Multi-scale alignment and Spatial ROI Module for COVID-19 Diagnosis

TL;DR

This paper introduces a novel deep learning framework with multi-scale spatial pooling and attention modules to improve COVID-19 lesion detection in CT and X-ray images, enhancing diagnostic accuracy.

Contribution

It proposes a deep spatial pyramid pooling and a COVID-19 infection detection module to better capture multi-scale features and focus on lesion areas, improving detection performance.

Findings

Higher accuracy in COVID-19 lesion detection across four datasets

Effective integration of multi-scale contextual information

Enhanced focus on lesion regions with the CID module

Abstract

Coronavirus Disease 2019 (COVID-19) has spread globally and become a health crisis faced by humanity since first reported. Radiology imaging technologies such as computer tomography (CT) and chest X-ray imaging (CXR) are effective tools for diagnosing COVID-19. However, in CT and CXR images, the infected area occupies only a small part of the image. Some common deep learning methods that integrate large-scale receptive fields may cause the loss of image detail, resulting in the omission of the region of interest (ROI) in COVID-19 images and are therefore not suitable for further processing. To this end, we propose a deep spatial pyramid pooling (D-SPP) module to integrate contextual information over different resolutions, aiming to extract information under different scales of COVID-19 images effectively. Besides, we propose a COVID-19 infection detection (CID) module to draw attention to the lesion area and remove interference from irrelevant information. Extensive experiments on four CT and CXR datasets have shown that our method produces higher accuracy of detecting COVID-19 lesions in CT and CXR images. It can be used as a computer-aided diagnosis tool to help doctors effectively diagnose and screen for COVID-19.