Extraction of the Two-Dimensional Cardiothoracic Ratio from Digital PA Chest Radiographs: Correlation with Cardiac Function and the Traditional Cardiothoracic Ratio

Browne, Robert A.; O'Reilly, Geraldine; McInerney, D.

doi:10.1007/s10278-003-1900-3

Cited by 21 publications

(13 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cardiomegaly can be assessed by the cardiothoracic ratio (CTR), which is measured manually by medical experts using the boundaries of the lungs and heart in CXRs [8]. 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].…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence-Based Diagnosis of Cardiac and Related Diseases

Arsalan

Owais

Mahmood

et al. 2020

JCM

View full text Add to dashboard Cite

Automatic chest anatomy segmentation plays a key role in computer-aided disease diagnosis, such as for cardiomegaly, pleural effusion, emphysema, and pneumothorax. Among these diseases, cardiomegaly is considered a perilous disease, involving a high risk of sudden cardiac death. It can be diagnosed early by an expert medical practitioner using a chest X-Ray (CXR) analysis. The cardiothoracic ratio (CTR) and transverse cardiac diameter (TCD) are the clinical criteria used to estimate the heart size for diagnosing cardiomegaly. Manual estimation of CTR and other diseases is a time-consuming process and requires significant work by the medical expert. Cardiomegaly and related diseases can be automatically estimated by accurate anatomical semantic segmentation of CXRs using artificial intelligence. Automatic segmentation of the lungs and heart from the CXRs is considered an intensive task owing to inferior quality images and intensity variations using nonideal imaging conditions. Although there are a few deep learning-based techniques for chest anatomy segmentation, most of them only consider single class lung segmentation with deep complex architectures that require a lot of trainable parameters. To address these issues, this study presents two multiclass residual mesh-based CXR segmentation networks, X-RayNet-1 and X-RayNet-2, which are specifically designed to provide fine segmentation performance with a few trainable parameters compared to conventional deep learning schemes. The proposed methods utilize semantic segmentation to support the diagnostic procedure of related diseases. To evaluate X-RayNet-1 and X-RayNet-2, experiments were performed with a publicly available Japanese Society of Radiological Technology (JSRT) dataset for multiclass segmentation of the lungs, heart, and clavicle bones; two other publicly available datasets, Montgomery County (MC) and Shenzhen X-Ray sets (SC), were evaluated for lung segmentation. The experimental results showed that X-RayNet-1 achieved fine performance for all datasets and X-RayNet-2 achieved competitive performance with a 75% parameter reduction.

show abstract

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence-Based Diagnosis of Cardiac and Related Diseases

Arsalan

Owais

Mahmood

et al. 2020

JCM

View full text Add to dashboard Cite

show abstract

“…1D-CTR is defined as the ratio of the transverse diameter of the heart to the transverse diameter of the thorax, as shown in Fig.5. Recently, the extraction of 2D cardiothoracic ratio (2D-CTR) from the chest radiographs has been extensively studied [14], since it is believed to be more robust than 1D-CTR. In our study, 2D-CTR is defined as the squared root of the ratio between the area of white region and the area of both white and grey regions, as shown on the right of Fig.5.…”

Section: D and 2d Cardiothoracic Ratiosmentioning

confidence: 99%

Segmenting Lung Fields in Serial Chest Radiographs Using Both Population and Patient-Specific Shape Statistics

Shi

Xue

et al. 2006

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2006

View full text Add to dashboard Cite

This paper presents a new deformable model using both populationbased and patient-specific shape statistics to segment lung fields from serial chest radiographs. First, a modified scale-invariant feature transform (SIFT) local descriptor is used to characterize the image features in the vicinity of each pixel, so that the deformable model deforms in a way that seeks for the region with similar SIFT local descriptors. Second, the deformable model is constrained by both population-based and patient-specified shape statistics. Initially, population-based shape statistics takes most of the rules when the number of serial images is small; gradually, patient-specific shape statistics takes more rules after a sufficient number of segmentation results on the same patient have been obtained. The proposed deformable model can adapt to the shape variability of different patients, and obtain more robust and accurate segmentation results.

show abstract

“…CTAR is defined as the ratio between the cardiac area and the whole thoracic area [2]. Although there are more published articles about CTR, there are only two study reporting on CTAR [2,10]. The report by Hasan et al [2] is a methodological study that allowed a successful measurement of CTAR by using an automatic segmentation technique on digital chest radiograph images.…”

Section: Introductionmentioning

confidence: 99%

“…The report by Hasan et al [2] is a methodological study that allowed a successful measurement of CTAR by using an automatic segmentation technique on digital chest radiograph images. Whereas in the study by Browne et al [10], CTAR was calculated by making a drawing on the digital PA chest radiographs with the help of mouse and the correlation between the ejection fraction and CTAR was examined in individuals with various cardiac diseases, however, healthy subjects were not included in the study. An anatomical mistake has been made in both studies during the determination of the upper border of the heart, and the major vessels originating from the heart were also included within the borders of the heart [2,10].…”

Section: Introductionmentioning

confidence: 99%

“…Whereas in the study by Browne et al [10], CTAR was calculated by making a drawing on the digital PA chest radiographs with the help of mouse and the correlation between the ejection fraction and CTAR was examined in individuals with various cardiac diseases, however, healthy subjects were not included in the study. An anatomical mistake has been made in both studies during the determination of the upper border of the heart, and the major vessels originating from the heart were also included within the borders of the heart [2,10]. Therefore, the anatomical borders of the heart were tried to be determined more accurately in this study.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cardiothoracic area ratio for evaluation of ejection fraction in patients

Karaman¹

2019

Ann Clin Anal Med

View full text Add to dashboard Cite

Aim: The advent of digital radiology and computerized workstations renders it very easy to measure cardiothoracic ratio (CTR) and cardiothoracic area ratio (CTAR) on chest radiographs. The aim of this study was to assess whether CTAR correlates with the left ventricular ejection fraction (EF) better than CTR in healthy individuals and patients with congestive heart failure. Material and Method: The study included 156 healthy individuals and 98 heart failure patients undergoing echocardiography and digital chest radiography. The CTR was calculated in the traditional manner, and the CTAR was taken as the ratio between the pixel counts of the cardiac area and whole thoracic area. Results: The traditional CTR showed an inverse correlation with ejection fraction in both healthy individuals (r =-0.13) and heart failure patients (r =-0.19). The CTAR showed an improved correlation (r =-0.32 for healthy individuals and r =-0.37 for heart failure patients). If it is assumed that an ejection fraction of 55% or more indicates normal cardiac function, a value of 50% or less for CTAR can be taken as normal. Discussion: Digital chest radiography is widely used as a popular technique for diagnosing various thoracic and cardiac diseases. Cardiomegaly is associated with an adverse outcome in patients with heart disease. Therefore, evaluation of heart size is an important clinical variable, and changes in heart size may be used to monitor and grade cardiac disease severity. Conclusion: Our findings suggest that the CTAR correlates better with cardiac function as assessed by the ejection fraction than the traditional CTR.

show abstract

Extraction of the Two-Dimensional Cardiothoracic Ratio from Digital PA Chest Radiographs: Correlation with Cardiac Function and the Traditional Cardiothoracic Ratio

Cited by 21 publications

References 17 publications

Artificial Intelligence-Based Diagnosis of Cardiac and Related Diseases

Artificial Intelligence-Based Diagnosis of Cardiac and Related Diseases

Segmenting Lung Fields in Serial Chest Radiographs Using Both Population and Patient-Specific Shape Statistics

Cardiothoracic area ratio for evaluation of ejection fraction in patients

Contact Info

Product

Resources

About