当前位置: X-MOL 学术Vis. Comput. Ind. Biomed. Art › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multi-scale characterizations of colon polyps via computed tomographic colonography
Visual Computing for Industry, Biomedicine, and Art ( IF 3.2 ) Pub Date : 2019-12-27 , DOI: 10.1186/s42492-019-0032-7
Weiguo Cao 1 , Marc J Pomeroy 2 , Yongfeng Gao 1 , Matthew A Barish 1 , Almas F Abbasi 1 , Perry J Pickhardt 3 , Zhengrong Liang 2
Affiliation  

Texture features have played an essential role in the field of medical imaging for computer-aided diagnosis. The gray-level co-occurrence matrix (GLCM)-based texture descriptor has emerged to become one of the most successful feature sets for these applications. This study aims to increase the potential of these features by introducing multi-scale analysis into the construction of GLCM texture descriptor. In this study, we first introduce a new parameter - stride, to explore the definition of GLCM. Then we propose three multi-scaling GLCM models according to its three parameters, (1) learning model by multiple displacements, (2) learning model by multiple strides (LMS), and (3) learning model by multiple angles. These models increase the texture information by introducing more texture patterns and mitigate direction sparsity and dense sampling problems presented in the traditional Haralick model. To further analyze the three parameters, we test the three models by performing classification on a dataset of 63 large polyp masses obtained from computed tomography colonoscopy consisting of 32 adenocarcinomas and 31 benign adenomas. Finally, the proposed methods are compared to several typical GLCM-texture descriptors and one deep learning model. LMS obtains the highest performance and enhances the prediction power to 0.9450 with standard deviation 0.0285 by area under the curve of receiver operating characteristics score which is a significant improvement.

中文翻译:

通过计算机断层扫描结肠成像对结肠息肉的多尺度表征

纹理特征在用于计算机辅助诊断的医学成像领域中发挥了重要作用。基于灰度共生矩阵 (GLCM) 的纹理描述符已成为这些应用中最成功的特征集之一。本研究旨在通过在 GLCM 纹理描述符的构建中引入多尺度分析来增加这些特征的潜力。在本研究中,我们首先引入一个新的参数——stride,来探索GLCM的定义。然后我们根据其三个参数提出了三个多尺度GLCM模型,(1)多位移学习模型,(2)多步长学习模型(LMS),(3)多角度学习模型。这些模型通过引入更多纹理模式来增加纹理信息,并减轻传统 Haralick 模型中出现的方向稀疏和密集采样问题。为了进一步分析这三个参数,我们通过对由 32 个腺癌和 31 个良性腺瘤组成的计算机断层扫描结肠镜检查获得的 63 个大息肉肿块的数据集进行分类来测试这三个模型。最后,将所提出的方法与几个典型的 GLCM 纹理描述符和一个深度学习模型进行了比较。LMS 获得了最高的性能,并将预测能力提高到 0.9450,标准差为 0.0285,在接受者操作特征得分曲线下按面积计算,这是一个显着的改进。我们通过对从计算机断层扫描结肠镜检查获得的 63 个大息肉肿块的数据集进行分类来测试这三个模型,其中包括 32 个腺癌和 31 个良性腺瘤。最后,将所提出的方法与几个典型的 GLCM 纹理描述符和一个深度学习模型进行了比较。LMS 获得了最高的性能,并将预测能力提高到 0.9450,标准差为 0.0285,在接受者操作特征得分曲线下按面积计算,这是一个显着的改进。我们通过对从计算机断层扫描结肠镜检查获得的 63 个大息肉肿块的数据集进行分类来测试这三个模型,其中包括 32 个腺癌和 31 个良性腺瘤。最后,将所提出的方法与几个典型的 GLCM 纹理描述符和一个深度学习模型进行了比较。LMS 获得了最高的性能,并将预测能力提高到 0.9450,标准差为 0.0285,在接受者操作特征得分曲线下按面积计算,这是一个显着的改进。
更新日期:2019-12-27
down
wechat
bug