Automatic detection of tuberculosis related abnormalities in Chest X-ray images using hierarchical feature extraction scheme
Automatic detection of tuberculosis related abnormalities in Chest X-ray images using hierarchical feature extraction scheme
复制标题
DOI：
10.1016/j.eswa.2020.113514
复制
发表时间：
2020-11-15
影响因子：
8.5
通讯作者：
Netam, Satyabhuwan Singh
中科院分区：
文献类型：
--
作者：
Chandra, Tej Bahadur;Verma, Kesari;Netam, Satyabhuwan Singh
机器学习技术已经广泛用于医学图像中的异常检测。胸部X射线图像（CXR）是用于检测各种疾病病理的非侵入性诊断工具之一。软组织的解剖结构不明确是分离正常和异常图像的主要挑战之一。本研究的主要目的是模仿专家放射科医生的计算机辅助诊断（CAD）系统的解释程序。我们提出了一种自动检测异常CXR图像的技术，包括一个或多个病理，如胸腔积液，浸润，纤维化，肺门扩大，致密实变等，由于结核病（TB）。所提出的异常检测技术是基于分层特征提取方案，其中的功能被用于在两个层次的健康和不健康的群体进行分类。在第一级中，从分割的肺野中提取手工制作的几何特征，如形状、大小、偏心率、周长等，并且在第二级中，传统的一阶统计特征沿着纹理特征，如能量、熵、对比度、相关性等。此外，监督分类的方法上提取的特征，以检测正常和异常的CXR图像。在两个公共数据集（蒙哥马利集和深圳集）的共800幅CXR图像上验证了算法的性能。所得结果（准确度= 95.60 +/- 5.07%，曲线下面积（AUC）= 0.95 +/- 0.06，用于蒙哥马利采集，深圳采集的准确度= 99.40 +/- 1.05%，AUC = 0.99 +/- 0.01）示出了与现有技术方法相比，所提出的用于TB检测的技术的有前途的性能。此外，使用弗里德曼事后多重比较方法对所得结果进行了统计验证，证实了所提出方法的重要性。(c)2020爱思唯尔有限公司保留所有权利。
Machine learning techniques have been widely used for abnormality detection in medical images. Chest X-ray images (CXR) are among the non-invasive diagnostic tools used to detect various disease pathologies. The ambiguous anatomical structure of soft tissues is one of the major challenges for segregating normal and abnormal images. The main objective of this study is to mimic the expert radiologist's interpretation procedure in computer-aided diagnosis (CAD) systems. We propose an automatic technique for detection of abnormal CXR images containing one or more pathologies like pleural effusion, infiltration, fibrosis, hila enlargement, dense consolidation, etc. due to tuberculosis (TB). The proposed abnormality detection technique is based on the hierarchical feature extraction scheme in which the features are used in two-level of hierarchy to categorize healthy and unhealthy groups. In level one the handcrafted geometrical features like shape, size, eccentricity, perimeter, etc. and in level 2 traditional first order statistical feature along with texture features like energy, entropy, contrast, correlation, etc. are extracted from segmented lung-fields. Further, a supervised classification approach is employed on the extracted features to detect normal and abnormal CXR images. The performance of the algorithm is validated on a total of 800 CXR images from two public datasets, namely the Montgomery set and Shenzhen set. The obtained results (accuracy = 95.60 +/- 5.07% and area under curve (AUC) = 0.95 +/- 0.06 for Montgomery collection, and accuracy = 99.40 +/- 1.05% and AUC = 0.99 +/- 0.01 for Shenzhen collection) shows the promising performance of the proposed technique for TB detection compared to the existing state of the art approaches. Further, the obtained results are statistically validated using Friedman post-hoc multiple comparison methods, which confirms the significance of the proposed method. (c) 2020 Elsevier Ltd. All rights reserved.