Busca avançada
Ano de início
Entree


A deep learning approach for COVID-19 screening and localization on Chest X-Ray images

Texto completo
Autor(es):
Marcomini, Karem Daiane ; Cardona Cardenas, Diego Armando ; Machado Traina, Agma Juci ; Krieger, Jose Eduardo ; Gutierrez, Marco Antonio ; Drukker, K ; Iftekharuddin, KM
Número total de Autores: 7
Tipo de documento: Artigo Científico
Fonte: MEDICAL IMAGING 2022: COMPUTER-AIDED DIAGNOSIS; v. 12033, p. 9-pg., 2022-01-01.
Resumo

Chest X-ray (CXR) images have a high potential in the monitoring and examination of various lung diseases, including COVID-19. However, the screening of a large number of patients with diagnostic hypothesis for COVID-19 poses a major challenge for physicians. In this paper, we propose a deep learning-based approach that can simultaneously suggest a diagnose and localize lung opacity areas in CXR images. We used a public dataset containing 5, 639 posteroanterior CXR images. Due to unbalanced classes (69.2% of the images are COVID-19 positive), data augmentation was applied only to images belonging to the normal category. We split the dataset into train and test sets with proportional rate at 90:10. To the classification task, we applied 5-fold cross-validation to the training set. The EfficientNetB4 architecture was used to perform this classification. We used a YOLOv5 pre-trained in COCO dataset to the detection task. Evaluations were based on accuracy and area under the ROC curve (AUROC) metrics to the classification task and mean average precision (mAP) to the detection task. The classification task achieved an average accuracy of 0.83 +/- 0.01 (95% CI [0.81, 0.84]) and AUC of 0.88 +/- 0.02 (95% CI [0.85, 0.89]) in 5-fold over the test dataset. The best result was reached in fold 3 (0.84 and 0.89 of accuracy and AUC, respectively). Positive results were evaluated by the opacity detector, which achieved a mAP of 59.51%. Thus, the good performance and rapid diagnostic prediction make the system a promising means to assist radiologists in decision making tasks. (AU)

Processo FAPESP: 20/07200-9 - Analisando dados complexos vinculados a COVID-19 para apoio à tomada de decisão e prognóstico
Beneficiário:Agma Juci Machado Traina
Modalidade de apoio: Auxílio à Pesquisa - Regular
Processo FAPESP: 16/17078-0 - Mineração, indexação e visualização de Big Data no contexto de sistemas de apoio à decisão clínica (MIVisBD)
Beneficiário:Agma Juci Machado Traina
Modalidade de apoio: Auxílio à Pesquisa - Temático
Processo FAPESP: 20/14180-4 - Desenvolvimento de marcadores radiográficos quantitativos para Medicina de Precisão de síndromes respiratórias agudas
Beneficiário:Karem Daiane Marcomini
Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado