Applied Computing Group (NCA - UFMA), Federal University of Maranhao, Brazil.
Applied Computing Group (NCA - UFMA), Federal University of Maranhao, Brazil.
Comput Methods Programs Biomed. 2019 Aug;177:285-296. doi: 10.1016/j.cmpb.2019.06.005. Epub 2019 Jun 6.
Chest X-ray (CXR) is one of the most used imaging techniques for detection and diagnosis of pulmonary diseases. A critical component in any computer-aided system, for either detection or diagnosis in digital CXR, is the automatic segmentation of the lung field. One of the main challenges inherent to this task is to include in the segmentation the lung regions overlapped by dense abnormalities, also known as opacities, which can be caused by diseases such as tuberculosis and pneumonia. This specific task is difficult because opacities frequently reach high intensity values which can be incorrectly interpreted by an automatic method as the lung boundary, and as a consequence, this creates a challenge in the segmentation process, because the chances of incomplete segmentations are increased considerably. The purpose of this work is to propose a method for automatic segmentation of lungs in CXR that addresses this problem by reconstructing the lung regions "lost" due to pulmonary abnormalities.
The proposed method, which features two deep convolutional neural network models, consists of four steps main steps: (1) image acquisition, (2) initial segmentation, (3) reconstruction and (4) final segmentation.
The proposed method was experimented on 138 Chest X-ray images from Montgomery County's Tuberculosis Control Program, and has achieved as best result an average sensitivity of 97.54%, an average specificity of 96.79%, an average accuracy of 96.97%, an average Dice coefficient of 94%, and an average Jaccard index of 88.07%.
We demonstrate in our lung segmentation method that the problem of dense abnormalities in Chest X-rays can be efficiently addressed by performing a reconstruction step based on a deep convolutional neural network model.
胸部 X 光（CXR）是用于检测和诊断肺部疾病的最常用成像技术之一。无论是在数字 CXR 中进行检测还是诊断，计算机辅助系统的一个关键组成部分都是自动分割肺区域。这项任务的主要挑战之一是将密集异常（也称为不透明性）覆盖的肺区域包含在分割中，这些异常可能是由结核病和肺炎等疾病引起的。这项特定任务具有挑战性，因为不透明度通常会达到很高的强度值，这可能会被自动方法错误地解释为肺边界，从而在分割过程中造成挑战，因为不完整分割的可能性大大增加。这项工作的目的是提出一种用于自动分割 CXR 中肺部的方法，通过重建由于肺部异常而“丢失”的肺区域来解决这个问题。
该方法由两个深度卷积神经网络模型组成，主要包括四个步骤：（1）图像采集，（2）初始分割，（3）重建，（4）最终分割。
该方法在蒙哥马利县结核病控制计划的 138 张胸部 X 光图像上进行了实验，最佳结果为平均灵敏度 97.54%，平均特异性 96.79%，平均准确性 96.97%，平均 Dice 系数 94%，平均 Jaccard 指数 88.07%。
我们在肺部分割方法中证明，通过基于深度卷积神经网络模型执行重建步骤，可以有效地解决胸部 X 光片中密集异常的问题。
