Robust endocytoscopic image classification based on higher-order symmetric tensor analysis and multi-scale topological statistics
Robust endocytoscopic image classification based on higher-order symmetric tensor analysis and multi-scale topological statistics
复制标题
DOI：
10.1007/s11548-020-02255-3
复制
发表时间：
2020-09
影响因子：
3
通讯作者：
H. Itoh;Y. Nimura;Y. Mori;M. Misawa;S. Kudo;K. Hotta;K. Ohtsuka;S. Saito;Yutaka Saito;H. Ikematsu;Y. Hayashi;M. Oda;K. Mori
中科院分区：
文献类型：
--
作者：
H. Itoh;Y. Nimura;Y. Mori;M. Misawa;S. Kudo;K. Hotta;K. Ohtsuka;S. Saito;Yutaka Saito;H. Ikematsu;Y. Hayashi;M. Oda;K. Mori
目的细胞内镜是一种新型的内窥镜，它可以进行常规的内窥镜观察和细胞水平的超放大观察。虽然细胞内镜有望提高结肠镜检查的成本效益，但细胞内镜图像诊断需要医生的大量知识和高水平经验。为了克服这个困难，我们开发了一个强大的细胞内镜（EC）图像分类方法的计算机辅助诊断（CAD）系统的建设，因为实时CAD可以解决准确性问题，并减少interobserver variability.MethodWe提出了一种新的特征提取方法，通过引入高阶对称张量分析的多尺度拓扑统计图像上的计算，并将该特征提取与EC图像分类相结合。我们通过与三种深度学习方法进行比较，实验评估了我们所提出的方法的分类准确性。我们通过使用我们的大规模多医院数据集进行了这种比较，该数据集包含超过3800名患者的约55，000张图像。ResultsOur提出的方法对四家医院的所有图像实现了平均90%的分类准确率，即使最好的深度学习方法仅对一家医院的图像实现了95%的分类准确率。在具有拒绝选项的情况下，所提出的方法实现了专家级的准确分类。这些结果表明，我们所提出的方法对坑图案的变化，包括颜色，对比度，形状，和hospitals.ConclusionsWe开发了一个强大的EC图像分类方法与新的特征提取的差异的鲁棒性。该方法具有较强的泛化能力，对构造实用的CAD系统是有用的。
PurposeAn endocytoscope is a new type of endoscope that enables users to perform conventional endoscopic observation and ultramagnified observation at the cell level. Although endocytoscopy is expected to improve the cost-effectiveness of colonoscopy, endocytoscopic image diagnosis requires much knowledge and high-level experience for physicians. To circumvent this difficulty, we developed a robust endocytoscopic (EC) image classification method for the construction of a computer-aided diagnosis (CAD) system, since real-time CAD can resolve accuracy issues and reduce interobserver variability.MethodWe propose a novel feature extraction method by introducing higher-order symmetric tensor analysis to the computation of multi-scale topological statistics on an image, and we integrate this feature extraction with EC image classification. We experimentally evaluate the classification accuracy of our proposed method by comparing it with three deep learning methods. We conducted this comparison by using our large-scale multi-hospital dataset of about 55,000 images of over 3800 patients.ResultsOur proposed method achieved an average 90% classification accuracy for all the images in four hospitals even though the best deep learning method achieved 95% classification accuracy for images in only one hospital. In the case with a rejection option, the proposed method achieved expert-level accurate classification. These results demonstrate the robustness of our proposed method against pit pattern variations, including differences of colours, contrasts, shapes, and hospitals.ConclusionsWe developed a robust EC image classification method with novel feature extraction. This method is useful for the construction of a practical CAD system, since it has sufficient generalisation ability.