Accuracy of chest radiography for evaluating significantly abnormal pulmonary vascularity in children with congenital heart disease

Tumkosit, Monravee; Yingyong, Numfon; Mahayosnond, Atchara; Choo, Ki Seok; Goo, Hyun Woo

doi:10.1007/s10554-012-0073-x

Cited by 9 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It had been taught that speci c CHDs can have classic manifestations on chest radiography. Typical examples include a boot-shaped heart [11] for tetralogy of Fallot [17], "egg on a string" for D-transposition of the great arteries [18], and a snowman appearance for total anomalous pulmonary venous connection [17], etc. Furthermore, chest radiography is useful for the assessment of PBF in CHD patients; and PBF is one of the most important ndings for differential diagnosis of CHD, especially when availability of cross-sectional imaging is limited.…”

Section: Discussionmentioning

confidence: 99%

“…Final diagnoses were determined from clinical information, computed tomography, echocardiography or surgical reports. The CHD patients with increased PBF was de ned as the ratio of pulmonary-to-systemic blood ow (Qp:Qs) of greater than 1.5 derived from cardiac catherization [11]. The patients were diagnosed to have decreased PBF by a combined evaluation of oxygen saturation and morphological features investigated with computed tomography angiography [12].…”

Section: Study Populationmentioning

confidence: 99%

See 1 more Smart Citation

Using Deep Learning to Detect Pediatric Congenital Heart Disease by Chest Radiography

Chen¹,

Wu²,

Chung³

et al. 2021

Preprint

View full text Add to dashboard Cite

Purpose: To detect congenital heart disease (CHD) patients is a challenging task in low-income areas with limited resources. Chest radiography is usually available in these areas, but the diagnostic accuracy needs to be improved. The aim of the study was to establish a deep learning-based diagnostic tool for paediatric CHD patients using chest radiography. Methods: Totally 11,105 chest radiographs from 11,105 paediatric patients in two centres were labeled, and a convolutional neural network (CNN) was trained for diagnosing CHD in the dataset from Hospital 1. To demonstrate the generalizability and the clinical usefulness of CNN, the accuracy in test set from two centres were both reported. We also trained another CNN to evaluate pulmonary blood flow (PBF) on chest radiographs of the patients. Moreover, the predictive results of both CNN were compared to the decisions of three experienced radiologists (range 10–35 years) without any patient information. Results: The accuracy of CNN for detecting CHD was 81.4% (95% confidence interval, [78.3%–84.2%]) in Hospital 2, while the accuracy was 85.6% (95% confidence interval, [84.0%–87.1%]) in Hospital 1. The overall accuracy of CNN for evaluating PBF was 78.9% (95% confidence interval, [74.3%–83.0%]). Compared to three experienced radiologists, CNN showed statistically non-inferiority at a 5% margin for the accuracy (P < 0.025) in detecting CHD and evaluating PBF.Conclusions: The deep learning-based diagnostic tool we developed could effectively detect CHD and evaluate for PBF on chest radiography. It can potentially aid the radiologists and cardiologists in the future.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Study Populationmentioning

confidence: 99%

Using Deep Learning to Detect Pediatric Congenital Heart Disease by Chest Radiography

Chen¹,

Wu²,

Chung³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In contrast, a more recent study found thoracic radiology to have a low accuracy as a diagnostic method for congenital heart diseases in dogs (Lamb;Boswood;Volkman;Connolly, 2001). In human medicine, an accuracy ranging from 30% to 78% has been shown in the differentiation of healthy patients from those with congenital heart disease, and this range of accuracy was attributed to the variation in the severity of the diseases (Tumkosit et al, 2012). However, some authors still consider radiography to be a poor test, even when performed for the purpose of screening (Fonseca;Chang;Senac;Knight;Sklansky, 2005).…”

Section: Introductionmentioning

confidence: 94%

“…Radiographic examination is routinely used because it is a lowcost technique capable of providing important complementary information in the initial assessment and therapeutic management of patients (Côté et al, 2015;Schweigmann;Gassner;Maurer, 2006). For this reason, even in humans, it remains the most common screening test in patients with suspected heart diseases (Tumkosit;Yingyong;Mahayosnond;Choo;Goo, 2012). This modality is useful in evaluating changes in cardiac size, large vessels and pulmonary vascularization.…”

Section: Introductionmentioning

confidence: 99%

Use of computed radiology as a screening test for the identification of congenital heart disease in dogs

Lucina

Silva

Giannico

et al. 2020

SCA

View full text Add to dashboard Cite

The objectives of this study were to evaluate the accuracy of thoracic radiology as a screening test for congenital heart diseases in dogs, to identify the main contributions and limitations of this modality, and to verify the reproducibility of the evaluations by three observers with different levels of training. An interobserver, observational, retrospective and prospective study was carried out, including ninety dogs: thirty healthy animals, thirty with acquired heart diseases and thirty with congenital heart diseases, which all had thoracic radiographs and a confirmed echocardiographic diagnosis. The cases were separated and randomized by a mediator who did not participate in the reading of the radiographic examinations, and no evaluator had access to the patients' data. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy of each observer were calculated in relation to the correct classification of dogs to groups of normal or acquired and congenital heart diseases, as well as identification of enlargement of the cardiac silhouette and large vessels of dogs with congenital heart diseases. Finally, the Kappa coefficient was obtained between the observers to verify the reproducibility of the radiological evaluations performed. In general, sensitivity, PPV and accuracy were unsatisfactory ( 70%), and the agreement ranged from poor to reasonable (between 0 and 0.39). Although greater accuracy was achieved in the differentiation of healthy dogs from those with acquired and congenital heart diseases by thoracic radiography, when compared to the other studies, the modality was able only to identify healthy patients, and could not differentiate the individuals with different forms of heart disease or define the cardiac malformations. In addition, there was low reproducibility between observers, therefore, this technique should not be used as a sole screening method in dogs with suspected congenital heart diseases.

show abstract

“…Study by Tumkosit et al (2012) demonstrated an accuracy of pulmonary vascularity chest x-ray interpretation compared to cardiac catheterization. They reported that chest x-ray had high sensitivity to diagnose increased pulmonary vascularity.…”

mentioning

confidence: 99%

The Improvement Chest X-Ray After Carvedilol Theraphy in Heart Failure Due to Left to Right Shunt.

Rahman¹,

Zuraedah²,

Hidayat³

et al. 2017

IJAR

View full text Add to dashboard Cite

heart failure, left to right shunt congenital heart defect, carvedilol, cardio-thoracic ratio.Background: Heart failure due to left to right shunt congenital heart defect will increase pulmonary blood flow and cause volume overload. This condition activated the sympathetic nervous system and the reninangiotensin-aldosteron system. Conventional therapy has not blocked the sympathetic system yet. Carvedilol, a novel non selective β-blocker, reduced mortality and hospitalization in adults with heart failure. Limited information was available about its use in children. Objective: To evaluate the effect of carvedilol on chest x-ray in children with heart failure due to left to right shunt congenital heart defect. Methods: A randomized, double-blind, placebo-controlled study was done. In addition to conventional therapy, patients were assigned to receive placebo or carvedilol. Carvedilol was initiated at a dose of 0.05 mg/kg/day, with a target dose of 0.2 mg/kg/day. Chest x-ray was done before-after treatment and evaluated for cardio-thoracic ratio and pulmonary vascularity. The data was analyzed using independent sample t-test and Chi-square test, with confidence interval 95%. Results: Of 30 patients, 15 in each group. The mean age was 57.6(SD 43.57) months, 19(63.3%) were boys. There were 21(70%) children with VSD and 9(30%) children with PDA. Compared to control group, children in the carvedilol group had a significant decrease of cardiothoracic ratio (-2.94±2.34% versus -0.48±3.19%, p=0.023, CI 95%:-4.556 to-0.360). However, there was no significant change of pulmonary vascularity(p=0.153). Conclusion: Carvedilol decreased the cardio-thoracic ratio on chest xray, but did not improve the pulmonary vascularity in children with heart failure due to left to right shunt Congenital heart defect.

show abstract

Accuracy of chest radiography for evaluating significantly abnormal pulmonary vascularity in children with congenital heart disease

Cited by 9 publications

References 13 publications

Using Deep Learning to Detect Pediatric Congenital Heart Disease by Chest Radiography

Using Deep Learning to Detect Pediatric Congenital Heart Disease by Chest Radiography

Use of computed radiology as a screening test for the identification of congenital heart disease in dogs

The Improvement Chest X-Ray After Carvedilol Theraphy in Heart Failure Due to Left to Right Shunt.

Contact Info

Product

Resources

About