Related Experiment Video
Updated: Aug 26, 2025
Four-Dimensional Computed Tomography-Guided Valve Sizing for Transcatheter Pulmonary Valve Replacement
Published on: January 20, 2022
Fully automatic cardiac four chamber and great vessel segmentation on CT pulmonary angiography using deep learning
Michael J Sharkey1,2, Jonathan C Taylor2, Samer Alabed1
1Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, United Kingdom.
Insights
This study developed an automated deep learning model for segmenting the heart and great vessels in computed tomography pulmonary angiography (CTPA) scans. The model accurately assesses cardiac structures, improving pulmonary vascular disease diagnosis and hemodynamic prediction.
Area of Science:
- Medical Imaging
- Cardiovascular Imaging
- Artificial Intelligence in Medicine
Background:
- Computed tomography pulmonary angiography (CTPA) is crucial for diagnosing pulmonary vascular diseases like pulmonary hypertension and embolism.
- Current cardiac and great vessel assessments in CTPA rely on manual measurements with poor reproducibility.
- Automated segmentation offers a solution to improve the accuracy and consistency of CTPA analysis.
Purpose of the Study:
- To develop an automated deep learning model for whole heart segmentation (four chambers and great vessels) in CTPA.
- To evaluate the accuracy and generalizability of the automated segmentation model.
- To assess the correlation of deep learning-derived volumetric biomarkers with invasive hemodynamics.
Main Methods:
- A nine-structure semantic segmentation model was developed using deep learning (convolutional neural network) on 200 patients.
- The model was trained and validated, with testing on internal (100 patients) and external (20 patients) cohorts.
- Ground truth segmentations were performed by expert cardiothoracic radiologists, and failure analysis was conducted in 1,333 patients.
Main Results:
- The automated model achieved high Dice similarity coefficients (DSC) for most structures (0.87-0.93), indicating accurate segmentation.
- Left and right ventricle myocardium segmentations showed lower DSC (0.83 and 0.58) but comparable to interobserver variability.
- Deep learning volumetric biomarkers showed strong correlation with invasive hemodynamics, outperforming manual measurements.
Conclusions:
- Fully automated segmentation of the heart and great vessels in CTPA has been successfully achieved with high accuracy and low failure rates.
- The developed deep learning model demonstrates good generalizability across different vendors and hospitals.
- Automated volumetric biomarkers from CTPA hold potential for improving cardiac assessment and predicting invasive hemodynamics.
Introduction:
Computed tomography pulmonary angiography (CTPA) is an essential test in the work-up of suspected pulmonary vascular disease including pulmonary hypertension and pulmonary embolism. Cardiac and great vessel assessments on CTPA are based on visual assessment and manual measurements which are known to have poor reproducibility. The primary aim of this study was to develop an automated whole heart segmentation (four chamber and great vessels) model for CTPA.
Methods:
A nine structure semantic segmentation model of the heart and great vessels was developed using 200 patients (80/20/100 training/validation/internal testing) with testing in 20 external patients. Ground truth segmentations were performed by consultant cardiothoracic radiologists. Failure analysis was conducted in 1,333 patients with mixed pulmonary vascular disease. Segmentation was achieved using deep learning via a convolutional neural network. Volumetric imaging biomarkers were correlated with invasive haemodynamics in the test cohort.
Results:
Dice similarity coefficients (DSC) for segmented structures were in the range 0.58-0.93 for both the internal and external test cohorts. The left and right ventricle myocardium segmentations had lower DSC of 0.83 and 0.58 respectively while all other structures had DSC >0.89 in the internal test cohort and >0.87 in the external test cohort. Interobserver comparison found that the left and right ventricle myocardium segmentations showed the most variation between observers: mean DSC (range) of 0.795 (0.785-0.801) and 0.520 (0.482-0.542) respectively. Right ventricle myocardial volume had strong correlation with mean pulmonary artery pressure (Spearman's correlation coefficient = 0.7). The volume of segmented cardiac structures by deep learning had higher or equivalent correlation with invasive haemodynamics than by manual segmentations. The model demonstrated good generalisability to different vendors and hospitals with similar performance in the external test cohort. The failure rates in mixed pulmonary vascular disease were low (<3.9%) indicating good generalisability of the model to different diseases.
Conclusion:
Fully automated segmentation of the four cardiac chambers and great vessels has been achieved in CTPA with high accuracy and low rates of failure. DL volumetric biomarkers can potentially improve CTPA cardiac assessment and invasive haemodynamic prediction.
