A review on lung boundary detection in chest X-rays

Abstract

PurposeChest radiography is the most common imaging modality for pulmonary diseases. Due to its wide usage, there is a rich literature addressing automated detection of cardiopulmonary diseases in digital chest X-rays (CXRs). One of the essential steps for automated analysis of CXRs is localizing the relevant region of interest, i.e., isolating lung region from other less relevant parts, for applying decision-making algorithms there. This article provides an overview of the recent literature on lung boundary detection in CXR images.MethodsWe review the leading lung segmentation algorithms proposed in period 2006–2017. First, we present a review of articles for posterior–anterior view CXRs. Then, we mention studies which operate on lateral views. We pay particular attention to works that focus their efforts on deformed lungs and pediatric cases. We also highlight the radiographic measures extracted from lung boundary and their use in automatically detecting cardiopulmonary abnormalities. Finally, we identify challenges in dataset curation and expert delineation process, and we listed publicly available CXR datasets.Results(1) We classified algorithms into four categories: rule-based, pixel classification-based, model-based, hybrid, and deep learning-based algorithms. Based on the reviewed articles, hybrid methods and deep learning-based methods surpass the algorithms in other classes and have segmentation performance as good as inter-observer performance. However, they require long training process and pose high computational complexity. (2) We found that most of the algorithms in the literature are evaluated on posterior–anterior view adult CXRs with a healthy lung anatomy appearance without considering challenges in abnormal CXRs. (3) We also found that there are limited studies for pediatric CXRs. The lung appearance in pediatrics, especially in infant cases, deviates from adult lung appearance due to the pediatric development stages. Moreover, pediatric CXRs are noisier than adult CXRs due to interference by other objects, such as someone holding the child’s arms or the child’s body, and irregular body pose. Therefore, lung boundary detection algorithms developed on adult CXRs may not perform accurately in pediatric cases and need additional constraints suitable for pediatric CXR imaging characteristics. (4) We have also stated that one of the main challenges in medical image analysis is accessing the suitable datasets. We listed benchmark CXR datasets for developing and evaluating the lung boundary algorithms. However, the number of CXR images with reference boundaries is limited due to the cumbersome but necessary process of expert boundary delineation.ConclusionsA reliable computer-aided diagnosis system would need to support a greater variety of lung and background appearance. To our knowledge, algorithms in the literature are evaluated on posterior–anterior view adult CXRs with a healthy lung anatomy appearance, without considering ambiguous lung silhouettes due to pathological deformities, anatomical alte...

Artificial Intelligence-Based Diagnosis of Cardiac and Related Diseases

“…The CXR is a common diagnostic tool used by doctors to detect various radiological signs. The lung shape features from the CXR can be used to diagnose pleural effusion, which is directly related to tuberculosis and congestive heart failure [3]. Considering the importance of chest anatomy, emphysema, which causes hyperinflation of alveoli, can be observed by the lung shape because a silhouette appearance of the lung field is created.…”

“…Several studies have evaluated segmentation of the chest anatomy to estimate the CTR for cardiomegaly and related diseases [9][10][11][12][13]. To obtain advancement in diagnosis, automated systems are required to aid the medical specialist and overcome the diagnostic burden [2,3]. Most of the described diseases are related to the shape and size of the anatomical structures, which require accurate segmentation of the lung and heart boundaries.…”

Lung Field Segmentation in Chest X-rays: A Deformation-Tolerant Procedure Based on the Approximation of Rib Cage Seed Points

“…Two of them measure the overlapping area and one the distance between the two contours. These measures are widely used in relevant studies [12]. Specifically: Jaccard similarity coefficient:…”

“…Automated CXR interpretation could drastically alleviate the increasing workload of radiologists by complementing their diagnostic procedures and acting as a "second opinion" [11]. From a technical standpoint, a typical CXR analysis algorithm comprises the following discrete steps: defining the Region Of Interest (ROI), identifying specific imaging features of the ROI and using a machine learning strategy to classify the detected pathology [12]. In the case of CXR analysis, the ROI is the lung region within the bony thorax, and its correct identification is a crucial prerequisite.…”

“…Accurately delineating the lung boundaries is a very challenging image analysis problem, and it is well studied in the literature. The majority of available algorithms are evaluated based on anatomically "correct" CXRs and are sometimes prone to error due to anatomical variations, chest deformities and incorrect positioning of the patient [12].…”