TY - JOUR
T1 - A Multiclass Radiomics Method-Based WHO Severity Scale for Improving COVID-19 Patient Assessment and Disease Characterization From CT Scans
AU - Henao, John Anderson Garcia
AU - Depotter, Arno
AU - Bower, Danielle V.
AU - Bajercius, Herkus
AU - Todorova, Plamena Teodosieva
AU - Saint-James, Hugo
AU - De Mortanges, Aurélie Pahud
AU - Barroso, Maria Cecilia
AU - He, Jianchun
AU - Yang, Junlin
AU - You, Chenyu
AU - Staib, Lawrence H.
AU - Gange, Christopher
AU - Ledda, Roberta Eufrasia
AU - Caminiti, Caterina
AU - Silva, Mario
AU - Cortopassi, Isabel Oliva
AU - Dela Cruz, Charles S.
AU - Hautz, Wolf
AU - Bonel, Harald M.
AU - Sverzellati, Nicola
AU - Duncan, James S.
AU - Reyes, Mauricio
AU - Poellinger, Alexander
N1 - Publisher Copyright:
© Wolters Kluwer Health, Inc. All rights reserved.
PY - 2023/12/1
Y1 - 2023/12/1
N2 - Objectives The aim of this study was to evaluate the severity of COVID-19 patients' disease by comparing a multiclass lung lesion model to a single-class lung lesion model and radiologists' assessments in chest computed tomography scans. Materials and Methods The proposed method, AssessNet-19, was developed in 2 stages in this retrospective study. Four COVID-19-induced tissue lesions were manually segmented to train a 2D-U-Net network for a multiclass segmentation task followed by extensive extraction of radiomic features from the lung lesions. LASSO regression was used to reduce the feature set, and the XGBoost algorithm was trained to classify disease severity based on the World Health Organization Clinical Progression Scale. The model was evaluated using 2 multicenter cohorts: a development cohort of 145 COVID-19-positive patients from 3 centers to train and test the severity prediction model using manually segmented lung lesions. In addition, an evaluation set of 90 COVID-19-positive patients was collected from 2 centers to evaluate AssessNet-19 in a fully automated fashion. Results AssessNet-19 achieved an F1-score of 0.76 ± 0.02 for severity classification in the evaluation set, which was superior to the 3 expert thoracic radiologists (F1 = 0.63 ± 0.02) and the single-class lesion segmentation model (F1 = 0.64 ± 0.02). In addition, AssessNet-19 automated multiclass lesion segmentation obtained a mean Dice score of 0.70 for ground-glass opacity, 0.68 for consolidation, 0.65 for pleural effusion, and 0.30 for band-like structures compared with ground truth. Moreover, it achieved a high agreement with radiologists for quantifying disease extent with Cohen κ of 0.94, 0.92, and 0.95. Conclusions A novel artificial intelligence multiclass radiomics model including 4 lung lesions to assess disease severity based on the World Health Organization Clinical Progression Scale more accurately determines the severity of COVID-19 patients than a single-class model and radiologists' assessment.
AB - Objectives The aim of this study was to evaluate the severity of COVID-19 patients' disease by comparing a multiclass lung lesion model to a single-class lung lesion model and radiologists' assessments in chest computed tomography scans. Materials and Methods The proposed method, AssessNet-19, was developed in 2 stages in this retrospective study. Four COVID-19-induced tissue lesions were manually segmented to train a 2D-U-Net network for a multiclass segmentation task followed by extensive extraction of radiomic features from the lung lesions. LASSO regression was used to reduce the feature set, and the XGBoost algorithm was trained to classify disease severity based on the World Health Organization Clinical Progression Scale. The model was evaluated using 2 multicenter cohorts: a development cohort of 145 COVID-19-positive patients from 3 centers to train and test the severity prediction model using manually segmented lung lesions. In addition, an evaluation set of 90 COVID-19-positive patients was collected from 2 centers to evaluate AssessNet-19 in a fully automated fashion. Results AssessNet-19 achieved an F1-score of 0.76 ± 0.02 for severity classification in the evaluation set, which was superior to the 3 expert thoracic radiologists (F1 = 0.63 ± 0.02) and the single-class lesion segmentation model (F1 = 0.64 ± 0.02). In addition, AssessNet-19 automated multiclass lesion segmentation obtained a mean Dice score of 0.70 for ground-glass opacity, 0.68 for consolidation, 0.65 for pleural effusion, and 0.30 for band-like structures compared with ground truth. Moreover, it achieved a high agreement with radiologists for quantifying disease extent with Cohen κ of 0.94, 0.92, and 0.95. Conclusions A novel artificial intelligence multiclass radiomics model including 4 lung lesions to assess disease severity based on the World Health Organization Clinical Progression Scale more accurately determines the severity of COVID-19 patients than a single-class model and radiologists' assessment.
KW - CT segmentation
KW - pulmonary disease
KW - radiomics modeling
KW - technology assessment
UR - https://www.scopus.com/pages/publications/85176508388
U2 - 10.1097/RLI.0000000000001005
DO - 10.1097/RLI.0000000000001005
M3 - Article
C2 - 37493348
AN - SCOPUS:85176508388
SN - 0020-9996
VL - 58
SP - 882
EP - 893
JO - Investigative Radiology
JF - Investigative Radiology
IS - 12
ER -