Robust Weakly Supervised Learning for COVID-19 Recognition Using Multi-Center CT Images

TL;DR

This paper introduces CIFD-Net, a robust weakly supervised learning model that effectively addresses multi-domain shift in multi-center COVID-19 CT scan recognition, improving accuracy and reliability over existing methods.

Contribution

The paper proposes a novel weakly supervised learning paradigm and CIFD-Net model to handle multi-domain shifts in COVID-19 CT recognition, enhancing accuracy and robustness.

Findings

CIFD-Net outperforms state-of-the-art methods in accuracy.

The model effectively handles multi-center, multi-scanner variability.

Robustness against domain shifts improves diagnostic reliability.

Abstract

The world is currently experiencing an ongoing pandemic of an infectious disease named coronavirus disease 2019 (i.e., COVID-19), which is caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Computed Tomography (CT) plays an important role in assessing the severity of the infection and can also be used to identify those symptomatic and asymptomatic COVID-19 carriers. With a surge of the cumulative number of COVID-19 patients, radiologists are increasingly stressed to examine the CT scans manually. Therefore, an automated 3D CT scan recognition tool is highly in demand since the manual analysis is time-consuming for radiologists and their fatigue can cause possible misjudgment. However, due to various technical specifications of CT scanners located in different hospitals, the appearance of CT images can be significantly different leading to the failure of many automated image recognition approaches. The multi-domain shift problem for the multi-center and multi-scanner studies is therefore nontrivial that is also crucial for a dependable recognition and critical for reproducible and objective diagnosis and prognosis. In this paper, we proposed a COVID-19 CT scan recognition model namely coronavirus information fusion and diagnosis network (CIFD-Net) that can efficiently handle the multi-domain shift problem via a new robust weakly supervised learning paradigm. Our model can resolve the problem of different appearance in CT scan images reliably and efficiently while attaining higher accuracy compared to other state-of-the-art methods.