Radiomics-based machine learning differentiates “ground-glass” opacities due to COVID-19 from acute non-COVID-19 lung disease
Abstract Ground-glass opacities (GGOs) are a non-specific high-resolution computed tomography (HRCT) finding tipically observed in early Coronavirus disesase 19 (COVID-19) pneumonia. However, GGOs are also seen in other acute lung diseases, thus making challenging the differential diagnosis. To this...
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-08-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-021-96755-0 |
| _version_ | 1818421239755046912 |
|---|---|
| author | Andrea Delli Pizzi Antonio Maria Chiarelli Piero Chiacchiaretta Cristina Valdesi Pierpaolo Croce Domenico Mastrodicasa Michela Villani Stefano Trebeschi Francesco Lorenzo Serafini Consuelo Rosa Giulio Cocco Riccardo Luberti Sabrina Conte Lucia Mazzamurro Manuela Mereu Rosa Lucia Patea Valentina Panara Stefano Marinari Jacopo Vecchiet Massimo Caulo |
| author_facet | Andrea Delli Pizzi Antonio Maria Chiarelli Piero Chiacchiaretta Cristina Valdesi Pierpaolo Croce Domenico Mastrodicasa Michela Villani Stefano Trebeschi Francesco Lorenzo Serafini Consuelo Rosa Giulio Cocco Riccardo Luberti Sabrina Conte Lucia Mazzamurro Manuela Mereu Rosa Lucia Patea Valentina Panara Stefano Marinari Jacopo Vecchiet Massimo Caulo |
| author_sort | Andrea Delli Pizzi |
| collection | DOAJ |
| description | Abstract Ground-glass opacities (GGOs) are a non-specific high-resolution computed tomography (HRCT) finding tipically observed in early Coronavirus disesase 19 (COVID-19) pneumonia. However, GGOs are also seen in other acute lung diseases, thus making challenging the differential diagnosis. To this aim, we investigated the performance of a radiomics-based machine learning method to discriminate GGOs due to COVID-19 from those due to other acute lung diseases. Two sets of patients were included: a first set of 28 patients (COVID) diagnosed with COVID-19 infection confirmed by real-time polymerase chain reaction (RT-PCR) between March and April 2020 having (a) baseline HRCT at hospital admission and (b) predominant GGOs pattern on HRCT; a second set of 30 patients (nCOVID) showing (a) predominant GGOs pattern on HRCT performed between August 2019 and April 2020 and (b) availability of final diagnosis. Two readers independently segmented GGOs on HRCTs using a semi-automated approach, and radiomics features were extracted using a standard open source software (PyRadiomics). Partial least square (PLS) regression was used as the multivariate machine-learning algorithm. A leave-one-out nested cross-validation was implemented. PLS β-weights of radiomics features, including the 5% features with the largest β-weights in magnitude (top 5%), were obtained. The diagnostic performance of the radiomics model was assessed through receiver operating characteristic (ROC) analysis. The Youden’s test assessed sensitivity and specificity of the classification. A null hypothesis probability threshold of 5% was chosen (p < 0.05). The predictive model delivered an AUC of 0.868 (Youden’s index = 0.68, sensitivity = 93%, specificity 75%, p = 4.2 × 10–7). Of the seven features included in the top 5% features, five were texture-related. A radiomics-based machine learning signature showed the potential to accurately differentiate GGOs due to COVID-19 pneumonia from those due to other acute lung diseases. Most of the discriminant radiomics features were texture-related. This approach may assist clinician to adopt the appropriate management early, while improving the triage of patients. |
| first_indexed | 2024-12-14T13:07:12Z |
| format | Article |
| id | doaj.art-ca0ccf9204d9467b9413f9ffef0d7789 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-14T13:07:12Z |
| publishDate | 2021-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-ca0ccf9204d9467b9413f9ffef0d77892022-12-21T23:00:17ZengNature PortfolioScientific Reports2045-23222021-08-011111910.1038/s41598-021-96755-0Radiomics-based machine learning differentiates “ground-glass” opacities due to COVID-19 from acute non-COVID-19 lung diseaseAndrea Delli Pizzi0Antonio Maria Chiarelli1Piero Chiacchiaretta2Cristina Valdesi3Pierpaolo Croce4Domenico Mastrodicasa5Michela Villani6Stefano Trebeschi7Francesco Lorenzo Serafini8Consuelo Rosa9Giulio Cocco10Riccardo Luberti11Sabrina Conte12Lucia Mazzamurro13Manuela Mereu14Rosa Lucia Patea15Valentina Panara16Stefano Marinari17Jacopo Vecchiet18Massimo Caulo19Department of Neuroscience, Imaging and Clinical Sciences, “G. d’Annunzio” UniversityDepartment of Neuroscience, Imaging and Clinical Sciences, “G. d’Annunzio” UniversityCenter of Advanced Studies and Technology (CAST), “G. d’Annunzio” University of Chieti-PescaraDepartment of Radiology, “Santissima Annunziata” Hospital, “G. d’Annunzio” University of ChietiDepartment of Neuroscience, Imaging and Clinical Sciences, “G. d’Annunzio” UniversityDepartment of Radiology, Stanford University School of MedicineDepartment of Radiology, “Santissima Annunziata” Hospital, “G. d’Annunzio” University of ChietiDepartment of Radiology, Netherlands Cancer InstituteDepartment of Neuroscience, Imaging and Clinical Sciences, “G. d’Annunzio” UniversityDepartment of Radiation Oncology, “Santissima Annunziata” Hospital, “G. d’Annunzio” University of ChietiUnit of Ultrasound in Internal Medicine, Department of Medicine and Science of Aging, “G. D’Annunzio” UniversityDepartment of Radiology, “Santissima Annunziata” Hospital, “G. d’Annunzio” University of ChietiDepartment of Radiology, “Santissima Annunziata” Hospital, “G. d’Annunzio” University of ChietiDepartment of Radiology, “Santissima Annunziata” Hospital, “G. d’Annunzio” University of ChietiDepartment of Radiology, “Santissima Annunziata” Hospital, “G. d’Annunzio” University of ChietiDepartment of Radiology, “Santissima Annunziata” Hospital, “G. d’Annunzio” University of ChietiDepartment of Radiology, “Santissima Annunziata” Hospital, “G. d’Annunzio” University of ChietiDepartment of Pneumology, “Santissima Annunziata” Hospital, “G. d’Annunzio” University of ChietiClinic of Infectious Diseases, Department of Medicine and Science of Aging, University ‘G. d’Annunzio’ Chieti-PescaraDepartment of Neuroscience, Imaging and Clinical Sciences, “G. d’Annunzio” UniversityAbstract Ground-glass opacities (GGOs) are a non-specific high-resolution computed tomography (HRCT) finding tipically observed in early Coronavirus disesase 19 (COVID-19) pneumonia. However, GGOs are also seen in other acute lung diseases, thus making challenging the differential diagnosis. To this aim, we investigated the performance of a radiomics-based machine learning method to discriminate GGOs due to COVID-19 from those due to other acute lung diseases. Two sets of patients were included: a first set of 28 patients (COVID) diagnosed with COVID-19 infection confirmed by real-time polymerase chain reaction (RT-PCR) between March and April 2020 having (a) baseline HRCT at hospital admission and (b) predominant GGOs pattern on HRCT; a second set of 30 patients (nCOVID) showing (a) predominant GGOs pattern on HRCT performed between August 2019 and April 2020 and (b) availability of final diagnosis. Two readers independently segmented GGOs on HRCTs using a semi-automated approach, and radiomics features were extracted using a standard open source software (PyRadiomics). Partial least square (PLS) regression was used as the multivariate machine-learning algorithm. A leave-one-out nested cross-validation was implemented. PLS β-weights of radiomics features, including the 5% features with the largest β-weights in magnitude (top 5%), were obtained. The diagnostic performance of the radiomics model was assessed through receiver operating characteristic (ROC) analysis. The Youden’s test assessed sensitivity and specificity of the classification. A null hypothesis probability threshold of 5% was chosen (p < 0.05). The predictive model delivered an AUC of 0.868 (Youden’s index = 0.68, sensitivity = 93%, specificity 75%, p = 4.2 × 10–7). Of the seven features included in the top 5% features, five were texture-related. A radiomics-based machine learning signature showed the potential to accurately differentiate GGOs due to COVID-19 pneumonia from those due to other acute lung diseases. Most of the discriminant radiomics features were texture-related. This approach may assist clinician to adopt the appropriate management early, while improving the triage of patients.https://doi.org/10.1038/s41598-021-96755-0 |
| spellingShingle | Andrea Delli Pizzi Antonio Maria Chiarelli Piero Chiacchiaretta Cristina Valdesi Pierpaolo Croce Domenico Mastrodicasa Michela Villani Stefano Trebeschi Francesco Lorenzo Serafini Consuelo Rosa Giulio Cocco Riccardo Luberti Sabrina Conte Lucia Mazzamurro Manuela Mereu Rosa Lucia Patea Valentina Panara Stefano Marinari Jacopo Vecchiet Massimo Caulo Radiomics-based machine learning differentiates “ground-glass” opacities due to COVID-19 from acute non-COVID-19 lung disease Scientific Reports |
| title | Radiomics-based machine learning differentiates “ground-glass” opacities due to COVID-19 from acute non-COVID-19 lung disease |
| title_full | Radiomics-based machine learning differentiates “ground-glass” opacities due to COVID-19 from acute non-COVID-19 lung disease |
| title_fullStr | Radiomics-based machine learning differentiates “ground-glass” opacities due to COVID-19 from acute non-COVID-19 lung disease |
| title_full_unstemmed | Radiomics-based machine learning differentiates “ground-glass” opacities due to COVID-19 from acute non-COVID-19 lung disease |
| title_short | Radiomics-based machine learning differentiates “ground-glass” opacities due to COVID-19 from acute non-COVID-19 lung disease |
| title_sort | radiomics based machine learning differentiates ground glass opacities due to covid 19 from acute non covid 19 lung disease |
| url | https://doi.org/10.1038/s41598-021-96755-0 |
| work_keys_str_mv | AT andreadellipizzi radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT antoniomariachiarelli radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT pierochiacchiaretta radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT cristinavaldesi radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT pierpaolocroce radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT domenicomastrodicasa radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT michelavillani radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT stefanotrebeschi radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT francescolorenzoserafini radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT consuelorosa radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT giuliococco radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT riccardoluberti radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT sabrinaconte radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT luciamazzamurro radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT manuelamereu radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT rosaluciapatea radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT valentinapanara radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT stefanomarinari radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT jacopovecchiet radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease AT massimocaulo radiomicsbasedmachinelearningdifferentiatesgroundglassopacitiesduetocovid19fromacutenoncovid19lungdisease |