This article is a Preprint
Preprints are preliminary research reports that have not been certified by peer review. They should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Preprints posted online allow authors to receive rapid feedback and the entire scientific community can appraise the work for themselves and respond appropriately. Those comments are posted alongside the preprints for anyone to read them and serve as a post publication assessment.
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.
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