Background: COVID assessment can be performed using the recently developed individual risk score (prediction of severe respiratory failure in hospitalized patients with SARS-COV2 infection, PREDI-CO score) based on High Resolution Computed Tomography. In this study, we evaluated the possibility of automatizing this estimation using semi-supervised AI-based Radiomics, leveraging the possibility of performing non-supervised segmentation of ground-glass areas. Methods: We collected 92 from patients treated in the IRCCS Sant’Orsola-Malpighi Policlinic and public databases; each lung was segmented using a pre-trained AI method; ground-glass opacity was identified using a novel, non-supervised approach; radiomic measurements were collected and used to predict clinically relevant scores, with particular focus on mortality and the PREDI-CO score. We compared the prediction obtained through different machine learning approaches. Results: All the methods obtained a well-balanced accuracy (70%) on the PREDI-CO score but did not obtain satisfying results on other clinical characteristics due to unbalance between the classes. Conclusions: Semi-supervised segmentation, implemented using a combination of non-supervised segmentation and feature extraction, seems to be a viable approach for patient stratification and could be leveraged to train more complex models. This would be useful in a high-demand situation similar to the current pandemic to support gold-standard segmentation for AI training.

Classification performance for covid patient prognosis from automatic ai segmentation—a single-center study

Biondi R.
Primo
;
Curti N.
Secondo
;
Giampieri E.;Vara G.;Bartoletti M.;Cattabriga A.;Cocozza M. A.;Ciccarese F.;De Benedittis C.;Cercenelli L.;Bortolani B.;Marcelli E.;Pierotti L.;Viale P.;Golfieri R.
Penultimo
;
Castellani G.
Ultimo
2021

Abstract

Background: COVID assessment can be performed using the recently developed individual risk score (prediction of severe respiratory failure in hospitalized patients with SARS-COV2 infection, PREDI-CO score) based on High Resolution Computed Tomography. In this study, we evaluated the possibility of automatizing this estimation using semi-supervised AI-based Radiomics, leveraging the possibility of performing non-supervised segmentation of ground-glass areas. Methods: We collected 92 from patients treated in the IRCCS Sant’Orsola-Malpighi Policlinic and public databases; each lung was segmented using a pre-trained AI method; ground-glass opacity was identified using a novel, non-supervised approach; radiomic measurements were collected and used to predict clinically relevant scores, with particular focus on mortality and the PREDI-CO score. We compared the prediction obtained through different machine learning approaches. Results: All the methods obtained a well-balanced accuracy (70%) on the PREDI-CO score but did not obtain satisfying results on other clinical characteristics due to unbalance between the classes. Conclusions: Semi-supervised segmentation, implemented using a combination of non-supervised segmentation and feature extraction, seems to be a viable approach for patient stratification and could be leveraged to train more complex models. This would be useful in a high-demand situation similar to the current pandemic to support gold-standard segmentation for AI training.
2021
Biondi R.; Curti N.; Coppola F.; Giampieri E.; Vara G.; Bartoletti M.; Cattabriga A.; Cocozza M.A.; Ciccarese F.; De Benedittis C.; Cercenelli L.; Bortolani B.; Marcelli E.; Pierotti L.; Strigari L.; Viale P.; Golfieri R.; Castellani G.
File in questo prodotto:
File Dimensione Formato  
12.Biondi-Classification Performance for COVID Patients.pdf

accesso aperto

Descrizione: Articolo in rivista
Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 4.12 MB
Formato Adobe PDF
4.12 MB Adobe PDF Visualizza/Apri
applsci-11-05438-s001.zip

accesso aperto

Tipo: File Supplementare
Licenza: Licenza per accesso libero gratuito
Dimensione 191.26 kB
Formato Zip File
191.26 kB Zip File 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/11585/853769
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 4
social impact