An Ordinal Radiomic Model To Predict The Differentiation Grade Of Invasive Non-Mucinous Pulmonary Adenocarcinoma Based On Low-Dose Computed Tomography In Lung Cancer Screening

Objectives: To construct a radiomic model of low-dose CT(LDCT)to predict the differentiation grade of invasive non-mucinous pulmonary adenocarcinoma(IPA)and compare its diagnostic performance with quantitative-semantic model and radiologists.Materials and Methods: A total of 682 pulmonary nodules were divided into primary cohort(181 well differentiated;254 moderately differentiated;64 poorly differentiated)and validation cohort(69 well differentiated;99 moderately differentiated;15 poorly differentiated)according to scanners.The radiomic and quantitative-semantic models were built using ordinal logistic regression.The diagnostic performance of the models and radiologists was assessed by area under curve(AUC)of receiver operating characteristic curve and accuracy.Results: The radiomic model demonstrated excellent diagnostic performance in the validation cohort [AUC,0.900(95%CI: 0.847-0.939)for well differentiated vs.moderately/poorly differentiated;AUC,0.929(95%CI: 0.882-0.962)for well/moderately differentiated vs.poorly differentiated;accuracy,0.803(95%CI: 0.737-0.857)].No significant difference of diagnostic performance was found between the radiomic model and radiological expert [AUC,0.840(95%CI: 0.779-0.890)for well differentiated vs.moderately/poorly differentiated,P = 0.130;AUC,0.852(95%CI:0.793-0.900)for well/ moderately differentiated vs.poorly differentiated,P =0.170;accuracy,0.743(95%CI: 0.673-0.804),P = 0.079],but the radiomic model outperformed the quantitative-semantic model and inexperienced radiologists(all P <0.05).Conclusions: The radiomic model of LDCT could be used to predict the differentiation grade of IPA in lung cancer screening,and its diagnostic performance was comparable to that of radiological expert.