Computer-assisted detection of acute pulmonary embolism at CT pulmonary angiography in children and young adults: a diagnostic performance analysis

Automatic detection of pulmonary embolism on computed tomography pulmonary angiogram scan using a three-dimensional convolutional neural network

OBJECTIVE

To propose a convolutional neural network (EmbNet) for automatic pulmonary embolism detection on computed tomography pulmonary angiogram (CTPA) scans and to assess its diagnostic performance.

METHODS

305 consecutive CTPA scans between January 2019 and December 2021 were enrolled in this study (142 for training, 163 for internal validation), and 250 CTPA scans from a public dataset were used for external validation. The framework comprised a preprocessing step to segment the pulmonary vessels and the EmbNet to detect emboli. Emboli were divided into three location-based subgroups for detailed evaluation: central arteries, lobar branches, and peripheral regions. Ground truth was established by three radiologists.

RESULTS

The EmbNet's per-scan level sensitivity, specificity, positive predictive value (PPV), and negative predictive value were 90.9%, 75.4%, 48.4%, and 97.0% (internal validation) and 88.0%, 70.5%, 42.7%, and 95.9% (external validation). At the per-embolus level, the overall sensitivity and PPV of the EmbNet were 86.0% and 61.3% (internal validation), and 83.5% and 57.5% (external validation). The sensitivity and PPV of central emboli were 89.7% and 52.0% (internal validation), and 94.4% and 43.0% (external validation); of lobar emboli were 95.2% and 76.9% (internal validation), and 93.5% and 72.5% (external validation); and of peripheral emboli were 82.6% and 61.7% (internal validation), and 80.2% and 59.4% (external validation). The average false positive rate was 0.45 false emboli per scan (internal validation) and 0.69 false emboli per scan (external validation).

CONCLUSION

The EmbNet provides high sensitivity across embolus locations, suggesting its potential utility for initial screening in clinical practice.

Prevalence and Associated Risk Factors of Pulmonary Embolism in Children and Young Adults With Nephrotic Syndrome: A Chinese Large Cohort Study

PURPOSE

Nephrotic syndrome (NS) is highly associated with an increased risk of pulmonary embolism (PE) in children and young adults. However, few studies have specified the risk factors of PE in children and young adults with NS. We sought to determine the prevalence and associated factors of PE confirmed with computed tomography pulmonary angiography in Chinese children and young adults with NS.

METHODS

Data from 444 children and young adults with NS who had computed tomography pulmonary angiography from December 2010 to October 2018 were retrospectively analyzed. The prevalence of PE was estimated for different age, sex, and histopathologic types of NS. Multivariable logistic regression was used to identify independent risk factors of PE in children and young adults with NS. Models incorporating the independent risk factors were evaluated using receiver operation characteristic curves. Area under the curve was used to determine the best-performing prognosticators for predicting PE.

RESULTS

There were 444 patients in the study cohort (310 male patients, 134 female patients; mean age 19±3 y; range: 6 to 25 y). PE was present in 24.8% of the participants (110 of 444, 18.2% female). Children and young adult NS patients with PE tend to be older, male, to have a previous thromboembolism history and smoking, and have a higher level of proteinuria, D-dimer, and serum albumin (P<0.05 for all). Children and young adults with membranous nephropathy are likely to have a higher incidence of PE than those with other types of nephropathy. Membranous nephropathy and proteinuria were significant predictors of PE in children and young adults with NS (P<0.05 for all). The area under the curves of each model for the presence of PE in children and young adults with NS based on biochemical parameters and clinical information (model 1), adjusted for proteinuria (model 2), and adjusted for membranous nephropathy (model 3) were 0.578, 0.657, and 0.709, respectively. Compared with model 1, model 2, and model 3 showed statistically significant differences (model 1 vs. model 2, P=0.0336; model 1 vs. model 3, P=0.0268). There was no statistically significant difference between model 2 and model 3 (P=0.2947).

CONCLUSION

This study identified membranous nephropathy and proteinuria as independent associated factors of PE in children and young adults with NS, which can be noted as a risk factor to guide clinician management in this population.