COVID-index: A texture-based approach to classifying lung lesions based on CT images

Abstract

COVID-19 is an infectious disease caused by a newly discovered type of coronavirus called SARS-CoV-2. Since the discovery of this disease in late 2019, COVID-19 has become a worldwide concern, mainly due to its high degree of contagion. As of April 2021, the number of confirmed cases of COVID-19 reported to the World Health Organization has already exceeded 135 million worldwide, while the number of deaths exceeds 2.9 million. Due to the impacts of the disease, efforts in the literature have intensified in terms of studying approaches aiming to detect COVID-19, with a focus on supporting and facilitating the process of disease diagnosis. This work proposes the application of texture descriptors based on phylogenetic relationships between species to characterize segmented CT volumes, and the subsequent classification of regions into COVID-19, solid lesion or healthy tissue. To evaluate our method, we use images from three different datasets. The results are promising, with an accuracy of 99.93%, a recall of 99.93%, a precision of 99.93%, an F1-score of 99.93%, and an AUC of 0.997. We present a robust, simple, and efficient method that can be easily applied to 2D and/or 3D images without limitations on their dimensionality.

AI-Based human audio processing for COVID-19: A comprehensive overview

“…It would be interesting to evaluate whether multi-modal analysis helps improving the accuracy of C19 detection: Image analysis is providing novel solutions using X-ray [50] , [51] , [52] , [53] , [54] , [55] and chest CT images [56] , [57] , [58] , [59] , [60] , [61] , [62] , [63] . Some of them [50] , [52] , [55] , [58] , [60] , [64] have discriminated C19 from another pulmonary disorder (pneumonia).…”

Detection of COVID-19 lesions based on computed tomography using U-Net 2.5D and GAN

“…After applying the pre-processing and lung extraction steps, this work proposes the segmentation of COVID-19 lesions. In CT, the most common lesions are ground-glass opacities, mosaic paving, consolidations, reticular opacities, subpleural lines, inverted halo sign, and pleural thickening [DE CARVALHO BRITO et al 2021]. The proposed method explores two CNN architectures U-Net and Generative Adversarial Network (GAN).…”

A fast lightweight network for the discrimination of COVID-19 and pulmonary diseases

“…Determining the feature that is capable of faithfully describing the image content is the cornerstone of recognition systems. Some researchers have opted for handcrafted features, such as gray-level co-occurrence matrix (GLCM) and histogram of gradients (HoG) [14] , [15] , [16] , while, most researchers have considered using different deep architectures to automatically learn effective representations from chest images. For instance, in [16] , GLCM and two other texture features were used to detect COVID-19 from CXR images.…”

“…For instance, in [16] , GLCM and two other texture features were used to detect COVID-19 from CXR images. In another work [15] , an experimental assessment was carried out to measure the performance of different texture features, including deep and handcrafted ones. Similarly, authors in [14] considered employing HoG together with CNN for the diagnosis of COVID-19 and pneumonia.…”