Your browser doesn't support javascript.
COVision: Convolutional Neural Network for the Differentiation of COVID-19 from Common Pulmonary Conditions using CT Scans (preprint)
medrxiv; 2023.
Preprint in English | medRxiv | ID: ppzbmed-10.1101.2023.01.22.23284880
ABSTRACT
With the growing amount of COVID-19 cases, especially in developing countries with limited medical resources, it is essential to accurately diagnose COVID-19 with high specificity. Due to characteristic ground-glass opacities (GGOs), present in both COVID-19 and other acute lung diseases, misdiagnosis occurs often 26.6% of the time in manual interpretations of CT scans. Current deep-learning models can identify COVID-19 but cannot distinguish it from other common lung diseases like bacterial pneumonia. COVision is a multi-classification convolutional neural network (CNN) that can differentiate COVID-19 from other common lung diseases, with a low false-positivity rate. This CNN achieved an accuracy of 95.8%, AUROC of 0.970, and specificity of 98%. We found a statistical significance that our CNN performs better than three independent radiologists with at least 10 years of experience. especially in differentiating COVID-19 from pneumonia. After training our CNN with 105,000 CT slices, we analyzed the activation maps of our CNN and found that lesions in COVID-19 presented peripherally, closer to the pleura, whereas pneumonia lesions presented centrally. Finally, using federated averaging, we ensemble our CNN with a pretrained clinical factors neural network (CFNN) to create a comprehensive diagnostic tool.
Subject(s)

Full text: Available Collection: Preprints Database: medRxiv Main subject: Pneumonia / Pneumonia, Bacterial / COVID-19 / Lung Diseases Language: English Year: 2023 Document Type: Preprint

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: Preprints Database: medRxiv Main subject: Pneumonia / Pneumonia, Bacterial / COVID-19 / Lung Diseases Language: English Year: 2023 Document Type: Preprint