# AI-Based Pulmonary Embolism Detection: The Added Value of a False-Positive Reduction Module over a Region Proposal Network

## TL;DR

This study shows that adding a false-positive reduction module to an AI model improves the accuracy of detecting pulmonary embolism in CT scans.

## Contribution

The study introduces a modified AI model that significantly reduces false positives in pulmonary embolism detection.

## Key findings

- The Modified Mask R-CNN reduced false-positive rate per scan by 31% compared to the RPN-only model.
- Positive Predictive Value increased by 10.5% with the modified model.
- The model showed a 7.4% improvement in detecting clinically significant emboli.

## Abstract

Background: High false-positive rates remain a significant challenge in the automated detection of pulmonary embolism (PE) using Computed Tomography Pulmonary Angiography (CTPA). This study evaluated the additional value of a False-Positive Reduction (FPR) module integrated into a Region Proposal Network (RPN). Methods: A retrospective analysis of 303 CTPA scans (163 PE-positive and 140 PE-negative) was conducted from a single tertiary institution. Both models were additionally validated on an independent external cohort of 100 CTPA scans (50 PE-positive and 50 PE-negative) from the RSNA PE Challenge dataset. The diagnostic performance of the one-stage RPN-only model was compared with that of a two-stage Modified Mask R-CNN (Region-based Convolutional Neural Network) incorporating the FPR module. Results: The Modified Mask R-CNN exhibited significant improvement in terms of specificity. The false-positive rate per scan decreased by 31% in comparison to the RPN-only model. Although there was a slight reduction in patient-level sensitivity, the Positive Predictive Value significantly increased by 10.5%. Additionally, patient-level specificity for emboli with a volume ≥ 1000 mm3 increased, reflecting a 7.4% relative improvement in detecting clinically significant emboli. Conclusions: The Modified Mask R-CNN significantly reduced false positives while maintaining high sensitivity over a region proposal network.