# Deep learning-based identification of chronic pulmonary embolism on CTPA: a regional lung analysis using multiplanar MIP images

## TL;DR

A deep learning model can identify chronic pulmonary embolism and related conditions from CT scans by analyzing different lung regions.

## Contribution

The study introduces a novel regional lung analysis using multiplanar MIP images to improve chronic pulmonary embolism detection with CNNs.

## Key findings

- The CNN achieved an AUROC of 0.80 for CPE detection using full lung volume MIPs.
- Proximal vessels were most important for CTEPH detection, with AUROC of 0.88 using full data.
- Including more vascular regions improved model performance for both CPE and CTEPH classification.

## Abstract

Chronic pulmonary embolism (CPE) and chronic thromboembolic pulmonary hypertension (CTEPH) are challenging to diagnose, with delayed detection increasing mortality. We evaluated the performance of a convolutional neural network (CNN) in identifying these conditions from computed tomography pulmonary angiography (CTPA)-derived maximum intensity projection (MIP) images using a novel approach including proximal pulmonary vessels and a layered segmentation of the lung volume to assess the diagnostic value of different vascular regions.

We included 41 CPE, 41 acute pulmonary embolism (APE) and 41 normal controls (non-PE). 25 of the CPE patients had CTEPH confirmed by right heart catheterization. CNN classifiers were trained to identify CPE or CTEPH against a combined APE and non-PE group. Eleven masking schemes were applied for both classification tasks, resulting in 22 experiments. Model performances were compared using areas under the receiver operating characteristic curves (AUROC).

The model achieved good performance in distinguishing CPE from non-PE and APE cases (cross-validation AUROC 0.80) using full lung volume MIPs, while performance decreased with reduced data. For CTEPH classification against non-PE and APE, the model reached AUROC 0.88 with full data and 0.86 using only the most proximal half of the lung volume, suggesting key diagnostic features reside centrally. Using an open-source segmentation model, which excludes proximal vessels, resulted in lower AUROCs (0.74 for CPE, 0.83 for CTEPH).

The cross-validation indicated that CPE and CTEPH could be identified from CTPA-derived MIP images, with performance improving as more vessels were included. The proximal vessels were most relevant for CTEPH detection.

Our study shows that neural networks can identify chronic pulmonary embolism in CTPA and the role of different vascular regions in that task, with the potential to improve future imaging diagnostics in patients with chronic pulmonary embolism.

A convolutional neural network detects chronic thromboembolic pulmonary hypertension and chronic embolism from CTPA MIP projections.CTPA data were divided into four concentric anatomic layers for regional analysis.Central layers were most important for identifying CTEPH features.Network performance improved when more vessel regions were used as input.

A convolutional neural network detects chronic thromboembolic pulmonary hypertension and chronic embolism from CTPA MIP projections.

CTPA data were divided into four concentric anatomic layers for regional analysis.

Central layers were most important for identifying CTEPH features.

Network performance improved when more vessel regions were used as input.