Cardiovascular border (CB) analysis is the primary method for detecting and quantifying the severity of cardiovascular disease using posterior-anterior chest radiographs (CXRs). This study aimed to develop and validate a deep learning–based automatic CXR CB analysis algorithm (CB_auto) for diagnosing and quantitatively evaluating valvular heart disease (VHD).
We developed CB_auto using 816 normal and 798 VHD CXRs. For validation, 640 normal and 542 VHD CXRs from three different hospitals and 132 CXRs from a public dataset were assigned. The reliability of the CB parameters determined by CB_auto was evaluated. To evaluate the differences between parameters determined by CB_auto and manual CB drawing (CB_hand), the absolute percentage measurement error (APE) was calculated. Pearson correlation coefficients were calculated between CB_hand and echocardiographic measurements.
CB parameters determined by CB_auto yielded excellent reliability (intraclass correlation coefficient > 0.98). The 95% limits of agreement for the cardiothoracic ratio were 0.00 ± 0.04% without systemic bias. The differences between parameters determined by CB_auto and CB_hand as defined by the APE were < 10% for all parameters except for carinal angle and left atrial appendage. In the public dataset, all CB parameters were successfully drawn in 124 of 132 CXRs (93.9%). All CB parameters were significantly greater in VHD than in normal controls (all p < 0.05). All CB parameters showed significant correlations (p < 0.05) with echocardiographic measurements.
The CB_auto system empowered by deep learning algorithm provided highly reliable CB measurements that could be useful not only in daily clinical practice but also for research purposes.
• A deep learning–based automatic CB analysis algorithm for diagnosing and quantitatively evaluating VHD using posterior-anterior chest radiographs was developed and validated.
• Our algorithm (CB_auto) yielded comparable reliability to manual CB drawing (CB_hand) in terms of various CB measurement variables, as confirmed by external validation with datasets from three different hospitals and a public dataset.
• All CB parameters were significantly different between VHD and normal control measurements, and echocardiographic measurements were significantly correlated with CB parameters measured from normal control and VHD CXRs.
This is a preview of subscription content, access via your institution.
Buy single article
Instant access to the full article PDF.
Price excludes VAT (USA)
Tax calculation will be finalised during checkout.
Absolute percentage measurement error
Automatic CB drawing
Manual CB drawing
- CT ratio:
Intraclass correlation coefficient
Valvular heart disease
Zipes DP (2018) Braunwald's heart disease: a textbook of cardiovascular medicine, 11th Edition. BMH Medical Journal - ISSN 2348–392X:63%V 65
Dimopoulos K, Giannakoulas G, Bendayan I et al (2013) Cardiothoracic ratio from postero-anterior chest radiographs: a simple, reproducible and independent marker of disease severity and outcome in adults with congenital heart disease. Int J Cardiol 166:453–457
Browne RF, O’Reilly G, McInerney D (2004) Extraction of the two-dimensional cardiothoracic ratio from digital PA chest radiographs: correlation with cardiac function and the traditional cardiothoracic ratio. J Digit Imaging 17:120–123
Danzer CS (1919) The cardiothoracic ratio: an index of cardiac enlargement.:Bibliography. The American Journal of the Medical Sciences (1827–1924) 157:513
Wittenborg MH, Neuhauser EB (1955) Diagnostic roentgenology in congenital heart disease. Circulation 11:462–485
Li Z, Hou Z, Chen C et al (2019) Automatic cardiothoracic ratio calculation with deep learning. IEEE Access 7:37749–37756
Arsalan M, Owais M, Mahmood T, Choi J, Park KR (2020) Artificial intelligence-based diagnosis of cardiac and related diseases. J Clin Med 9
Nakayama M, Shibuya A, Inoue R, Kondo Y (2008) Automated measurement of cardiothoracic ratio using an R package. AMIA Annu Symp Proc:1064
Candemir S, Jaeger S, Lin W, Xue Z, Antani S, Thoma G (2016) Automatic heart localization and radiographic index computation in chest x-rays. Proc SPIE Vol 9785
Lee W, Kim JB, Yang DH et al (2018) Comparative effectiveness of coronary screening in heart valve surgery: computed tomography versus conventional coronary angiography. J Thorac Cardiovasc Surg 155(1423–1431):e1423
Irvin J, Rajpurkar P, Ko M et al (2019) Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. Proceedings of the AAAI conference on artificial intelligence, pp 590–597
Shiraishi J, Katsuragawa S, Ikezoe J et al (2000) Development of a digital image database for chest radiographs with and without a lung nodule: receiver operating characteristic analysis of radiologists’ detection of pulmonary nodules. AJR Am J Roentgenol 174:71–74
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical image computing and computer-assisted intervention. Springer, pp 234–241
Jung A (2019) Imgaug documentation. Readthedocs io, Jun 25
He K, Gkioxari G, Dollár P, Girshick R (2017) Mask r-cnn. Proceedings of the IEEE international conference on computer vision, pp 2961–2969
Lin T-Y, Maire M, Belongie S et al (2014) Microsoft coco: common objects in context. European conference on computer vision. Springer, pp 740–755
Bland JM, Altman DG (1986) Statistical methods for assessing agreement between two methods of clinical measurement. Lancet 1:307–310
Kim C, Lee KY, Shin C et al (2018) Comparison of filtered back projection, hybrid iterative reconstruction, model-based iterative reconstruction, and virtual monoenergetic reconstruction images at both low- and standard-dose settings in measurement of emphysema volume and airway wall thickness: a CT phantom study. Korean J Radiol 19:809–817
Kim SK, Kim C, Lee KY et al (2019) Accuracy of model-based iterative reconstruction for CT volumetry of part-solid nodules and solid nodules in comparison with filtered back projection and hybrid iterative reconstruction at various dose settings: an anthropomorphic chest phantom study. Korean J Radiol 20:1195–1206
Koo TK, Li MY (2016) A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J Chiropr Med 15:155–163
Yang DH, Seo JB, Lee IS et al (2005) Displaced aortic arch sign on chest radiographs: a new sign for the detection of a left paratracheal esophageal mass. Eur Radiol 15:936–940
Tomašev N, Glorot X, Rae JW et al (2019) A clinically applicable approach to continuous prediction of future acute kidney injury. Nature 572:116–119
Rajkomar A, Oren E, Chen K et al (2018) Scalable and accurate deep learning with electronic health records. NPJ Digital Medicine 1:18
Yu T, Luo J, Ahuja N (2005) Shape regularized active contour using iterative global search and local optimization. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), pp 655–662 vol. 652
van Ginneken B, Stegmann MB, Loog M (2006) Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public database. Med Image Anal 10:19–40
Shi Y, Qi F, Xue Z et al (2008) Segmenting lung fields in serial chest radiographs using both population-based and patient-specific shape statistics. IEEE Trans Med Imaging 27:481–494
Hasan MA, Lee SL, Kim DH, Lim MK (2012) Automatic evaluation of cardiac hypertrophy using cardiothoracic area ratio in chest radiograph images. Comput Methods Programs Biomed 105:95–108
Park SH, Han K (2018) Methodologic guide for evaluating clinical performance and effect of artificial intelligence technology for medical diagnosis and prediction. Radiology 286:800–809
Park SH, Kressel HY (2018) Connecting technological innovation in artificial intelligence to real-world medical practice through rigorous clinical validation: what peer-reviewed medical journals could do. J Korean Med Sci 33:e152
England JR, Cheng PM (2019) Artificial intelligence for medical image analysis: a guide for authors and reviewers. AJR Am J Roentgenol 212:513–519
This work was supported by a grant from the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health and Welfare, Republic of Korea (HI18C2383 & HI18C0022).
The scientific guarantor of this publication is Dong Hyun Yang.
Conflict of interest
The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.
Statistics and biometry
No complex statistical methods were necessary for this paper.
Written informed consent was waived by the Institutional Review Board.
Institutional Review Board approval was obtained.
• diagnostic or prognostic study
• multicenter study
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Below is the link to the electronic supplementary material.
Supplementary file2 (MP4 13894 KB)
About this article
Cite this article
Kim, C., Lee, G., Oh, H. et al. A deep learning–based automatic analysis of cardiovascular borders on chest radiographs of valvular heart disease: development/external validation. Eur Radiol 32, 1558–1569 (2022). https://doi.org/10.1007/s00330-021-08296-9