Prediction of Pulmonary to Systemic Flow Ratio in Patients With Congenital Heart Disease Using Deep Learning–Based Analysis of Chest Radiographs

Abstract Background Deep learning algorithms are increasingly used for automatic medical imaging analysis and cardiac chamber segmentation. Especially in congenital heart disease, obtaining a sufficient number of training images and data anonymity issues remain of concern. Methods Progressive generative adversarial networks (PG-GAN) were trained on cardiac magnetic resonance imaging (MRI) frames from a nationwide prospective study to generate synthetic MRI frames. These synthetic frames were subsequently used to train segmentation networks (U-Net) and the quality of the synthetic training images, as well as the performance of the segmentation network was compared to U-Net-based solutions trained entirely on patient data. Results Cardiac MRI data from 303 patients with Tetralogy of Fallot were used for PG-GAN training. Using this model, we generated 100,000 synthetic images with a resolution of 256 × 256 pixels in 4-chamber and 2-chamber views. All synthetic samples were classified as anatomically plausible by human observers. The segmentation performance of the U-Net trained on data from 42 separate patients was statistically significantly better compared to the PG-GAN based training in an external dataset of 50 patients, however, the actual difference in segmentation quality was negligible (< 1% in absolute terms for all models). Conclusion We demonstrate the utility of PG-GANs for generating large amounts of realistically looking cardiac MRI images even in rare cardiac conditions. The generated images are not subject to data anonymity and privacy concerns and can be shared freely between institutions. Training supervised deep learning segmentation networks on this synthetic data yielded similar results compared to direct training on original patient data.

Download Full-text

Chest radiographic findings in children with asplenia syndrome

Asian Biomedicine ◽

10.2478/abm-2010-0074 ◽

2010 ◽

Vol 4 (4) ◽

pp. 585-594

Author(s):

Panruethai Trinavarat ◽

Kullana Tantiprawan ◽

Apichai Khongphatthanayothin

Keyword(s):

Congenital Heart Disease ◽

Heart Disease ◽

Congenital Heart ◽

Heart Diseases ◽

Pulmonary Atresia ◽

Chest Radiographs ◽

Pulmonary Vasculature ◽

Ipsilateral Side ◽

Radiographic Findings ◽

Asplenia Syndrome

Abstract Background: Early diagnosis of asplenia syndrome is important because prophylactic antibiotic and proper vaccination will prevent serious infection. Most children with asplenia syndrome present with symptoms of congenital heart disease. Chest X-ray is usually the first line imaging modality. Objective: Define useful findings in chest radiograph that could suggest the diagnosis of asplenia syndrome. Methods: Chest radiographs of pediatric patients who had asplenia syndrome diagnosed between January 1, 2002 and June 30, 2008 in a single institute were retrospectively reviewed for the positions of the visceral organs in the chest and abdomen. Results: Three hundred seventy one chest radiographs of 30 patients were reviewed. The mean age at diagnosis was 3 years old. Asplenia was diagnosed by ultrasound in 27 patients, by CT scan in two patients, and by damaged red blood cell scintigraphy in one patient. Six important findings detected from chest radiographs were, 1) bilateral minor fissures, 16 cases (53%), 2) bilateral eparterial bronchi, 16 cases (53%), 3) ipsilateral side of stomach and liver, 12 cases (40%), 4) ipsilateral side of minor fissure or eparterial bronchus and stomach, 10 cases (33%), 5) symmetrical transverse lie of the liver, nine cases (30%), and 6) contralateral side of minor fissure or eparterial bronchus and the liver in seven cases (23%). All except two patients (93%) had at least one of the above findings. All patients had congenital heart diseases. Most of the heart diseases were pulmonary atresia or pulmonary stenosis (88%) and single ventricle (85%). Conclusion: Chest radiographs have high sensitivity in suggesting the diagnosis of asplenia syndrome, when detecting one or more of the above findings, particular in patients with congenital heart disease and decreased pulmonary vasculature.

Download Full-text