Medicine, Faculty of Scince, Medicine and Health, University of Wollongong, North Avenue, Wollongong, NSW, Australia.
Artif Intell Med. 2019 Mar;94:18-27. doi: 10.1016/j.artmed.2018.12.008. Epub 2018 Dec 29.
A capsule endoscopy examination of the human small bowel generates a large number of images that have high similarity. In order to reduce the time it takes to review the high similarity images, clinicians will increase the playback speed, typically to 15 frames per second [1]. Associated with this behaviour is an increased probability of overlooking an image that may contain an abnormality. An alternative option to increasing the playback speed is the application of abnormality detection systems to detect abnormalities such as ulcers, tumors, polyps and bleeding. However, applying all of these detection systems requires significant computing time and still produces numerous images with high similarity depending on the specificity of the utilized detection systems. An interesting approach to reduce viewing time is the application of a frame reduction system that reduces the number of images by omitting those with a high similarity of information. The advantage of such a system is that the specialist only needs to review a single image that technically represents a series of images with high similarity. This reduces the total number of images that a specialist must review and importantly, images containing any abnormality are not removed from the review, but simply reduced in number. Thus, the current study developed a frame reduction system using various color models using Bayer images for color texture and a modified local binary pattern (LBP) for structural information. The proposed system achieved a reduction ratio of 93.87%, which is higher than the existing systems and required lesser computation due to the utilization of Bayer images.
胶囊内镜检查人类小肠会生成大量高度相似的图像。为了减少审查高度相似图像所需的时间，临床医生会提高回放速度，通常提高到每秒 15 帧[1]。这种行为会增加错过可能包含异常的图像的概率。另一种选择是应用异常检测系统来检测溃疡、肿瘤、息肉和出血等异常。然而，应用所有这些检测系统都需要大量的计算时间，并且仍然会产生许多具有高度相似性的图像，具体取决于所使用的检测系统的特异性。减少查看时间的一种有趣方法是应用帧减少系统，该系统通过省略具有高度相似信息的图像来减少图像数量。这种系统的优点是，专家只需要查看一张代表一系列高度相似图像的单一图像。这减少了专家必须审查的图像总数，并且重要的是，不会从审查中删除包含任何异常的图像，而只是减少数量。因此，本研究使用各种颜色模型开发了一种帧减少系统，该系统使用 Bayer 图像进行颜色纹理和改进的局部二值模式 (LBP) 进行结构信息。所提出的系统实现了 93.87%的缩减率，高于现有系统，并且由于使用了 Bayer 图像，所需的计算量更少。
