Selected article for: "acute respiratory syndrome and lung bacterial infection"
Author: Avola, Danilo; Bacciu, Andrea; Cinque, Luigi; Fagioli, Alessio; Marini, Marco Raoul; Taiello, Riccardo
Title: Study on Transfer Learning Capabilities for Pneumonia Classification in Chest-X-Rays Image
  • Cord-id: euc72p2a
  • Document date: 2021_10_6
    • ID: euc72p2a
    Snippet: Over the last year, the severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) and its variants have highlighted the importance of screening tools with high diagnostic accuracy for new illnesses such as COVID-19. To that regard, deep learning approaches have proven as effective solutions for pneumonia classification, especially when considering chest-x-rays images. However, this lung infection can also be caused by other viral, bacterial or fungi pathogens. Consequently, efforts are being
    Document: Over the last year, the severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) and its variants have highlighted the importance of screening tools with high diagnostic accuracy for new illnesses such as COVID-19. To that regard, deep learning approaches have proven as effective solutions for pneumonia classification, especially when considering chest-x-rays images. However, this lung infection can also be caused by other viral, bacterial or fungi pathogens. Consequently, efforts are being poured toward distinguishing the infection source to help clinicians to diagnose the correct disease origin. Following this tendency, this study further explores the effectiveness of established neural network architectures on the pneumonia classification task through the transfer learning paradigm. To present a comprehensive comparison, 12 well-known ImageNet pre-trained models were fine-tuned and used to discriminate among chest-x-rays of healthy people, and those showing pneumonia symptoms derived from either a viral (i.e., generic or SARS-CoV-2) or bacterial source. Furthermore, since a common public collection distinguishing between such categories is currently not available, two distinct datasets of chest-x-rays images, describing the aforementioned sources, were combined and employed to evaluate the various architectures. The experiments were performed using a total of 6330 images split between train, validation and test sets. For all models, common classification metrics were computed (e.g., precision, f1-score) and most architectures obtained significant performances, reaching, among the others, up to 84.46% average f1-score when discriminating the 4 identified classes. Moreover, confusion matrices and activation maps computed via the Grad-CAM algorithm were also reported to present an informed discussion on the networks classifications.

    Search related documents:
    Co phrase search for related documents
    • activation function and long short: 1, 2
    • activation function and long short term: 1, 2
    • activation function and long short term memory: 1, 2
    • activation function and loss value: 1
    • active area and long short: 1, 2
    • active area and long short term: 1, 2
    • active area and long short term memory: 1
    • active area and low number: 1, 2
    • active area and low performance: 1, 2
    • adam optimizer and long short: 1, 2, 3
    • adam optimizer and long short term: 1, 2, 3
    • adam optimizer and long short term memory: 1, 2, 3
    • adam optimizer and loss value: 1
    • adaptive weight and long short: 1
    • adaptive weight and long short term: 1
    • adaptive weight and long short term memory: 1
    • long short and loss value: 1
    • long short and low accuracy: 1, 2, 3, 4
    • long short and low number: 1, 2, 3, 4, 5, 6