PECon: Contrastive Pretraining to Enhance Feature Alignment between CT and EHR Data for Improved Pulmonary Embolism Diagnosis

TL;DR

PECon introduces a supervised contrastive pretraining method that aligns features from CT scans and EHR data, significantly improving pulmonary embolism diagnosis accuracy and explainability.

Contribution

It proposes a novel contrastive learning approach to fuse CT and EHR data, enhancing feature alignment for better PE diagnosis.

Findings

Achieved state-of-the-art F1-score of 0.913 on RadFusion dataset.

Outperformed existing methods in PE diagnosis accuracy.

Enhanced model explainability compared to other approaches.

Abstract

Previous deep learning efforts have focused on improving the performance of Pulmonary Embolism(PE) diagnosis from Computed Tomography (CT) scans using Convolutional Neural Networks (CNN). However, the features from CT scans alone are not always sufficient for the diagnosis of PE. CT scans along with electronic heath records (EHR) can provide a better insight into the patients condition and can lead to more accurate PE diagnosis. In this paper, we propose Pulmonary Embolism Detection using Contrastive Learning (PECon), a supervised contrastive pretraining strategy that employs both the patients CT scans as well as the EHR data, aiming to enhance the alignment of feature representations between the two modalities and leverage information to improve the PE diagnosis. In order to achieve this, we make use of the class labels and pull the sample features of the same class together, while pushing away those of the other class. Results show that the proposed work outperforms the existing techniques and achieves state-of-the-art performance on the RadFusion dataset with an F1-score of 0.913, accuracy of 0.90 and an AUROC of 0.943. Furthermore, we also explore the explainability of our approach in comparison to other methods. Our code is publicly available at https://github.com/BioMedIA-MBZUAI/PECon.