Department of Electronic Engineering, The Chinese University of Hong Kong, and Institute of Digestive Disease, Prince of Wales Hospital, Shatin N.T., Hong Kong SAR, China.
Artif Intell Med. 2011 May;52(1):11-6. doi: 10.1016/j.artmed.2011.01.003. Epub 2011 Feb 24.
Capsule endoscopy is useful in the diagnosis of small bowel diseases. However, the large number of images produced in each test is a tedious task for physicians. To relieve burden of physicians, a new computer-aided detection scheme is developed in this study, which aims to detect small bowel tumors for capsule endoscopy.
A novel textural feature based on multi-scale local binary pattern is proposed to discriminate tumor images from normal images. Since tumor in small bowel exhibit great diversities in appearance, multiple classifiers are employed to improve detection accuracy. 1200 capsule endoscopy images chosen from 10 patients' data constitute test data in our experiment.
Multiple classifiers based on k-nearest neighbor, multilayer perceptron neural network and support vector machine, which are built from six different ensemble rules, are experimented in three different color spaces. The results demonstrate an encouraging detection accuracy of 90.50%, together with a sensitivity of 92.33% and a specificity of 88.67%.
The proposed scheme using color texture features and classifier ensemble is promising for small bowel tumor detection in capsule endoscopy images.
胶囊内镜在小肠疾病的诊断中具有重要价值。然而，每次检查产生的大量图像对医生来说是一项繁琐的任务。为了减轻医生的负担，本研究开发了一种新的计算机辅助检测方案，旨在检测胶囊内镜中的小肠肿瘤。
本研究提出了一种基于多尺度局部二值模式的新型纹理特征，用于区分肿瘤图像和正常图像。由于小肠中的肿瘤在外观上存在很大的差异，因此采用了多种分类器来提高检测准确性。我们的实验中使用了来自 10 名患者数据的 1200 张胶囊内镜图像作为测试数据。
在三种不同的颜色空间中，基于 k-最近邻、多层感知机神经网络和支持向量机的多个分类器，这些分类器是基于六种不同的集成规则构建的，进行了实验。实验结果表明，该方案在胶囊内镜图像中小肠肿瘤检测方面具有令人鼓舞的检测准确率（90.50%），同时具有较高的灵敏度（92.33%）和特异性（88.67%）。
本研究提出的使用颜色纹理特征和分类器集成的方案，有望用于胶囊内镜图像中小肠肿瘤的检测。
