Quantification of pulmonary involvement in COVID-19 pneumonia by means of a cascade of two U-nets: training and assessment on multiple datasets using different annotation criteria.

Journal: International journal of computer assisted radiology and surgery
Published Date: Oct 26, 2021

Abstract

PURPOSE: This study aims at exploiting artificial intelligence (AI) for the identification, segmentation and quantification of COVID-19 pulmonary lesions. The limited data availability and the annotation quality are relevant factors in training AI-methods. We investigated the effects of using multiple datasets, heterogeneously populated and annotated according to different criteria.

Authors

  • Francesca Lizzi
    Scuola Normale Superiore, Pisa, Italy. francesca.lizzi@sns.it.
  • Abramo Agosti
    Department of Mathematics, University of Pavia, Pavia, Italy.
  • Francesca Brero
    INFN, Pavia division, Pavia, Italy.
  • Raffaella Fiamma Cabini
    INFN, Pavia division, Pavia, Italy.
  • Maria Evelina Fantacci
    Istituto Nazionale di Fisica Nucleare, Sezione di Pisa, Pisa, Italy.
  • Silvia Figini
    INFN, Pavia division, Pavia, Italy.
  • Alessandro Lascialfari
    INFN, Pavia division, Pavia, Italy.
  • Francesco Laruina
    Scuola Normale Superiore, Pisa, Italy.
  • Piernicola Oliva
    Department of Chemistry and Pharmacy, University of Sassari, Sassari, Italy.
  • Stefano Piffer
    Department of Biomedical Experimental Clinical Science "M. Serio", University of Florence, Florence, Italy.
  • Ian Postuma
    INFN, Pavia division, Pavia, Italy.
  • Lisa Rinaldi
    INFN, Pavia division, Pavia, Italy.
  • Cinzia Talamonti
    Department of Biomedical Experimental Clinical Science "M. Serio", University of Florence, Florence, Italy.
  • Alessandra Retico
    Istituto Nazionale di Fisica Nucleare, Sezione di Pisa, Pisa, Italy.

Keywords

External Resources

Popular Topics
Recent Journals