From Early Morphometrics to Machine Learning-What Future for Cardiovascular Imaging of the Pulmonary Circulation?

External validation, radiological evaluation, and development of deep learning automatic lung segmentation in contrast-enhanced chest CT

OBJECTIVES

There is a need for CT pulmonary angiography (CTPA) lung segmentation models. Clinical translation requires radiological evaluation of model outputs, understanding of limitations, and identification of failure points. This multicentre study aims to develop an accurate CTPA lung segmentation model, with evaluation of outputs in two diverse patient cohorts with pulmonary hypertension (PH) and interstitial lung disease (ILD).

METHODS

This retrospective study develops an nnU-Net-based segmentation model using data from two specialist centres (UK and USA). Model was trained (n = 37), tested (n = 12), and clinically evaluated (n = 176) on a diverse 'real-world' cohort of 225 PH patients with volumetric CTPAs. Dice score coefficient (DSC) and normalised surface distance (NSD) were used for testing. Clinical evaluation of outputs was performed by two radiologists who assessed clinical significance of errors. External validation was performed on heterogenous contrast and non-contrast scans from 28 ILD patients.

RESULTS

A total of 225 PH and 28 ILD patients with diverse demographic and clinical characteristics were evaluated. Mean accuracy, DSC, and NSD scores were 0.998 (95% CI 0.9976, 0.9989), 0.990 (0.9840, 0.9962), and 0.983 (0.9686, 0.9972) respectively. There were no segmentation failures. On radiological review, 82% and 71% of internal and external cases respectively had no errors. Eighteen percent and 25% respectively had clinically insignificant errors. Peripheral atelectasis and consolidation were common causes for suboptimal segmentation. One external case (0.5%) with patulous oesophagus had a clinically significant error.

CONCLUSION

State-of-the-art CTPA lung segmentation model provides accurate outputs with minimal clinical errors on evaluation across two diverse cohorts with PH and ILD.

CLINICAL RELEVANCE

Clinical translation of artificial intelligence models requires radiological review and understanding of model limitations. This study develops an externally validated state-of-the-art model with robust radiological review. Intended clinical use is in techniques such as lung volume or parenchymal disease quantification.

KEY POINTS

• Accurate, externally validated CT pulmonary angiography (CTPA) lung segmentation model tested in two large heterogeneous clinical cohorts (pulmonary hypertension and interstitial lung disease). • No segmentation failures and robust review of model outputs by radiologists found 1 (0.5%) clinically significant segmentation error. • Intended clinical use of this model is a necessary step in techniques such as lung volume, parenchymal disease quantification, or pulmonary vessel analysis.

The Diagnostic Approach to Pulmonary Hypertension

The clinical presentation of pulmonary hypertension (PH) is nonspecific, resulting in significant delays in its detection. In the majority of cases, PH is a marker of the severity of other cardiopulmonary diseases. Differential diagnosis aimed at the early identification of patients with pulmonary arterial hypertension (PAH) and chronic thromboembolic pulmonary hypertension (CTEPH) who do require specific and complex therapies is as important as PH detection itself. Despite all efforts aimed at the noninvasive assessment of pulmonary arterial pressure, the formal confirmation of PH still requires catheterization of the right heart and pulmonary artery. The current document will give an overview of strategies aimed at the early diagnosis of PAH and CTEPH, while avoiding their overdiagnosis. It is not intended to be a replica of the recently published European Society of Cardiology (ESC) and European Respiratory Society (ERS) Guidelines on Diagnosis and Treatment of Pulmonary Hypertension, freely available at the Web sites of both societies. While promoting guidelines' recommendations, including those on new definitions of PH, we will try to bring them closer to everyday clinical practice, benefiting from our personal experience in managing patients with suspected PH.