Multi-Feature Multi-Scale CNN-Derived COVID-19 Classification from Lung Ultrasound Data

TL;DR

This paper presents a multi-feature, multi-scale CNN approach using lung ultrasound data to classify COVID-19, offering a noninvasive, cost-effective alternative to traditional imaging methods with promising results.

Contribution

The study introduces a novel multi-scale residual CNN with feature fusion for COVID-19 classification from lung ultrasound images, integrating local phase and radial symmetry features.

Findings

Achieved high classification accuracy on POCUS and ICLUS-DB datasets.

Demonstrated the effectiveness of multi-feature fusion in improving diagnostic performance.

Validated the potential of ultrasound-based deep learning for COVID-19 detection.

Abstract

The global pandemic of the novel coronavirus disease 2019 (COVID-19) has put tremendous pressure on the medical system. Imaging plays a complementary role in the management of patients with COVID-19. Computed tomography (CT) and chest X-ray (CXR) are the two dominant screening tools. However, difficulty in eliminating the risk of disease transmission, radiation exposure and not being costeffective are some of the challenges for CT and CXR imaging. This fact induces the implementation of lung ultrasound (LUS) for evaluating COVID-19 due to its practical advantages of noninvasiveness, repeatability, and sensitive bedside property. In this paper, we utilize a deep learning model to perform the classification of COVID-19 from LUS data, which could produce objective diagnostic information for clinicians. Specifically, all LUS images are processed to obtain their corresponding local phase filtered images and radial symmetry transformed images before fed into the multi-scale residual convolutional neural network (CNN). Secondly, image combination as the input of the network is used to explore rich and reliable features. Feature fusion strategy at different levels is adopted to investigate the relationship between the depth of feature aggregation and the classification accuracy. Our proposed method is evaluated on the point-of-care US (POCUS) dataset together with the Italian COVID-19 Lung US database (ICLUS-DB) and shows promising performance for COVID-19 prediction.