Pristine annotations-based multi-modal trained artificial intelligence solution to triage chest X-ray for COVID-19

TL;DR

This paper presents a novel AI model for COVID-19 triage using chest X-ray images trained with both X-ray and CT data, improving accuracy and localization over X-ray only models.

Contribution

It introduces the first multi-modal training approach for X-ray based COVID-19 triage, enhancing model performance compared to single-modality training.

Findings

AUC improved from 0.89 to 0.93 with multi-modal training

Dice coefficient increased from 0.59 to 0.62

First to leverage multi-modal data for X-ray COVID-19 diagnosis

Abstract

The COVID-19 pandemic continues to spread and impact the well-being of the global population. The front-line modalities including computed tomography (CT) and X-ray play an important role for triaging COVID patients. Considering the limited access of resources (both hardware and trained personnel) and decontamination considerations, CT may not be ideal for triaging suspected subjects. Artificial intelligence (AI) assisted X-ray based applications for triaging and monitoring require experienced radiologists to identify COVID patients in a timely manner and to further delineate the disease region boundary are seen as a promising solution. Our proposed solution differs from existing solutions by industry and academic communities, and demonstrates a functional AI model to triage by inferencing using a single x-ray image, while the deep-learning model is trained using both X-ray and CT data. We report on how such a multi-modal training improves the solution compared to X-ray only training. The multi-modal solution increases the AUC (area under the receiver operating characteristic curve) from 0.89 to 0.93 and also positively impacts the Dice coefficient (0.59 to 0.62) for localizing the pathology. To the best our knowledge, it is the first X-ray solution by leveraging multi-modal information for the development.