3D Convolutional Neural Network for Covid Assessment on CT Scans
10th KES International Conference on Innovation in Medicine and Healthcare, KES-InMed 2022
; 308:3-14, 2022.
Article
in English
| Scopus | ID: covidwho-1971636
ABSTRACT
Due to the rapid spread of the COVID-19 respiratory pathology, an effective diagnosis of positive cases is necessary to stop the contamination. CT scans offer a 3D view of the patient’s thorax and COVID-19 appears as ground glass opacities on these images. This paper describes a deep learning based approach to automatically classify CT scan images as COVID-19 or not COVID-19. We first build a dataset and preprocess this data. Preprocessing includes normalization, resizing and data augmentation. Then, the training step is based on a neural network used for tuberculosis pathology. Training of the dataset is performed using a 3D convolutional neural network. The results of the neural network model on the test set returns an accuracy of 80%. A prototype of the approach is implemented in a form of a web application to assist doctors and speed up the COVID-19 diagnosis. Codes of both the training and the web application are available online for further research. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
3D CNN; COVID-19; COVID-19 diagnosis; Deep learning; Computerized tomography; Convolution; Convolutional neural networks; Diagnosis; Pathology; Convolutional neural network; COVID-19 diagnose; CT-scan; Ground-glass opacity; Learning-based approach; Respiratory pathology; WEB application; Web applications
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
10th KES International Conference on Innovation in Medicine and Healthcare, KES-InMed 2022
Year:
2022
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS