Classification Performance for COVID Patient Prognosis from Automatic AI Segmentation—A Single-Center Study

Riccardo Biondi,Gastone Castellani,Maria Adriana Cocozza,Enrico Giampieri,Federica Ciccarese,Nico Curti,Rita Golfieri,Laura Cercenelli,Barbara Bortolani,Caterina De Benedittis,Francesca Coppola,Emanuela Marcelli,Giulio Vara,Lidia Strigari,Luisa Pierotti,Arrigo Cattabriga,Michele Bartoletti,Pierluigi Viale

doi:10.3390/app11125438

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.

Highlights

Since the beginning of last year, the world has been facing a health emergency, the pandemic caused by the novel Coronavirus, Sars-CoV2
This study involves 92 Computed Tomography (CT) scans of patients affected by COVID-19. 10 of these scans come from the public dataset “COVID-19 CT Lung and Infection Segmentation Dataset”
We collected a manual segmentation performed by an expert radiologist, which was used as the gold standard

Summary

Introduction

Since the beginning of last year, the world has been facing a health emergency, the pandemic caused by the novel Coronavirus, Sars-CoV2. Among imaging modalities, Computed Tomography (CT) is the most sensitive (60–98%) acquisition technique, but it has low specificity in the early stage of the disease [4] For this reason, World Health Organization (WHO) and most radiologic societies do not recommend performing screening CT (WHO characterizes COVID-19 as a pandemic—11 March 2020). 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. Conclusions: Semisupervised 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

Objectives

Methods

Discussion

Conclusion