The accurate detection of Covid-19 from chest Computed Tomography (CT) images can assist in early diagnosis and management of the disease. This paper presents a solution for Covid-19 detection, presented in the challenge of 3rd Covid-19 competition, inside the 'AI-enabled Medical Image Analysis Workshop' organized by IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) 2023. In this work, the application of deep learning models for chest CT image analysis was investigated, focusing on the use of a ResNet as a backbone network augmented with attention mechanisms. The ResNet provides an effective feature extractor for the classification task, while the attention mechanisms improve the model's ability to focus on important regions of interest within the images. We conducted extensive experiments on a provided dataset and achieved a macro F1 score of 0.78 on the test set, demonstrating the potential to assist the diagnosis of Covid-19. Our proposed approach leverages the power of deep learning with attention mechanisms to address the challenges of Covid-19 detection in the early detection and management of the disease. In both test and validation set, the proposed method outperformed the baseline of the challenge, ranking fifth in the competition.

Attention-Based Convolutional Neural Network for CT Scan COVID-19 Detection

Guarnera F.;Giudice O.;Ortis A.;Rundo F.;Battiato S.
2023-01-01

Abstract

The accurate detection of Covid-19 from chest Computed Tomography (CT) images can assist in early diagnosis and management of the disease. This paper presents a solution for Covid-19 detection, presented in the challenge of 3rd Covid-19 competition, inside the 'AI-enabled Medical Image Analysis Workshop' organized by IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) 2023. In this work, the application of deep learning models for chest CT image analysis was investigated, focusing on the use of a ResNet as a backbone network augmented with attention mechanisms. The ResNet provides an effective feature extractor for the classification task, while the attention mechanisms improve the model's ability to focus on important regions of interest within the images. We conducted extensive experiments on a provided dataset and achieved a macro F1 score of 0.78 on the test set, demonstrating the potential to assist the diagnosis of Covid-19. Our proposed approach leverages the power of deep learning with attention mechanisms to address the challenges of Covid-19 detection in the early detection and management of the disease. In both test and validation set, the proposed method outperformed the baseline of the challenge, ranking fifth in the competition.
2023
979-8-3503-0261-5
Computed Tomography classification
Covid-19 detection
Deep Learning
Medical imaging
File in questo prodotto:
File Dimensione Formato  
85163183299.pdf

solo gestori archivio

Tipologia: Versione Editoriale (PDF)
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 1.05 MB
Formato Adobe PDF
1.05 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11769/574429
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact